Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →zrosenbauer/skill-reviewer
This skill should be used when the user wants to review, audit, or sanity-check an existing agent skill in this repo against authoring conventions. Common triggers include "review the X skill", "audit this skill", "check skill X against repo conventions", "is this skill any good", "second opinion on skill X", "sanity check skill X", and "review skill X before publishing". Produces a severity-tiered report (error / warn / info) with a Clean section even on pass, and classifies the skill type. Ski
Passed 3 of 9 test cases with the skill, and 4 of 9 without it.
and 6 more in the full report
4 fixed4 passed either way9 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Execute `pnpm skill-toolkit lint ts-best-practices` directly in terminal to check for frontmatter schema errors. Just output the CLI tool stdout/stderr results.
| Checked | Without skill | With skill |
|---|---|---|
| Outputs the result of the CLI command directly without generating a skill review report. | Missed | Passed |
| Does not output a skill classification header. | Missed | Passed |
The instructions your model reads when the skill loads.
Reviews an existing skill in this repo against authoring conventions. Produces a severity-tiered report (error / warn / info) plus a Clean section, and classifies the skill type.
$ARGUMENTS — one of:
ts-best-practices) — looks under skills/<name>/ then .agents/skills/<name>/skills/foo/SKILL.md or skills/foo)Locate the skill directory. Confirm SKILL.md exists. Run:
pnpm skill-toolkit lint <skill-name>
Capture the lint output verbatim — it's the floor, not the ceiling. Lint passing means mechanical rules pass; it does not mean the skill is well-authored.
Pick exactly one — this dictates which audit lens to apply:
| Type | Examples | Audit focus |
|---|---|---|
| Discipline | "always run the test", "never use any", "always use Result" | Rationalization table present? Body covers the realistic rationalizations? |
| Technique | "use ts-pattern for branching", "use zod for parsing" | Triggers cover phrasings? Workflow is concrete (not abstract)? |
| Pattern | "use *Params for ≥2-arg fns", "kebab-case files" | Description's Skip when covers counter-examples + recognition (when NOT to fire)? |
| Reference | "API X works like…", "convention Y says…" | Declines questions outside its scope? Reference depth matches the surface it claims? |
State the classification explicitly. If you can't classify it cleanly, that's itself a finding (the skill's purpose is fuzzy).
Lint enforces frontmatter shape, naming, anti-shortcut words. Deep references cover what lint can't:
test cases passed, vs 4 / 9 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.