Workflow & Prompting — AI Agents, Skills & Tools
Agents, skills, guides, tools, and commands for workflow & prompting — 314 curated resources for building with AI coding agents.
Annotation Evidence Reviewer
Review a supervised text-label adjudication packet for traceable excerpts, preserved independent responses and rule-supported resolutions; flag missing evidence without choosing final labels.
Entity Match Reviewer
Review an entity-match candidate ledger against supplied records and owner criteria; flag unsupported match decisions, conflicting fields and transitive contradictions without merging or identifying people.
Exit Ticket Reviewer
Review a draft exit ticket against educator-supplied objectives and taught material. Flag untaught facts, unclear prompts, mismatched answer keys and gaps in objective coverage; return revisions for educator judgment without grading learners or diagnosing ability.
Literature Screening Reviewer
Use this agent to audit a literature screening log against a supplied protocol and local abstracts or paper extracts: trace each eligibility judgment to criteria and source text, flag unsupported exclusions, identify unresolved eligibility, and record protocol drift. Review the log without searching the web or changing inclusion decisions.
Study Card Reviewer
Review a draft flashcard set against supplied notes and stated learning targets. Identify unsupported answers, compound questions, duplicate targets and source conflicts in a card-by-card report; do not draft a new set, schedule practice or infer learner ability.
Prompt Engineer
Use this agent to design and iterate the prompts behind an LLM-powered product feature — instructions, few-shot examples, tool schemas, and the evals that prove a change actually helped. Examples — "this classification prompt is flaky, make it reliable", "design the system prompt and function schema for our support agent", "our extraction prompt regressed after I tweaked it, set up evals so this stops happening".
Image Description Reviewer
Review still-image text alternatives against page purpose, verified visual evidence and source data; flag missing meaning, invented detail and chart-description conflicts without claiming conformance.
Documentation Engineer
Use this agent to write and maintain technical docs that stay true to the code — READMEs, how-to guides, API references, and runbooks. Examples — updating a stale README after a refactor, documenting a new public API from its signatures, writing an on-call runbook for a service.
Git Github Expert
Use this agent for Git and GitHub workflows — rebases, conflict resolution, history surgery, PRs, and Actions. Examples — resolving a messy merge, rewriting history safely, fixing a workflow file.
Content Editor
Use this agent to edit marketing and editorial drafts (blog posts, landing pages, emails, social copy, newsletters) for clarity and brand voice while marking every unsourced claim, statistic, and superlative with a [CITATION NEEDED] or [VERIFY] tag and a one-line reason, never inventing a source, and returning the edited draft with a change log. Examples — 'edit this post before it goes to the client', 'tighten this launch email and tell me which numbers I need to back up', 'check this page copy against brand-voice.md and mark anything we cannot prove'.
Localization Copy Reviewer
Review paired source and translated marketing or help-document text for a specified locale against supplied terminology and style rules: flag lost meaning, negation, conditions, numbers, protected terms and ambiguous segments, with evidence-linked proposals for a human language reviewer.
Agent Architect
Use this agent to design a new Claude Code subagent or review an existing one — scoping, description, toolset, model, and output contract. Examples — "design an agent that triages flaky tests", "review my code-reviewer agent for scope creep", "why won't Claude auto-delegate to my agent?".
Context Engineer
Use this agent to engineer what an LLM agent carries in its context window — deciding what to include vs exclude vs retrieve on demand, designing project/agent memory (CLAUDE.md), compacting growing history, and allocating the token budget across system prompt, memory, retrieved docs, tool results, and conversation. Examples — "my agent forgets the schema we agreed on three turns ago", "the agent gets dumber and more inconsistent as the chat grows", "we're burning 60k tokens of tool output every turn", "what should this support agent always know vs look up?".
Workflow Orchestrator
Use this agent to break large tasks into coordinated multi-step plans and delegate to other agents. Examples — planning a multi-file refactor, orchestrating a migration, decomposing an epic.
Contract Obligation Reviewer
Compare a prepared vendor-contract obligation register with supplied agreement and amendment text: flag missing qualifying language, unsupported dates or parties, unresolved cross-references, and unproven supersession. Return a source-linked review packet for qualified counsel; do not give legal conclusions or approve terms.
Interview Scorecard Reviewer
Review a draft interview scorecard against supplied job tasks: flag criteria lacking job evidence, vague behavioral anchors, inconsistent question coverage, and unsupported weights before interviews. Review the rubric only; never score, rank, infer traits about, or select candidates.
Procedure Exception Reviewer
Review a drafted workplace SOP against captured walkthroughs and supplied exception cases: identify absent branches, unmet prerequisites, unclear stop conditions, and unsupported recovery steps without executing or editing the procedure.
Project Handoff Auditor
Use this agent to review a prepared human-to-human project handoff against its local source files: find missing deliverables, unsupported completion claims, unclear ownership, stale or conflicting decisions, and questions the receiving teammate cannot resolve from the packet. Report evidence and fixes without editing the packet.
Support Answer Auditor
Review prepared customer-support answer cards against supplied policy versions and applicability rules: flag unsupported promises, omitted eligibility conditions, contradictory answers, and missing escalation boundaries before the library is approved.
Survey Design Reviewer
Use this agent to review a draft customer survey before collection: check leading wording, double-barreled questions, missing response options, inconsistent scales, unsupported recall periods, and whether each question can answer the stated research objective. Return an annotated review and proposed rewrites without changing the survey.
Technical Cofounder
Use this agent when a non-technical founder needs an app built by an AI app builder or coding agent reviewed for the problems that hurt founders: missing login and permission checks, secrets committed to the code, customer data visible to the wrong users, surprise cloud and API bills, vendor lock-in, no backups, and no tests. It explains each finding in plain language with a severity and the question to ask an engineer. Examples — 'look over what Lovable built before I launch', 'is this Supabase app safe for real customer data', 'what will bite me if I ship this Claude Code project'.
RFP Completeness Reviewer
Review a prepared RFP submission against supplied requirements, addenda and attachment rules: find unanswered subparts, omitted documents, unproven exceptions, contradictory IDs and submission-rule gaps. Return an evidence-linked completeness review without drafting sales claims or submitting a bid.
Sales Engineer
Use this agent to review the technical asks a prospect has put in front of a deal — security questionnaires, integration and API requirements, SSO and provisioning, SLA and uptime demands, data residency and retention terms, custom feature requests — and separate what the product does today from what needs engineering, with evidence for each verdict from the product's own docs and code. It writes the answer language a rep can safely send, and flags the commitments nobody should make without Engineering, Security, Legal, or Finance signing off. Examples — 'they want SSO, SCIM and EU data residency, what can we say yes to', 'review this integration requirements doc before Thursday's technical call', 'they are asking for a 99.99% SLA and two-hour breach notification, tell me what we cannot commit to'.
Entity Match Candidate Ledger
Build a field-evidence ledger for proposed duplicate or cross-source record pairs, preserving source keys, original values and match/different/unresolved owner decisions without merging records.
Annotation Disagreement Ledger
Build an adjudication ledger from conflicting supervised text-label responses, preserving original reviewer labels, exact excerpts, task-rule versions and unresolved owner decisions.
Annotation Task Spec Builder
Specify the record and annotation-interface contract for an owner-defined supervised text-labeling task: approved label IDs, input text, model suggestions, human response fields and abstain handling.
Prompt Regression Tester
Build a regression test harness for an LLM prompt so a prompt edit or model upgrade can't silently degrade quality — a fixed eval set, checkable assertions, and a diff against a committed baseline. Use when changing a production prompt, migrating model versions, or any time 'I tweaked the prompt' needs to be backed by evidence instead of eyeballing two outputs.
