Review Commands
Explore 16 curated review commands for building with AI coding agents — what each one does, when to use it, and how to add it to your workflow.
Benchmark Rerankers
Measure whether adding a reranker actually improves retrieval, by scoring reranked vs. un-reranked results on a labeled query set.
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 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 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.
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.
Find Bug
Investigate a reported symptom, form hypotheses, and locate the root cause.
Red Team LLM
Red-team an LLM app or agent for prompt injection, jailbreaks, and data leakage — probe the real attack surface (input, RAG, tools, system prompt) with adversarial inputs and report what got through and how to fix it.
Review PR
Review a pull request for correctness, security, and style, and summarize findings.
Review Tests
Review the quality of a test suite, not just whether it passes — find weak assertions, missing edge cases, and tests coupled to implementation.
Security Scan
Scan the current diff or given paths for security vulnerabilities.