Loading...
Loading...
Found 2,898 Skills
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, optimize a skill's triggering, or set up an eval suite — even if the user just says "is this skill any good," "does my skill work," or "benchmark this skill." Drives Claude Code, OpenAI Codex, Antigravity (agy), Cursor, GitHub Copilot, Amp, opencode, or Grok in headless mode.
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
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.