Research Evidence Extractor
Extract a structured study evidence table from supplied paper text or readable research excerpts using a user-defined column schema: record study and source IDs, methods, population, outcomes, units, time points, source locations, and missing data. Use after papers have been selected and before synthesis; do not search for papers, decide eligibility, compute pooled effects, or draft conclusions.
3D Asset Handoff Sheet
Build a 3D asset handoff sheet from supplied export metadata, target-app technical reports and human viewer notes, preserving mesh/UV/material versions and untested checks.
Image Description Draft
Draft purpose-specific still-image text alternatives from supplied verified visual observations and page context, separating short alt text from complex-image long-description needs.
Code Example Verifier
Verify documentation code examples against the current repository and toolchain, then fix snippets, imports, commands, and expected output without changing the documented intent. Use when docs examples may be stale, an SDK or API changed, users report copy-paste failures, or before publishing tutorials, READMEs, migration guides, and release documentation.
Contract Obligation Register
Extract a draft vendor-contract obligation register from supplied agreement text with parties, duties, triggers, timing wording, conditions, exceptions, cross-references and exact section evidence. Use to prepare a qualified reviewer’s packet; do not interpret enforceability, choose controlling terms, or invent deadlines.
Decision Log Reconciler
Reconcile an existing business-project decision log with supplied dated notes and change records: connect decisions to evidence, preserve explicit supersession links, separate accepted choices from proposals, and list contradictions awaiting an owner. Use when project records disagree about what was decided; do not write an architectural ADR or create meeting minutes.
Exit Ticket Builder
Draft a short exit ticket from educator-approved learning objectives and taught material, mapping each question to an objective with an answer key and evidence. Use for low-stakes instructional feedback; do not grade student submissions, diagnose needs or invent curriculum standards.
Onboarding Guide Writer
Write a developer onboarding guide that gets a new contributor from clone to first merged change fast — a verified golden path, a quick architecture map, the real workflow conventions, and the gotchas that live only in senior engineers' heads. Use when a repo has no onboarding doc, when new hires keep asking the same setup questions, or when the README is a marketing page instead of a contributor guide.
Process to SOP
Convert supplied workplace walkthrough notes or readable process captures into one draft SOP with sourced steps, explicit inputs and outputs, observed branches, stop conditions, and an owner review queue. Use after a real process has been captured; do not invent policy or write an incident runbook.
Readme Generator
Generate or refresh a project README grounded in the actual repository. Use when a project has no README, a stale one, or you want install/usage/scripts/structure sections that match the real code.
Source Concept Map Builder
Build a concept-node and relationship table from supplied document passages for one focal question, preserving source locations and contested edges before an AI mind map is drawn.
Support Answer Card Builder
Draft one reusable customer-support answer card per supplied policy question, with approved source locators, applicability, required facts, concise answer wording, exclusions, and an escalation boundary. Use when turning documented policies into an answer library; do not invent policy or send replies.
Branch Rebaser
Rebase the current branch onto its base and walk every conflict methodically, resolving each by understanding both sides. Use when your feature branch has fallen behind main and you want a clean, linear history without clobbering changes.
Conventional Commits
Generate clear Conventional Commits messages from staged changes. Use when committing code and you want a well-structured, consistent commit message.
Asset Metadata Review Ledger
Map AI-suggested media catalog tags to a supplied controlled vocabulary and asset-version evidence, returning accept/reject/unresolved rows without inferring identities or usage rights.
Brand Voice Profiler
Derive a reusable brand voice guide from five to ten writing samples you paste in: tone axes scored with quoted evidence, use and avoid vocabulary, sentence rhythm, formatting habits, dos and don'ts, three before/after rewrites, and a rules block ready to paste into a SKILL.md, with every rule traced to a sample and disagreements between samples flagged instead of averaged. Use when your team writes in a recognizable voice that nobody has written down, or the guide you have was never derived from what you actually publish.
Content Repurposer
Turn one long-form piece you paste in (an article, transcript, webinar summary, or case study) into four channel-ready derivatives, an X thread, a LinkedIn post, a newsletter section, and a short-video script, each inside its channel's length and format limits, with every claim and number carried over exactly as written and any statistic the original does not source flagged instead of repeated as fact. Use when a finished piece has to go out on several channels and the derivatives must say only what the original says.
Email Sequence Drafter
Draft a four-to-six email sequence from a goal, an audience, and the product notes you paste in: a send-timing table, one job per email, three subject-line variants per email with character counts, a formatted and a plain-text version of each message, every product claim traced to your notes, and a compliance footer placeholder on every email. Use when a welcome, onboarding, launch, or nurture sequence has to be written from what the product actually does rather than from what a template assumes.
Landing Page Copywriter
Draft landing-page copy from an offer, an audience, and the proof points you actually have, as a complete section set (hero, problem, solution, how it works, proof, pricing framing, FAQ, and three CTA variants) in PAS or AIDA, with a [PROOF NEEDED] marker wherever a testimonial, number, or logo would normally sit but was not supplied. Use when a page needs first-draft copy and you would rather see the gaps than have them filled with invented social proof.
Localization Glossary Builder
Build a draft bilingual terminology glossary from supplied source-target samples and product references: retain term IDs, approved equivalents, protected strings, context, disallowed variants and unresolved translations. Use before reviewing localized marketing or help copy; do not translate a whole document or invent approved terms.
Seo Content Brief Writer
Write an SEO content brief from a target keyword plus the SERP notes and competitor outlines you paste in: search intent with evidence, an angle the ranking pages under-serve, an H2/H3 outline, the entities and questions to cover, internal-link placeholders, a length-checked meta title and description, and a word-count target explained by the SERP rather than a rule of thumb. Use when a writer or a coding agent needs a brief before drafting an article and you do not want search volumes, difficulty scores, or rankings invented.
Competitor Teardown
Build a structured teardown of one competitor from the pages, screenshots, and pricing text you paste in: positioning, target customer, pricing model, a feature table with evidence, and the wedge opportunities where you could win, with every unknown flagged as something to research rather than guessed. Use when sizing up a competitor before a PRD, a pitch, or a pricing decision and you want an analysis grounded only in what they publish.
Feedback Codebook Designer
Design a versioned coding codebook for recurring customer-feedback classification from a supplied pilot sample: define one code per job with inclusion rules, exclusions, verbatim examples, boundary cases, and an unresolved bucket. Use before labeling support tickets or survey comments, or when a feedback taxonomy has overlapping labels; do not synthesize interviews or rank product priorities.
Investor Update Writer
Draft a monthly investor update from the metrics and notes you paste: a three-line TL;DR, a metrics table with month-over-month deltas computed only from the numbers you supplied, wins, misses stated with their numbers, explicit asks, and a runway note. Never fills in a figure you did not give. Use when the update is due, the raw numbers are in a spreadsheet export or a scratch doc, and you want a draft that is honest about the misses.
Job Scorecard Builder
Draft a pre-interview job scorecard from supplied role tasks and human-selected priorities: map each criterion to task evidence, write observable three-level anchors and interview prompts, and preserve unresolved weighting choices. Use before interviewing; do not assess or rank candidates.
Mvp Scope Cutter
Cut a feature list or PRD down to a ruthless version one: a keep / cut / later table with a one-line reason per row, plus the single smallest thing you could build to test the riskiest assumption. Use when first-release scope keeps growing, when an AI app builder session has produced more features than you can validate, or before you commit money or engineering time to a build.
