skill-reviewer
Skill1 starsChanged 9 months agoMITView on GitHub
Audit installed skills and agents for bloat, overlap, and improvement opportunities. Use when the user wants to review, audit, list, or improve their skills and agents. Triggers on "review skills", "audit skills", "list skills", "skill review", "improve skills".
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, security-review and 2 more.
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
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 3 projects that use this
SentrySkillskill-creator
Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.
Also in 6 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 4 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 repository9 other files it gives its agents.
- bug-bash-updateSkill
- ci-cd-pipelineSkill
- claudemd-auditorSkill
- docs-consolidatorSkill
- ralphSkill
- refactor-auditSkill
- reflectSkill
- setup-workflowSkill
- smoke-testSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
After presenting all findings, ask the user which changes to apply.
- Distinctive: line 59
Don't review this skill (skill-reviewer) unless explicitly asked.
- Distinctive: line 60
When estimating tokens, use the rough formula: word count * 1.3.
- Distinctive: line 61
If a skill has no issues worth flagging, say so briefly and move on.
“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
Inventory all installed skills and agents, then deep-review selected ones for conciseness, clarity, overlap, and token efficiency.
Workflow
Phase 1: Build inventory
Scan all skill and agent locations. For each item, count lines in the main file and any reference files.
Locations:
- Global skills:
~/.claude/skills/*/SKILL.md+references/*.md - Global agents:
~/.claude/agents/*.md - Project skills:
.claude/skills/*/SKILL.md+references/*.md - Project agents:
.claude/agents/*.md
Build a table sorted by total lines (largest first):
| Scope | Name | Type | Main Lines | Ref Lines | Total |
|---------|------------------|-------|------------|-----------|-------|
| global | ci-cd-pipeline | skill | 120 | 45 | 165 |
| project | bug-bash-update | skill | 109 | 0 | 109 |
| global | debugger | agent | 98 | 0 | 98 |Phase 2: Ask what to review
Present the table. Ask the user which items to deep-review. They can pick one, several, or "all".
Phase 3: Deep review
For each selected item, read the full content and analyze:
- Conciseness — Verbose sections, redundant instructions, unnecessary examples. Flag anything that could be shorter without losing meaning.
- Clarity — Ambiguous instructions, missing context, unclear phase transitions. Would another LLM session interpret this correctly?
- Scope overlap — Responsibilities duplicated with other skills/agents in the inventory. Note which items overlap and what to consolidate.
- Token efficiency — Estimate token count (words * 1.3). Flag sections that consume disproportionate tokens relative to their value.
- Structural consistency — Does it follow the same patterns (frontmatter, phases, guidelines) as other skills? Note deviations.
Phase 4: Present findings with rewrites
For each issue, show:
- Current text (quoted)
- Problem (one sentence)
- Suggested rewrite (the improved version)
After presenting all findings, ask the user which changes to apply. Then apply the approved edits.
Guidelines
- Be specific. "This section is verbose" is useless. "Lines 12-18 repeat the trigger list from the frontmatter" is actionable.
- Preserve intent. Compress prose, don't change behavior.
- Don't review this skill (skill-reviewer) unless explicitly asked.
- When estimating tokens, use the rough formula: word count * 1.3.
- If a skill has no issues worth flagging, say so briefly and move on.
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.

