agent-skills-review
Skill1 starsChanged 4 days agoApache-2.0View on GitHub
Review SKILL.md quality for Waza readiness and agent-skills-instructions compliance. Use when evaluating SKILL.md quality, checking compliance with skill authoring standards, preparing skills for release, reviewing skill PRs, or running waza readiness checks.
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .apm/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/actions/CLAUDE.mdCLAUDE.md
- .github/workflows/CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-skills.mdcCursor rule
- .cursor/rules/bats.mdcCursor rule
- .cursor/rules/github-actions-workflow.mdcCursor rule
- .cursor/rules/go.mdcCursor rule
- .cursor/rules/go-test.mdcCursor rule
- .cursor/rules/instructions.mdcCursor rule
- .cursor/rules/markdown.mdcCursor rule
- .cursor/rules/shell-script.mdcCursor rule
- .cursor/rules/terraform.mdcCursor rule
- agent-skills-reviewSkill
- changelogSkill
- ci-sweeperSkill
- docs-creatorSkill
- docs-updaterSkill
- github-actions-reviewSkill
- github-actions-validationSkill
- github-issue-autofixSkill
- github-issue-triageSkill
- github-pr-bodySkill
- github-pr-reviewSkill
- github-pr-reviseSkill
- go-reviewSkill
- go-validationSkill
- instructions-reviewSkill
- loop-verifierSkill
- markdown-validationSkill
- refactorSkill
- shell-script-reviewSkill
- shell-script-validationSkill
- tech-debtSkill
- test-gapSkill
- changelogSkill
- ci-sweeperSkill
- docs-creatorSkill
- docs-updaterSkill
- github-actions-reviewSkill
- github-actions-validationSkill
- github-issue-autofixSkill
- github-issue-triageSkill
- github-pr-bodySkill
- github-pr-reviewSkill
- github-pr-reviseSkill
- go-reviewSkill
- go-validationSkill
- instructions-reviewSkill
- loop-verifierSkill
- markdown-validationSkill
- refactorSkill
- shell-script-reviewSkill
- shell-script-validationSkill
- tech-debtSkill
- test-gapSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Run validation scripts and parse results to assess SKILL.md quality against S-_, Q-_, P-_, and BP-_ checks.
- Very specific: line 28
Check waza check token output and apply Q-09 per Workflow step 2.
- Very specific: line 40
run benchmark content evaluations (waza run eval.yaml) as a substitute for compliance checks
- Very specific: line 57
If target SKILL.md does not exist, set Status: failed per references/common-output-format.md and stop without running other checks.
- Distinctive: line 61
If one validation script fails and the other succeeds, report successful checks normally and mark unresolved checks as deferred with script …
- Very specific: line 62
If both validation scripts fail, set Status: failed and include both commands, exit statuses, and stderr summaries in ## Issues.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Input
- Target (required):
<agent-root>/skills/*/SKILL.md - Sibling skills (optional): other
<agent-root>/skills/*/SKILL.mdin the same package or sharing the target's contract files — enables P-04; without them P-04 is deferred - Evidence (required when not pre-supplied): outputs from
scripts/validate_waza.shandscripts/validate.sh— run both in Workflow step 1 when absent from context
Output Specification
Return structured Markdown in accordance with references/common-output-format.md. That file is the source of truth for the output contract.
Skill-local addition: unlike other review skills, this skill runs validation scripts, so Status: failed also applies when both scripts fail. The ## Issues cause entry (no ItemID) then lists both commands, exit statuses, and stderr summaries.
Execution Scope
- Run validation scripts and parse results to assess SKILL.md quality against S-, Q-, P-, and BP- checks.
- Check
waza checktoken output and apply Q-09 per Workflow step 2.
USE FOR:
- review new SKILL drafts before release
- note token budget advisories when
waza checkexceeds 500 tokens (Q-09) - report SKILL spec compliance findings in PR reviews
DO NOT USE FOR:
- implement product features
- debug product runtime failures unrelated to SKILL quality checks
- run benchmark content evaluations (
waza run eval.yaml) as a substitute for compliance checks - modify or overwrite the target SKILL.md without explicit user approval (review output only; do not write or commit changes)
- merge PRs or edit unrelated files
- review product runtime behavior or application business logic
Reference Files Guide
- common-checklist.md (always read)
- common-output-format.md (always read)
- category-best-practices.md (always read)
- category-patterns.md (always read)
- category-quality.md (always read)
- category-structure.md (always read)
- common-troubleshooting.md (read on failure)
Workflow
- If target
SKILL.mddoes not exist, setStatus: failedper references/common-output-format.md and stop without running other checks. Otherwise runbash scripts/validate_waza.sh <skill-name>andbash scripts/validate.sh <SKILL.md>(CWD:<agent-root>/skills/agent-skills-review/). - Record token budget from
waza checkwhen present; if count > 500, add a Q-09 advisory entry to## Issuesand do not list Q-09 in## Checks (Failed/Deferred Only). Q-09 fails only whenwaza checkran but its token count is not recorded; ifvalidate_waza.shfailed, defer Q-09 per step 5. A skill compressed below sibling depth is a BP-04 finding, not Q-09. - Apply checks in order:
BP-*(best practices),P-*(workflow/policy),Q-*(quality language),S-*(structure). For Q-12, read everyreferences/file and the option parsing of bundledscripts/; for P-04, compare shared rules with the sibling skills. - Report failed/deferred items with ItemIDs.
- If one validation script fails and the other succeeds, report successful checks normally and mark unresolved checks as deferred with script name and exit status.
- If both validation scripts fail, set
Status: failedand include both commands, exit statuses, and stderr summaries in## Issues.
Error Handling
| Condition | Severity | Action |
Target SKILL.md does not exist | Fatal | Set Status: failed; stop without other checks |
validate_waza.sh or validate.sh missing | Fatal | Stop; report missing script path |
| One validation script fails, the other succeeds | Recoverable | Report successful checks; defer failed script checks with exit status |
| Both validation scripts fail | Fatal | Set Status: failed with command, exit status, and stderr summary in ## Issues |
common-checklist.md unavailable | Fatal | Stop; report missing dependency |
common-output-format.md unavailable | Recoverable | Note missing file; emit ## Checks Summary, ## Checks (Failed/Deferred Only), and ## Issues only |
| Script output missing after one rerun | Recoverable | Defer affected checks; include command and stderr per troubleshooting |
Examples
- Prompt:
Review SKILL.md and report only failed/deferred items - Result: Structured report per references/common-output-format.md (failed/deferred only).
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.