Prd Writer
Turn a founder's raw idea, voice-memo transcript, or scattered bullet points into a product requirements document with a fixed section order: problem, users, jobs-to-be-done, scope, non-goals, success metrics, open questions, and risks. Use when an idea needs to be written down in a form a cofounder, contractor, or AI coding agent can build from, and it is not yet a document.
Survey Path Test Builder
Build a survey-paths.json test packet from approved single-choice question IDs, complete answer-to-destination rules and named endings; preserve missing routes for owner resolution.
User Interview Synthesizer
Synthesize one or many customer interview transcripts or call notes into themes with participant counts, verbatim representative quotes, jobs-to-be-done statements, contradictions between what people said and did, and the questions to ask next. Never invents, merges, or rewords a quote. Use after a batch of discovery calls when the notes are piling up and you need to know what people actually said before deciding what to build.
Changelog From PRs
Draft a release changelog by summarizing merged pull requests since the last tag. Use when preparing a release or writing release notes.
Rollback Plan Writer
Write a tested rollback and forward-recovery plan for a release, including triggers, commands, compatibility constraints, data handling, verification, ownership, and stop conditions. Use before high-risk deploys, schema or configuration changes, dependency upgrades, model or provider migrations, feature launches, and any release where 'just redeploy the old version' is incomplete or unsafe.
Cold Email Deliverability Auditor
Audit a cold email program's sending setup and message body against the things that decide whether mail reaches an inbox: SPF, DKIM and DMARC records with their alignment and policy, the DNS lookup limit, a separate sending domain versus the primary corporate one, domain age and warmup state, list hygiene with bounce and complaint exposure, spam-trigger language, link and image ratio, unsubscribe presence, and the volume ramp per mailbox. Findings come back by severity with the concrete fix and the order to apply them. Use when a sending domain is new, replies have collapsed, or nobody has checked the DNS records, the list, and the copy in the same sitting.
Crm Export Auditor
Audit a CRM CSV export for the data faults that make every report built on it wrong: exact and near-duplicate accounts and contacts, close dates already in the past on open deals, deals with no activity in the last N days, blank required fields by stage, single-threaded deals carrying one contact, records with no owner or a departed one, stage and amount combinations that contradict each other, and currency, date and country formats that drift between rows. Returns a fix list ordered by how much each fault distorts a reported number, with the record IDs to correct and which fixes are safe to apply in bulk. Use when a pipeline number is disputed, when a migration or a dedupe is being planned, or when nobody has checked the export the forecast is built on.
Outreach Claim Checker
Check every factual and personalization claim in a drafted outreach email, or a batch of them, against the research the draft was written from: funding rounds, job titles and recent moves, tech stack, headcount, product launches and press, and named mutual connections. Each claim is marked sourced with the line that supports it, unsourced, contradicted, or stale, then unsupported specifics are cut or narrowed to what the research actually says, and every email leaves with a send, fix, or hold verdict. A source is never invented and never inferred. Use when outreach was personalized from AI or analyst research and nobody has verified the details before it reaches a prospect.
RFP Requirement Mapper
Turn supplied RFP instructions and explicit addenda into a draft atomic compliance matrix: preserve requirement IDs and wording, split subparts visibly, map response/evidence locators, and flag missing mandatory or exception authority. Use before assembling a bid; do not write persuasive answers or invent compliance claims.
Security Questionnaire Responder
Draft answers to a prospect's security questionnaire — a SIG, a CAIQ, a VSA, or a custom spreadsheet — strictly from the documents the company supplies: the SOC 2 report, the DPA, the subprocessor list, a penetration test summary, architecture and access-control notes. Every answer is tagged sourced with the document and section it came from, needs-review, or not-applicable with the reason, and a control that appears in no document is left unanswered rather than asserted. Anything touching contractual terms, breach-notification windows, data residency, roadmap dates, or an exception is routed to Legal or Security by name. Use when a deal is blocked on a questionnaire and every answer has to survive an auditor reading it back.
Agent Memory Designer
Design a project's CLAUDE.md and memory hierarchy by exploring the repo to learn its real build/test/lint commands, architecture, and non-obvious gotchas, then writing a concise, skimmable memory that keeps only what belongs in context. Use when onboarding a repo to Claude Code with no CLAUDE.md, or when an existing one is bloated, stale, or being ignored.
Claude Settings Auditor
Audit every Claude Code settings layer — user, project, local, and managed — and report the effective merged configuration with its risks: over-broad Bash allows, missing deny rules for secrets, bypassPermissions defaults, unvetted MCP servers and hooks, and rules that never match. Use before trusting a new repo's checked-in settings, or to harden your own before handing the agent more autonomy.
Hook Writer
Turn a plain-language automation request — 'format every file Claude edits', 'block writes to migrations', 'notify me when input is needed' — into a working Claude Code hook: the right event, a safe tested script, and the settings.json registration at the right scope. Use when you want a hook but don't want to hand-write the matcher, stdin JSON parsing, and exit-code plumbing.
Plugin Scaffolder
Scaffold a complete, valid Claude Code plugin from a description — the .claude-plugin/plugin.json manifest, component directories (skills, agents, commands, hooks, MCP config), portable ${CLAUDE_PLUGIN_ROOT} wiring, a local test loop with --plugin-dir, and a marketplace.json for distribution. Use when turning scattered .claude/ customizations into one installable, versioned package.
Prompt Optimizer
Diagnose why a prompt underperforms and rewrite it with the technique that fixes it — clearer structure, few-shot examples, an explicit output contract, or reasoning scaffolding — returning an optimized prompt, the rationale for every change, and what to measure to confirm the lift. Use when a prompt is flaky, verbose, drifting in format, or just not good enough.
Skill Auditor
Audit an installed set of Claude Code skills for the failure modes that make them misfire — overlapping descriptions that misroute tasks, trigger phrasing that never matches, bloated bodies, missing boundaries, and over-broad tool grants — and return a prioritized fix list with rewritten descriptions. Use when a skill fires on the wrong tasks, never fires at all, or a skills folder has grown past what anyone reviews.
Study Card Builder
Draft source-grounded study flashcards from approved notes for one stated learning goal, with question, answer, exact evidence quote, source locator and unresolved status. Use before learner review; do not generate classroom assessments, final grades or a study schedule.
Building Multi-Step Agent Workflows
Patterns for building multi-step agent workflows in Claude Code: decompose tasks, fan-out to parallel subagents, verify every step, and orchestrate.
Building Agents with the Claude Agent SDK
A working tutorial for the Claude Agent SDK in TypeScript and Python — query(), tool permissions, custom in-process MCP tools, subagents, hooks, and auth.
Running Claude Code in CI: Headless Mode & GitHub Actions
Claude Code without the terminal — claude -p flags, JSON and structured output, safe permission scoping, and the official GitHub Action responding to @claude.
Codex Subagents: Parallel Work Without Losing Control
Use Codex subagents for parallel exploration, review, tests, and implementation — including decomposition, custom agents, permissions, and merge discipline.
Multi-Agent Orchestration
Four patterns for coordinating multiple agents — fan-out, pipeline, orchestrator-worker, and verify/critic — and when each earns its overhead.
Parallel Claude Code Sessions with Git Worktrees
Run several Claude Code sessions at once without edits colliding — the built-in claude --worktree flag, .worktreeinclude, subagent isolation, and cleanup.
Are Claude Skills Safe? A Security Review Checklist
Skills are an instruction supply chain: what can go wrong with third-party SKILL.md files, and the review checklist before installing or distributing one.
Review AI Duplicate-Record Candidates Before Merging
Separate duplicate-record candidate generation from human match decisions, retaining source keys and field evidence before any merge.
Link Records Across Datasets with AI-Assisted Review
Build a cross-source entity crosswalk that preserves both record keys, unresolved candidates and cardinality decisions without silently joining or merging data.
