Loading...
Loading...
Found 2,878 Skills
Gate 2: Feature relationship map - visualizes feature landscape, groupings, and interactions at business level before technical architecture.
This skill should be used when the user asks to "manage review skills config", "update review skills", "discover review skills", "manage review presets", "validate review config", or mentions managing code review skills configuration. Use for configuration management tasks.
This skill should be used when the user asks to "test the triage skill", "run triage tests", "validate antithesis triage", "test:triage", or "smoke test triage". Orchestrates end-to-end testing of the antithesis-triage skill by running real triage operations via sub-agents and reviewing the results for bugs, skill compliance issues, and papercuts.
Review Specification - validates documents for completeness, quality, and consistency against the codebase. Use when checking spec quality at any pipeline stage.
Find and fix broken or insecure links across an entire site, including CMS content, to improve SEO and user experience. Audits HTTP/HTTPS issues and validates all internal and external links.
Generate, refine, research, and validate startup ideas through an interactive founder-specific idea machine. Use when Codex needs to ask a few focused questions, search current public web signals, rapidly brainstorm startup or SaaS ideas, learn from love/maybe/no reactions, produce additional idea rounds, compare finalists, investigate competitors and existing workarounds, select a promising opportunity, or create an evidence-linked Markdown startup-idea report.
Refine AI-generated code through specific feedback—point out errors, identify gaps, show desired changes, reference style guides
Turn the current conversation into a spec (Problem, Solution, User Stories, Decisions) and publish it as a GitHub issue. Validates a feature before any code is written.
Grade a delivered claim against the artifact instead of against the report of the artifact. Use when acting as a verifier or reviewer on someone else's finished work, checking whether a fix actually landed, confirming a task's done result is true, auditing a claim that has no diff to read — a backfill, a migration, a deploy, a config change — or self-auditing your own claim before you publish it. Covers splitting a claim into checkable assertions, the three-state verdict (pass, fail, not-reached), and the specific failure modes that survive a careless check. Keywords verify, verification, grade, verdict, acceptance, prove it, did it actually work, confirm the fix, check the claim, QA sign-off.
Audit React Doctor against ReactBench or similar diagnostic benchmark corpora for confirmed false positives, false negatives, taxonomy gaps, and verifier artifacts. Use when analyzing rd.log, rd-before.json, rd-after.json, model.patch, result.json, reward/test logs, rule distributions, or when asked to perform a second adversarial pass over React Doctor benchmark findings.