skill-reviewer
Skill0 starsChanged 4 months agoMITView on GitHub
Reviews a Claude Code skill against the repo's 8 authoring rules and proves it works via a baseline eval comparison (with-skill vs. disabled). Use when a skill was just created or edited, or when asked to review, evaluate, or benchmark a skill.
24 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/GitHub-Copilot-for-Azuretheir own version, first seen Nov 11, 2026
- zrosenbauer/skillstheir own version, first seen Nov 2, 2026
- HyperVon/agent-guidance-kittheir own version, first seen Nov 1, 2026
- jqaisystems/jqai-ai-skillstheir own version, first seen Nov 1, 2026
- harvard-lil/lawskills-hubtheir own version, first seen Nov 1, 2026
- qxryz/workflowgeneratortheir own version, first seen Oct 25, 2026
Used with
Projects with it also use skill-builder.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
BlockSkillskill-builder
Create, edit, or inspect Berd skills stored as skill folders with SKILL.md files. Use when the user wants to build a new skill, update an existing skill, convert a workflow into a reusable skill, or decide whether instructions, scripts, references, or assets belong in a skill.
Also in 3 projects that use this
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- bytedance/deer-flow★ 85ksame name
- microsoft/GitHub-Copilot-for-Azure★ 264same name
- Terryc21/skill-reviewer★ 57same name
- qxryz/workflowgenerator★ 48same name
- harvard-lil/lawskills-hub★ 46same name
- kumaran-is/claude-code-onboarding★ 35same name
- flightctl/ai-workflows★ 10same name
- wrsmith108/skill-builder-claude-skill★ 8same name
- alienzhou/doraemon-skills★ 4same name
- jqaisystems/jqai-ai-skills★ 3same name
14 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- build-phaseSkill
- code-reviewSkill
- debuggingSkill
- online-researchSkill
- security-reviewSkill
- skill-creatorSkill
- software-developmentSkill
- writing-plansSkill
- writing-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Run a baseline eval comparison (with-skill vs.
- Very specific: line 29
Create a TodoWrite item per stage.
- Very specific: line 36
Read the skill's SKILL.md, references, scripts, and evals/evals.json.
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Reviewer
Judge a skill. skill-creator builds; you review. Always run the static rubric,
then always proceed toward the baseline evals — but STOP for approval before
spawning any isolated runs, because they cost tokens and time.
The 8 authoring rules this rubric scores against are detailed in
references/rubric.md. (When working inside this repo, the same rules are also
documented in CLAUDE.md.)
Scope
This skill DOES:
- Score a skill against rules 1–8 (static rubric).
- Run a baseline eval comparison (with-skill vs. without-skill), or a blind A/B vs. the previous version for an edit.
- Render a PASS / ITERATE verdict with the top fixes.
This skill does NOT:
- Rewrite the skill → that's
skill-creator. Report findings; the author fixes. - Spawn any isolated run before the user approves at the Stage B gate.
Workflow
Create a TodoWrite item per stage. Checkpoint the Stage A rubric findings to
./.claude-skills-work/<skill>/review/ so a review can resume if interrupted.
(The Stage B eval RUNS use a separate workspace,
./.claude-skills-work/evals/<skill>/iteration-N/ — see references/running-evals.md.
The two paths are intentionally distinct: review findings vs. generated runs.)
Stage A — Static rubric (always)
Read the skill's SKILL.md, references, scripts, and evals/evals.json. Score
it against all 8 rules using references/rubric.md. Rate each finding:
🔴 Must fix · 🟡 Should fix · 🟢 Consider. Write findings to
review/rubric.md and report them. If rule 8 fails (no evals/evals.json),
say so — Stage B can't run without cases.
Stage B — Baseline evals ⛔ STOP GATE
- Count the work:
cases × 2 = runs(with_skill + without_skill). For an EDIT, the baseline is a snapshot of the previous version instead of "no skill". - Report the run count and that each run is a fresh isolated context with its own token/time cost, then STOP and ask the user to approve before spawning anything.
- On approval, follow
references/running-evals.md: spawn one subagent per run from a clean context, save outputs + atiming.json(tokens, duration) per run, grade each case against itsassertions(orexpected_outputif assertions aren't written yet), and aggregate a workspacebenchmark.jsonwithwith_skill,without_skill, anddelta.
Stage C — Verdict
Combine the rubric findings and the benchmark delta into a verdict:
- PASS — no 🔴 findings and the skill measurably helps (positive pass-rate delta at acceptable token/time cost).
- ITERATE — list the top fixes (🔴 first) and which eval cases regressed or
failed, so
skill-creatorcan address them.
Red flags (stop and correct)
| If you notice… | Do this |
| About to spawn runs without approval | STOP — the Stage B gate is mandatory |
| Editing the skill yourself | Don't — report findings; skill-creator fixes |
| Passing a skill on the rubric alone | A PASS also needs a positive eval delta |
| Grading a PASS on a vague assertion | Require concrete evidence; quote the output |
| Skipping Stage A because "evals will catch it" | Rubric is always run first |
No evals/evals.json present | Report rule 8 failure; ask author to add cases |
Done when
- Rubric findings are written and reported.
- Either the baseline benchmark exists with a
delta, or the user declined the eval run at the gate (note that in the verdict). - A PASS / ITERATE verdict is given with the top fixes.
References (load only when needed)
references/rubric.md— Stage A: the 8-rule checks + severity guidance.references/running-evals.md— Stage B: spawning runs, grading, aggregating.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