Base44 vs Lovable: Which AI App Builder for Non-Technical Founders?
Base44 vs Lovable for non-technical founders: Base44's all-in-one managed backend and hosting versus Lovable's Supabase stack with GitHub sync. Verdict first.
The Best AI Tools for Founders in 2026
The AI tools founders run a company on in 2026: assistants, app builders, agents and automation, decks and docs, and building, with a verdict per category.
The Best AI Tools for Marketers in 2026
The AI tools marketers run a content program on in 2026: assistants, writing, SEO, research, decks, video, and automation, with a verdict per category.
The Best AI Writing Tools in 2026
Six AI writing tools compared by job: long-form, ad copy, email, and writing inside Docs or Word. Jasper, Copy.ai, Claude, ChatGPT, Gemini, and Copilot.
The Best Claude Code Alternatives in 2026 (Free, Open-Source, and Paid)
The best Claude Code alternatives in 2026, sorted by why you're leaving: cost, open source, local models, an IDE, cloud agents, or OpenAI and Google.
The Best GitHub Copilot Alternatives in 2026 (Free and Paid)
The best GitHub Copilot alternatives in 2026: AI-native editors, open-source VS Code and JetBrains agents, self-hosted assistants and terminal agents.
ChatGPT Projects vs Claude Projects for Teams
Compare shared AI project context in ChatGPT and Claude, then build a team brief with clear instructions, source ownership, and a review process.
Claude Code vs Codex CLI: Terminal Agents Compared (2026)
Claude Code vs OpenAI's Codex CLI — autonomy vs sandboxed control, extensibility vs open source, model ecosystems, and which terminal agent fits your work.
Claude Code vs Cursor: Which AI Coding Tool in 2026?
Claude Code vs Cursor compared honestly — terminal agent vs AI-first editor, autonomy vs inline control, pricing models, and when to run both.
Claude Code vs OpenCode: First-Party vs Open Source (2026)
Claude Code vs OpenCode — Anthropic's tuned first-party agent vs the most-starred open-source one with 75+ providers. Control vs polish, decided honestly.
Claude Skills vs Custom GPTs: Different Answers to Reuse
Claude Skills are portable procedures; Custom GPTs are packaged chatbots inside ChatGPT. How they differ on portability, API access, sharing, and where each wins.
Claude vs ChatGPT for Writing and Marketing Copy
Claude vs ChatGPT for writing, compared on voice control, document creation, research grounding, collaboration, brand-voice enforcement, and agentic work.
Cursor vs Windsurf (Devin Desktop) in 2026
Cursor vs Windsurf — now Devin Desktop — compared: agent-first editing, Composer vs Devin Local, the Cognition rebrand, and which AI editor fits you.
GitHub Copilot vs Cursor: Extension or Editor? (2026)
GitHub Copilot vs Cursor compared — stay in your editor with an extension, or switch to an AI-first fork? Completion, agents, enterprise fit, and pricing shape.
Lovable vs Claude Code: Builder or Agent?
Lovable vs Claude Code for founders: the chat app builder that gives you a working product versus the coding agent that changes a real codebase. Verdict first.
Surfer vs Clearscope: Which SEO Content Tool in 2026?
Surfer vs Clearscope compared on the content editor, briefs, audits, AI writing, AI-visibility tracking, integrations, and pricing model, with a verdict first.
Claude Code Hooks: Automate Formatting, Tests, and Guardrails
How Claude Code hooks work — the major hook events, the settings.json configuration shape, exit codes and JSON output, plus three hooks worth copying.
Managing Claude Code Memory & Context: CLAUDE.md, /compact, and Auto-Memory
How Claude Code remembers — every CLAUDE.md scope and load order, path-scoped rules, the auto-memory system, and the context commands that keep sessions sharp.
Claude Code Plugins: Install, Use, and Build Your Own
How Claude Code plugins work — what they can bundle, the /plugin and marketplace commands, the plugin.json manifest, and building and testing your own.
Claude Code Settings & Permissions: settings.json Explained
Every Claude Code settings file and which one wins, the permission-rule syntax with its Bash matching gotchas, modes, and a safe starter settings.json.
Claude Code Slash Commands: The Built-in List and How to Write Your Own
Claude Code's built-in slash commands grouped by job, and how to write your own as skills: file format, frontmatter, arguments, and plugin namespacing.
CLAUDE.md Best Practices
How to write a CLAUDE.md that actually helps — what to include, what to leave out, and how to keep it current.
AGENTS.md for Codex: Project Instructions That Actually Work
Write an effective AGENTS.md for OpenAI Codex — what belongs in it, how nested overrides work, and how to verify the instructions Codex loaded.
Codex config.toml: Settings, Precedence, and Safe Defaults
Configure OpenAI Codex with config.toml — user and project scopes, precedence, sandbox and approvals, MCP, subagents, profiles, and safe defaults.
Codex CLI Sandbox and Approvals in 2026: Auto-Approve, Full Access, Web Search
Set Codex CLI's approval policy and sandbox mode: auto-approve without --full-auto, safe full access, network access, web search, profiles, and fixes.
Adjudicate AI-Assisted Text Labels with an Evidence Ledger
Resolve disputed text labels by preserving each response, source excerpt and task-rule version rather than accepting the model or majority automatically.
Prelabel a Text Dataset with AI Without Replacing Review
Prepare a small supervised text-labeling batch with separate model suggestions and human responses, using stable record IDs and an approved task specification.
Review AI Alt Text in the Context of Its Page
Draft image text alternatives from actual image evidence and page purpose, then review informative, decorative and functional uses before publishing.
Draft AI Chart Long Descriptions from Verified Data
Review a chart-description draft against the frozen source table, actual visual observations and its implemented page placement.
Create an AI Explanatory Diagram from Approved Text
Choose a diagram that preserves the relationships in approved text, then inspect labels, arrows and the exported visual before reuse.
Review AI-Generated 3D Meshes Before Asset Handoff
Evaluate an AI-generated mesh against a named target app and supplied asset requirements, using real inspection reports and human view checks.
Review AI PBR Texture Imports Against the Target Material
Check an AI texture set in its actual target material setup, preserving map roles, UV information and viewer evidence before approving the asset.
Build an Interview Scorecard with AI from Job Evidence
Build an interview scorecard with AI using approved job tasks, observable competencies, shared questions, rating anchors, and human rubric review.
Automating Startup Ops Without Engineers: Cowork, n8n, Zapier Agents, Lindy
Four ways to automate startup ops without an engineer: Claude Cowork, n8n, Zapier Agents, and Lindy compared, with a worked example each and the approval step.
Build an MVP with Claude Code: Idea to Deployed App in a Weekend
A non-developer's weekend plan for an MVP with Claude Code: one-page spec, a boring stack, tests as you go, Supabase for auth and data, Vercel to deploy.
Claude Code for Non-Developers and Founders: The Complete 2026 Guide
What Claude Code actually is in plain language, why non-developers use it, how permissions and CLAUDE.md work, and the first three tasks a founder should try.
Claude for Founders: Which Claude Product for Which Job
A surface map for founders: when to use claude.ai, Claude Design, Cowork, Claude Code, Claude for Excel, and Claude in Chrome, with a job-to-product table.
Claude Skills for Founders: 5 to Upload Today
Five Claude skills built for founders (PRD, MVP scope, interview synthesis, competitor teardown, investor update), how to upload them, and a prompt for each.
When Your Lovable or Bolt App Outgrows the Builder
Signs your Lovable or Bolt app has outgrown its builder, how GitHub sync gives you a repository, and what to audit first with Claude Code: auth, secrets, RLS.
