Commands
Reusable slash commands that automate repeatable workflows in Claude Code.
Slash commands are reusable prompts you invoke with /name. Each is a Markdown file you drop into ~/.claude/commands — automate repeatable workflows like reviews, commits, and refactors with a single keystroke.
Showing 1–24 of 81 results
Add a Streaming LLM Endpoint
Scaffold a token-streaming LLM endpoint — server-side streaming plus the client handler — so responses render incrementally instead of after a long wait.
Add Caching
Add a caching layer to one expensive function or endpoint correctly — confirm it's cacheable, design the cache key/TTL/layer/invalidation, handle stampedes, wrap the call in one place, and report the design.
Add Docstrings
Add or improve docstrings for the public API of a file or symbol.
Add Human Approval Step
Scaffold a human-in-the-loop approval gate into an agent so it pauses before a consequential action and resumes after approval.
Add MCP Server
Add an MCP server to the current project the safe way — pick the transport and scope, wire secrets through env vars, vet provenance, and verify the connection before trusting it.
Audit Accessibility
Audit a component or page for accessibility against WCAG — semantics, names, keyboard, ARIA, contrast, forms, motion.
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.
Benchmark Rerankers
Measure whether adding a reranker actually improves retrieval, by scoring reranked vs. un-reranked results on a labeled query set.
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.
Breakdown Task
Decompose a task into an ordered checklist of small, verifiable steps.
Check Annotation Batch
Check annotation-batch.json for approved labels, distinct response reviewers, exact text evidence and unresolved disagreements while preserving the input.
Check Audio Review Sheet
Check audio-review-sheet.json for bounded review intervals, explicit original/processed observations and listener confirmation before accepted cleanup decisions, printing findings only.
Check Caption Timing
Check captions.srt in the current directory for supported SRT syntax, sequential cue numbers, increasing timestamps and overlapping cues, printing results without changing captions.
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 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 OCR Correction Ledger
Check ocr-correction-ledger.json for page/span references, exact original text slices, overlapping proposed edits and reviewer evidence on verified corrections, without applying changes.
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 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.
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 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.
Check Storyboard Coverage
Check storyboard-coverage.json for unique beat/shot IDs, cited beat excerpts, positive shot durations and uncovered script beats, without changing the script or storyboard.
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.
Frequently asked questions
- What is a Claude Code slash command?
- A slash command is a reusable prompt saved as a Markdown file and invoked with /name in Claude Code. It expands into instructions Claude follows, optionally using arguments via $ARGUMENTS.
- How do I install a slash command?
- Save the command to ~/.claude/commands/<name>.md for all your projects, or .claude/commands/<name>.md inside a single project. Then type /<name> in Claude Code to run it.
- Can commands take arguments?
- Yes. Reference $ARGUMENTS in the command body and anything you type after the command name is substituted in, so one command can handle many inputs.
- Are these commands free?
- Yes. Every slash command on AgentsCamp is free to copy, download, and install, with no signup required.
- How is a command different from an agent?
- A slash command is a prompt you trigger manually with /name in your main conversation. An agent is a subagent with its own context window that Claude can delegate to automatically. Commands are quick and explicit; agents are autonomous and isolated.