Which Claude Plan (and Model) Should a Founder Pay For?
A decision guide by situation: solo pre-product, an MVP build with Claude Code, ops with Cowork, or a small team. Plan names and model choice, no prices.
The AI Engineer Roadmap for 2026
A staged path from API calls to production agents — the skills that matter in 2026, what to skip, and the guides and tools for each stage, in order.
The Best Claude Code Agents, Skills & Commands to Install First
A curated starter kit from the AgentsCamp library — the subagents, skills, and slash commands that pay off immediately, by workflow.
Choosing the Right Model: Haiku vs Sonnet vs Opus
How to pick the right Claude model tier — Haiku, Sonnet, or Opus — for any Claude Code agent or task, with a clear decision rubric and per-agent examples.
25 Claude Code Tips, Shortcuts, and Power Features
The 25 highest-leverage Claude Code tips — keyboard shortcuts, bash and memory prefixes, session commands, model tricks, and power features most people miss.
Anthropic's Knowledge-Work Plugins: Every Role Plugin, Explained
Every Anthropic knowledge-work plugin for Claude Cowork and Claude Code cataloged: what each role plugin bundles, the install commands, and how to fork one.
Claude Free vs Pro vs Max vs Team (2026): Which Plan Unlocks What
Every Claude plan compared as of September 2026: prices, usage tiers, and which plan unlocks Claude Code, Cowork, Design, Excel, Chrome, projects, and models.
Getting Started with Claude Code Agents
What Claude Code subagents are, why they help, and how to add your first one.
Installing Claude Code
Install Claude Code, authenticate, start a session in a real project, and add a minimal CLAUDE.md.
OpenAI Codex: A Practical Guide for Developers
Learn how OpenAI Codex works across the terminal, IDE, desktop app, and cloud — then set up a safe, repeatable workflow for real repositories.
How to Update Claude Code (and Fix Update Errors)
Update Claude Code for every install method: claude update vs npm install -g, auto-update channels, pinning a version, and fixes for common update errors.
What Is Claude Code?
A grounded explanation of Claude Code: an agentic command-line coding tool that reads files, runs commands, and works in a loop toward a goal.
Writing Your First Custom Agent
A step-by-step guide to authoring a focused, effective custom subagent.
Test AI Asset Search with Known Asset Examples
Evaluate asset discovery with a small set of known examples, expected exclusions and reviewed results before relying on natural-language catalog search.
Does AI-Written Content Rank in 2026? What Google Actually Says
What Google's own documentation says about AI-generated content in 2026: what it rewards, what scaled content abuse is, how AI features cite, and a checklist.
Review AI Digital Asset Metadata with a Controlled Vocabulary
Review AI-suggested asset tags against a supplied vocabulary, original asset versions and human visual observations before changing a catalog.
Review AI Localization with a Glossary and Source-Target Checks
Review AI-translated copy with a source-target register, approved terminology, protected placeholders, contextual checks, and qualified language review.
Build a Brand-Voice Skill for Claude (and Upload It Anywhere)
Turn 5-10 samples of your copy into a SKILL.md brand-voice skill, then upload it to claude.ai, install it in Claude Code, use it in Cowork, and test it.
Claude Code for Marketers: The Complete 2026 Guide
Why a marketer would open a terminal agent, when claude.ai or Cowork is the better tool, a CLAUDE.md for a content repo, five workflows, and what goes wrong.
Claude for Marketing Teams: claude.ai, Cowork, Claude Design, and Connectors
A surface map for marketing teams: which Claude product to open for brand context, asset folders, recurring reports, decks, CMS chores, and connectors.
Anthropic's Marketing Plugin for Claude: Every Skill and Command Explained
Every skill in Anthropic's open-source marketing plugin for Claude Cowork and Claude Code, its connectors, the install commands, and how to fork it.
Claude Skills for Marketers: 6 to Upload Today
Six Claude skills for marketers (brand voice, SEO brief, repurposing, landing page, email sequence, documents), how to upload them, and a prompt for each.
An SEO Content Workflow in Claude Code: Brief, Draft, On-Page Check
A repeatable SEO content workflow in Claude Code: a content repo with CLAUDE.md, SERP research over Exa and Firecrawl MCP, a brief, a draft, and on-page checks.
Which Claude Plan Should a Marketer Pay For?
A decision guide by situation: solo content marketer, a small team sharing brand context, heavy Cowork and Claude Design use, or an agency. No prices.
Adding MCP Servers to Claude Code: Local, Remote, and Project-Scoped
The complete claude mcp add reference — stdio vs HTTP transports, local/project/user scopes, .mcp.json with env expansion, OAuth via /mcp, and the gotchas.
Codex MCP Setup: Connect Tools and Live Context
Connect OpenAI Codex to MCP servers through the CLI, desktop app, IDE, or config.toml — with practical scoping, OAuth, and tool-approval guidance.
AI Coding Agents in 2026: The Open-Source & CLI Edition
Cursor and Windsurf vs the open-source agents — OpenCode, Cline, Aider, Codex CLI, and more. Who should bring their own model, and when to stay in the terminal.
Claude vs GPT vs Gemini for Coding in 2026
The three frontier model families compared for real coding work — agentic depth, ecosystem fit, context, and cost shape — plus how to actually choose.
Context Engineering
Treating the context window as a finite budget — what to load, what to leave out, and when to reset.
Cursor vs Claude Code vs GitHub Copilot vs Windsurf in 2026
A practical, opinionated comparison of the four mainstream AI coding tools — form factor, agentic depth, model choice, and who each one is for.
Designing System Prompts for LLM Apps and Agents
How to write system prompts that hold up in production: what belongs there vs. the user turn, structure that survives long context, and format/refusal rules.
Programmatic Prompt Optimization with DSPy: Stop Hand-Tuning Prompts
Hand-tuning prompts doesn't scale. DSPy treats prompting as programming — declare tasks as typed signatures and let an optimizer compile the prompts for you.
Effective Tool Use: Scoping an Agent's Toolset
How to scope tools and permissions so an agent reaches for the right one and can't do damage.
Prompt Patterns for Coding Agents
Practical prompting patterns: chaining, few-shot, context management, tool use, and output structuring.
Few-Shot vs Chain-of-Thought vs Structured Prompting: What to Use When (2026)
When to reach for few-shot examples, chain-of-thought reasoning, or structured/output-constrained prompting — a 2026 decision guide to the core techniques.
Vibe Coding in 2026: What It Is, When It Works, When It Bites
An honest guide to vibe coding — where prompt-and-accept development genuinely pays, where it accumulates risk, and the guardrails that make it professional.
Build an RFP Compliance Matrix with AI and Evidence
Build an RFP compliance matrix with AI that maps every requirement to source text, approved evidence, response locations, owners, and unresolved gaps.
Claude for Sales Teams: The Surface Map
Which Claude surface a sales team should actually open: Anthropic's free sales plugin, claude.ai Projects, Cowork, Claude Code, and MCP connectors.
Inside Anthropic's Sales Plugin for Claude: All Nine Skills
A per-skill breakdown of Anthropic's sales plugin for Claude: what each of the nine skills produces, how you trigger it, and where it falls down.
Claude Skills for Sales: The Set Worth Installing
The Claude skills a sales team should install: Anthropic's nine official ones, plus four of ours that verify and audit what the official set writes.
How to Research a Prospect with Claude (and Verify It Before You Send)
A step-by-step prospect research workflow in Claude: run account-research standalone, add an enrichment connector, draft the email, then verify every claim.
Which Claude Plan Should a Sales Team Pay For?
Which Claude surface a sales team needs — Cowork for the plugin, Projects for account context, connectors, Claude Code for ops — and where the numbers live.
The Agent Skills Standard: One SKILL.md for Every AI Tool
Agent Skills became an open standard in December 2025. Which tools read SKILL.md today — Copilot, Cursor, VS Code, Gemini CLI, Codex — and how to write portable skills.
The Best Claude Skills to Install in 2026
A skills-only tour of the AgentsCamp library — the Claude Code skills that earn a permanent slot, organized by the job they do.
9 Best Claude Skills for Code Review
Choose Claude skills for security, correctness, maintainability, and focused pull request review without relying on one vague review prompt.
10 Best Claude Skills for Debugging
Compare Claude skills and commands for stack traces, failing and flaky tests, regressions, slow queries, memory leaks, CPU hotspots, deadlocks, and agents.
10 Best Claude Skills for DevOps and SRE
Use Claude skills for incidents, rollbacks, SLOs, alerts, dashboards, logs, traces, containers, CI, and safer releases.
7 Best Claude Skills for Documentation
Use Claude skills to verify code examples and create accurate READMEs, API docs, runbooks, onboarding guides, ADRs, and diagrams.
9 Best Claude Skills for Git
Compare Claude skills and commands for commit messages, undoing mistakes, PR descriptions, rebases, conflicts, commit splitting, blame, and changelogs.
9 Best Claude Skills for Release Management
Use Claude skills for readiness reviews, canaries, rollbacks, API deprecations, migrations, versioning, changelogs, and release notes.
9 Best Claude Skills for Software Testing
Compare Claude skills for regression, unit, integration, contract, property, mutation, prompt, and test-data workflows.
Claude Code Skills: Best Practices
The patterns that make Claude Code skills reliable: trigger-first descriptions, one job per skill, lean bodies, bundled scripts, and scoped tools.
Claude's Document Skills: Excel, PowerPoint, Word, and PDF
How Anthropic's pre-built document skills let Claude produce real .xlsx, .pptx, .docx, and PDF files — on claude.ai, the API, and in Claude Code.
Claude Skills Examples: Annotated SKILL.md Files
Real SKILL.md examples you can copy — a minimal skill, a scoped-tools skill, a bundled-script skill — with the reasoning behind each line.
Claude Skills Use Cases: 20 Ideas Worth Building
Twenty concrete Claude skills use cases — for engineers, writers, analysts, and ops — with the pattern behind each and links to installable versions.
Codex Skills: Build Reusable Workflows with SKILL.md
Create, install, and test Codex skills with SKILL.md — including trigger descriptions, repo and user paths, progressive disclosure, and distribution.
How to Install Claude Skills
Every way to install Claude skills: manual copy, the agentscamp CLI, GitHub repos, plugins, team distribution, and uploading to claude.ai.
Packaging and Sharing Claude Code Skills
Take a skill from your personal ~/.claude folder to a versioned plugin your whole team installs from a marketplace — portably and with governance.
The SKILL.md Reference: Every Frontmatter Field Explained
A complete reference for the SKILL.md format — all frontmatter fields, naming rules, argument substitution, limits, and where skill files live.
Skills vs Agents vs Commands
How Claude Code's two extension mechanisms — subagents and skills — differ across three invocation patterns, with a decision table for choosing the right one.
Skills vs MCP Servers: When to Use Which
Skills inject procedure into context; MCP servers expose tools and live data over a protocol. A decision framework, the combine pattern, and examples.
Testing and Debugging Claude Code Skills
Verify a Claude Code skill triggers on the right prompts, check its output, and fix the five common failures — from vague triggers to broken paths.
What Are Claude Skills? The Complete Guide
Claude Skills explained: what a SKILL.md is, how progressive disclosure keeps skills cheap, where they run, and how to install or write your own.
Writing Your First Skill
A step-by-step guide to packaging a reusable procedure as a Claude Code skill that loads exactly when it's needed.
TDD with AI Agents: Red-Green as an Agent Loop
Test-driven development found its killer app: agents. How write-the-test-first turns AI coding into a verifiable loop, and the workflow that makes it stick.
Claude Code Troubleshooting: Fixes for the Most Common Problems
Fixes for the Claude Code problems people actually hit — install and auth failures, context-limit errors, MCP servers that won't connect, permission loops.
Claude Skills Not Working? Fixes for Every Failure Mode
Skill missing from the / menu, never auto-triggering, firing too often, or breaking mid-run — the symptom-by-symptom fix list for Claude skills.
Codex Troubleshooting: A Layer-by-Layer Recovery Guide
Troubleshoot OpenAI Codex when files, commands, configuration, worktrees, MCP, or app features misbehave — with a fast isolation and recovery sequence.
Build an AI Customer Support Answer Library You Can Check
Build an AI support answer library with source-backed answer cards, eligibility limits, escalation rules, and checked customer-question test cases.
How to Summarize an Email Thread with AI and Draft a Reply
Use AI to reconstruct a long email thread, distinguish current decisions from old requests, identify open questions, and draft a reply for review.
Draft AI Exit Tickets from Lesson Objectives
Draft short AI-assisted exit tickets from taught material, map each prompt to a learning objective, and review the answer key before classroom use.
AI Literature Review Workflow: Screen, Extract, and Verify
Use AI for a literature review with explicit eligibility criteria, study-level evidence tables, source locations, and checks for missing or conflicting data.
Create an AI Project Handoff Another Teammate Can Use
Create a project handoff with AI that preserves source files, current decisions, open questions, owners, and an acceptance check for the next teammate.
Create Standard Operating Procedures with AI from a Real Workflow
Create an SOP with AI from captured steps, explicit prerequisites, exception paths, and a teammate walkthrough that checks the procedure.
Build AI Study Cards from Your Notes
Turn approved notes into checked AI study cards with one learning target, source quotes, unresolved questions and a learner review before practice.
Plan AI Survey Branching Before Building the Form
Turn approved survey questions and routing rules into an explicit branch table, with stable IDs and unresolved paths before an AI form builder runs.
Prepare a Vendor Contract Review Packet with AI
Prepare a vendor contract review packet with AI that preserves clause evidence, conditions, obligation dates, missing documents, and reviewer questions.
Analyze Customer Feedback with AI: Themes You Can Check
Analyze customer feedback with AI using a source register, a reviewed codebook, distinct customer counts, and examples that preserve context.
Codex Automations: Schedule Reliable Background Work
Schedule Codex tasks for recurring checks and follow-ups — choose chat or standalone runs, local projects or worktrees, skills, permissions, and stopping rules.
Human-in-the-Loop AI Workflows: Approval Gates That Keep Agents Safe and Trusted
How to design human-in-the-loop into agent workflows — when to require approval, gate patterns, confidence escalation, review UX, and feedback loops.
Build a Source-Grounded AI Mind Map
Turn a bounded document set into a reviewed concept hierarchy with evidence for each branch and visible unresolved relationships.
Spec-Driven Development with AI Agents
Write the spec, let the agent implement against it — the SDD workflow (spec → plan → tasks → implement), when it beats prompt-and-iterate, and the tooling.
Test AI Survey Logic with Known Response Paths
Create complete response-path cases for an AI-built survey, check a local route model, then preview the actual form before collection.
Alttext AI
Evaluate AltText.ai drafts against inspected observations, page purpose, correction notes and the actual publishing review process.
Amp
Agentic coding tool, independent of Sourcegraph since December 2025: a CLI plus apps for the web, Mac, iPhone, and iPad, tuned for frontier-model coding.
Argilla
Evaluate Argilla for a supervised text task with separately preserved suggestions, human responses and decision evidence.
Base44
A Wix-owned AI app builder that turns a plain-English prompt into a working web app with database, auth, and hosting built in.
Be My Eyes
Evaluate Be My Eyes for a personal picture question, recording useful clarification, remaining uncertainty and independent evidence for consequential details.
Bolt
StackBlitz's in-browser AI agent that builds, runs, and deploys full-stack web apps in a WebContainer.
Bubble
A full no-code platform for web and native mobile apps with its own database, visual workflow logic, and AI generation from a prompt.
Bynder
Bynder centralizes digital assets and offers AI-assisted metadata and discovery, including image search and similarity-based asset finding.
Chatgpt
OpenAI's general-purpose AI assistant for chat, research, and finished documents, with Projects, memory, plugins, and a Work mode for multi-step tasks.
Claude Agent SDK
A toolkit for building custom agents on the same harness that powers Claude Code.
Claude Code
Anthropic’s official agentic coding tool that runs in the terminal, IDE, and web.
Claude
Anthropic's AI assistant app for web, desktop, and mobile, with Projects, connectors, Artifacts, skills, memory, and code execution.
Clearscope
A content optimization platform that grades drafts against top-ranking pages, discovers queries, tracks AI-answer mentions, and monitors published pages.
Codex CLI
OpenAI's open-source terminal coding agent with sandboxed execution and two-layer approval controls.
Copy AI
A go-to-market AI platform that codifies sales and marketing processes as Workflows, Agents, and Tables on top of a Brand Voice and Infobase.
Dedupe
Evaluate Dedupe through an owner-reviewed matching pilot with known pairs, preserved source keys, candidate coverage checks and unresolved cases.
Deepl
DeepL provides AI translation for text and documents, with preferred-term glossaries and paid options for team translation and customization workflows.
Descript
A video and podcast editor where you edit by editing the transcript, with Underlord, an AI co-editor, Studio Sound, AI voices, dubbing, and clip creation.
Devin
Cognition's autonomous AI software engineer that works in its own cloud workspace with an editor, terminal, and browser.
Dovetail
Dovetail organizes customer research and feedback with AI transcription, project summaries, searchable evidence, and channels for recurring signals.
DSPy
Program language models instead of prompting them: declare tasks as typed signatures and let optimizers compile the prompts and few-shot examples for you.
Elicit
Elicit supports academic research with a Research Agent, research reports, and a structured workflow for screening papers and extracting evidence.
Emergent
An agentic AI app builder that plans, codes, tests, and deploys full-stack web apps and Expo mobile apps from a chat prompt.
Gamma
An AI design partner that turns a prompt or a document into presentations, docs, websites, and social posts, with an Agent for edits and a credits-based plan.
Gemini
Google's Gemini app, a general-purpose AI assistant with Deep Research, Gems, Canvas, and direct integration into Gmail, Docs, Sheets, and Workspace.
Glean
Glean is an enterprise AI search and assistant platform that retrieves company knowledge through configured connectors and source access controls.
Glide
A no-code platform that turns spreadsheets and databases into mobile and desktop business apps, with an AI Agent that starts the build for you.
Goose
Open-source, on-machine AI agent, originally from Block and now an Agentic AI Foundation project — MCP-native and model-agnostic, with a CLI and desktop app.
Intercom Fin
Fin by Intercom is an AI customer agent with support-content training, guidance, pre-deployment batch testing, and configured human handover workflows.
Jasper
An enterprise marketing AI workspace with 100+ purpose-built agents, Jasper IQ brand context, Canvas, and an MCP server for other AI tools.
Jules
Google's asynchronous coding agent: it clones your GitHub repo into a cloud VM, proposes a plan built with Gemini, and opens a pull request once you approve.
Label Studio
Label Studio is an open-source annotation interface that can present imported or model-generated predictions for people to review and correct.
Loopio
Loopio is an RFP response platform with a reusable answer library, AI-assisted response drafting, project collaboration, and source-scoped generation controls.
MagicSchool
MagicSchool provides AI lesson, worksheet, quiz and rubric drafts that educators can tailor to supplied readings and instructional goals.
Meshy
Evaluate Meshy with a versioned prop pilot, owner-set requirements, real inspection reports and actual target-application viewer evidence.
Microsoft Copilot
Microsoft's work assistant inside Word, Excel, PowerPoint, Outlook, and Teams, grounded in your company's Microsoft 365 data, with Researcher and Analyst.
Miro
Evaluate Miro as a shared review surface for an approved concept hierarchy and its relationship ledger.
Napkin AI
Napkin AI turns imported or pasted text into editable visuals for documents and presentations, with export choices that depend on plan.
Opus Clip
An AI clipping tool that turns long videos into scored, captioned short clips for Shorts, TikTok, and Reels, with a scheduler, brand templates, and an API.
Perplexity
An AI answer engine that cites its sources on every response, with a Research mode for long reports, Projects for shared context, and the Comet browser.
RemNote
RemNote combines notes, AI-generated flashcards and quizzes, and spaced review, with a preview step for checking cards against the source.
Rork
An AI mobile app builder that turns a chat prompt into native iPhone (Swift), Android (Kotlin), and web apps you can publish to the App Store.
Scribe
Scribe captures on-screen workflows into editable visual guides and adds AI drafting features for titles, descriptions, and process documentation.
Softr
A no-code builder for client portals and internal tools on top of Airtable, Google Sheets, or its own database, now with AI app generation.
Spec Kit
GitHub's open-source toolkit for spec-driven development — a specify CLI and /speckit slash commands that walk any coding agent from spec to implementation.
Spellbook
Spellbook supports legal contract work with AI questions, source references, Microsoft Word review suggestions, and reusable contract-review instructions.
Surfer
An SEO and AI-visibility platform whose Content Editor scores drafts against live SERP guidelines, with AI writing, audits, and AI-search tracking.
Surveymonkey
SurveyMonkey combines AI survey drafting with editable survey questions and plan-dependent skip logic for respondent paths.
Tamr
Evaluate Tamr with a bounded mastering pilot that preserves source keys, exposes uncertain candidates and names the owner of each decision.
Typeform
Typeform builds online forms with AI-assisted questions, endings and branching rules that owners can preview and revise.
Warp
A modern, AI-powered terminal with an agent mode that can run and chain commands across your codebase.
Workable
Workable combines recruiting and HR software with AI drafting tools, configurable interview kits, shared rating scales, and candidate feedback records.
Count Feedback
Count a single-label feedback CSV with code: validate record IDs, collapse exact duplicate rows, reject conflicting rows for one ID, and report records, distinct known respondents, missing identities, and label totals without inventing prevalence.
Add Docstrings
Add or improve docstrings for the public API of a file or symbol.
Check Obligation Dates
Check a human-reviewed obligation CSV against an explicit as-of date with Python: validate calendar dates and status fields, list overdue or due-today open rows, missing owners/dates, and recorded late/future completions. Never infer legal deadlines, breach, or contract status from clauses.
Check Procedure Graph
Check explicitly recorded SOP step dependencies with Python: validate IDs and prerequisite references, compute deterministic execution layers for acyclic graphs, and report steps blocked by a cycle without executing the procedure.
Explain Code
Explain what the given code does, in clear prose with a short summary.
Snapshot Handoff
Create a deterministic inventory of an approved handoff directory: record relative file paths, byte lengths, and SHA-256 hashes with code, list skipped symlinks and unreadable files, and write a snapshot without interpreting project status or changing source files.
Update README
Update the README to reflect the current scripts, structure, and features of the repo.
Sync Branch
Fetch and rebase the current branch onto its base, resolving conflicts and verifying the build.
Brand Check
Score a draft file against the project's brand voice guide (brand-voice.md or a brand-voice skill) and list every violation with a rewrite, without editing it.
Check Translation Tokens
Compare recognized named placeholders in a source-target translation CSV with Python, preserving token multiplicity and flagging blank targets. Supports exact {name}, {{name}}, and %(name)s/%(name)d forms; does not validate full ICU, HTML, positional placeholders, or translation meaning.
Repurpose
Run content-repurposer on a file or pasted text and write the X thread, LinkedIn post, newsletter section, and video script to content/repurposed/.
Breakdown Task
Decompose a task into an ordered checklist of small, verifiable steps.
Estimate Effort
Produce a grounded effort and complexity estimate for a task by exploring the codebase read-only.
Plan Feature
Explore the codebase and produce an implementation plan for a feature.
Write Design Doc
Explore the codebase and write a decision-oriented design doc / RFC for a feature or system change.
Check Scorecard
Validate a draft job-interview scorecard JSON with Python: unique criteria, exactly three nonblank behavioral anchor slots, task-source and question references, and positive human-supplied decimal weights totaling exactly one. Never read or calculate candidate scores.
PRD
Turn an idea, pasted notes, or a notes file into a structured PRD and write it to docs/prd.md, or print it when there is no project.
Scope MVP
Cut a PRD or feature list to a version one: a keep / cut / later table with reasons plus the smallest build that tests the riskiest assumption, written to docs/mvp-scope.md.
Check Annotation Batch
Check annotation-batch.json for approved labels, distinct response reviewers, exact text evidence and unresolved disagreements while preserving the input.
Check Entity Match Ledger
Check entity-match-ledger.json for source-linked evidence values, duplicate pairs, reviewer presence and contradictory match groups without merging records.
Check Evidence Table
Check a study evidence CSV against a source registry with code: validate required columns and cells, row IDs, source references, duplicate study/outcome/time-point keys, and allowed status values, then report structural errors without judging research claims.
Check Exit Ticket Map
Check a local exit-ticket-map.json for objective/question IDs, objective coverage, supported answer evidence and unresolved review status, without editing it.
Check Study Card Map
Check a local study-card-map.json for valid card/source IDs, exact evidence quotes, duplicate questions and unresolved-card status, without editing it.
Check Survey Paths
Check survey-paths.json for complete single-choice routes, cycles, reachable nodes and expected test paths without editing the file or contacting a form service.
Audit CRM
Audit a CRM CSV export for duplicates, past close dates, stale deals, missing required fields, single-threaded deals, owner gaps and format drift, and write a ranked fix list with the record IDs.
Check Outreach
Fact-check a drafted outreach email, or a folder of them, against the research files it was written from and write an annotated report with a claims table, without editing the draft.
Check RFP Coverage
Check human-reviewed RFP requirement and response-matrix CSVs with Python: validate unique IDs and explicit flags, count supplied statuses including absent rows, and list mandatory attention items or ready rows missing required references. Does not prove claim accuracy or submit a bid.
Check Support Cases
Validate a local JSONL support-answer testset with Python: unique case IDs, exact fields, answer/clarify/escalate expectations, required answer-card references and sources, and explicit escalation reasons; report counts without running a support bot.
Create Skill
Scaffold a new Claude Code skill into .claude/skills/<name>/SKILL.md — a model-invoked capability with a trigger-rich description, scoped tools, and a lean body that pushes detail into resource files.
Create Slash Command
Scaffold a new Claude Code slash command into .claude/commands/ — a valid Markdown file with frontmatter, a least-privilege allowed-tools allowlist, and a $ARGUMENTS-driven body of numbered steps ending in a Report.
Create Subagent
Scaffold a new Claude Code subagent definition file into .claude/agents/ with a routing-ready description, scoped tools, and a system prompt.
Setup Claude CI
Wire Claude Code into this repo's CI the safe way — install the GitHub App or scaffold the workflow YAML, scope permissions to the minimum, set secrets correctly, and verify with a real trigger.
Agent Skills
Agent Skills are reusable procedures packaged as folders with a SKILL.md file — loaded by an AI agent on demand when a task matches, now an open standard.
AGENTS.md
AGENTS.md is a versioned instruction file that tells coding agents how to work in a repository — including commands, conventions, boundaries, and checks.
AI Slop
AI slop is low-effort, mass-produced AI-generated content — fluent, generic, and unchecked — flooding feeds, search results, and codebases.
Alternative Text
Choose useful wording for an image placement by keeping inspected observations, page purpose and human approval together.
Blocking in Record Matching
Understand how a candidate-selection rule can miss known pairs and why missing fields need coverage checks before identity review.
Brand Voice (in AI prompting)
Brand voice, in AI prompting, is the documented tone, vocabulary, and style rules a model is given so every draft sounds like one company, not the model.
Chain-of-Thought (CoT)
Chain-of-thought prompting has a model work through intermediate reasoning steps before answering — improving accuracy on multi-step problems.
Context Engineering
Context engineering is the discipline of curating exactly what enters an LLM's context window so it has the right information and nothing else.
Digital Asset Management
A catalog-review concept for separating files, descriptive metadata and supplied approval records before reuse.
Entity Resolution
Understand the identity question behind similar records, including false merges, missed matches and the source owner’s unresolved decisions.
Extended Thinking
Extended thinking is the reasoning tokens a model generates before its final answer, trading latency and cost for higher accuracy on hard problems.
Few-Shot Prompting
Few-shot prompting includes worked examples in the prompt so the model learns the task's pattern from demonstrations instead of instructions alone.
Formative assessment
Formative assessment gathers feedback during learning so teachers and learners can adjust next steps; an AI draft still needs educator review.
Lead Enrichment
Lead enrichment is filling the missing fields on a lead or account record, such as title, headcount, or tech stack, from data sources outside your own system.
Physically Based Rendering
Review an AI material handoff without confusing supplied map files with verified appearance in the target scene.
Prompt Engineering
Prompt engineering is the practice of designing an LLM's inputs — instructions, context, examples, and format — to reliably get the output you want.
Prompt Template
A prompt template is a parameterized prompt — fixed instructions with variable slots — turning prompts from strings into versioned, testable components.
Record Linkage
Understand the reviewable crosswalk needed before joining sources with unrelated keys, ambiguous candidates and explicit cardinality policies.
Sales Engagement Platform
A sales engagement platform is the system reps work out of: it sequences emails, calls, and tasks across channels and logs every touch back into the CRM.
Skip Logic
Skip logic routes a respondent to different survey questions or endings based on answers or other stated conditions.
Spaced repetition
Spaced repetition schedules reviews over time using recall feedback; AI can draft the cards, while the learner still checks their answers.
Subagent
A subagent is a specialist agent a primary agent delegates to — running in its own context window with its own prompt and tools, returning only a summary.
System Prompt
The system prompt is the standing instruction layer an LLM receives before user input — defining its role, rules, tools, and tone for the whole conversation.
Top-k Sampling
Top-k sampling restricts an LLM's next-token choice to the k most probable tokens before sampling; lower k is more deterministic, higher k more diverse.
Tree of Thoughts
Tree of Thoughts is a prompting method that explores multiple reasoning branches as a search tree, evaluating and backtracking among them.
UV Mapping
Understand why a 3D handoff keeps mesh, surface-layout and texture versions together before approving their actual target appearance.
Vibe Coding
Vibe coding is building software by describing intent in natural language and letting an AI agent write the code, judging results by behavior.
Zero-Shot Prompting
Zero-shot prompting asks a model to perform a task from instructions alone, with no examples — the default mode for capable modern LLMs.