monthly-review
Skill2 starsChanged 8 months agoMITView on GitHub
Monthly audit cycle — full SQWR audit across all 8 domains, dependency updates, tech debt review, and SLO check.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- AN0099/toothpaste-kittheir own version, first seen Oct 13, 2026
- Phoenixrr2113/ediththeir own version, first seen Apr 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- AN0099/toothpaste-kit★ 1same name
- Phoenixrr2113/edith★ 0same name
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.
- global/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- audit-runnerSkill
- auto-fixSkill
- brainstormSkill
- compliance-checkSkill
- contract-lookupSkill
- new-featureSkill
- pre-deploymentSkill
- project-setupSkill
- risk-scoreSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
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 26
Run the complete audit suite across all 8 domains.
- Distinctive: line 48
Check for outdated or vulnerable dependencies.
- Distinctive: line 70
Create issues for P1 items
- Distinctive: line 79
Check actual SLO metrics against targets in CLAUDE.md.
- Distinctive: line 87
If any SLO is breached:
- Distinctive: line 90
Add to Error History in CLAUDE.md
- Very specific: line 98
Check that all contracts have a current Last validated date.
- Distinctive: line 106
Observable truth: All contracts validated within the last 6 months.
- Very specific: line 116
Document the monthly review outcome in CHANGELOG.md under [Unreleased] as a "chore" entry.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
/monthly-review — Monthly Review Cycle
Usage: /monthly-review
Runs the full monthly review. Invoke this at the end of each sprint or month to maintain kit quality standards.
Phase 1 — Full Audit
Run the complete audit suite across all 8 domains.
Ask Claude: "Run agents/AGENT-FULL-AUDIT.md"Expected runtime: 20-45 minutes. The full audit runs:
- Security (22%) — blocking at <70
- Performance (18%) — recommended ≥70
- Code Quality (18%) — recommended ≥75
- Observability (12%) — recommended ≥60
- Accessibility (12%) — legal ≥80 (EU)
- Design (8%) — recommended ≥70
- AI Governance (5%) — recommended ≥80
- Deployment (5%) — pre-production gate
Observable truth: Full audit report with global score ≥ 85/100 and no blocking thresholds breached.
Phase 2 — Dependency Review
Check for outdated or vulnerable dependencies.
npm outdated
npm auditFor each vulnerability:
- CRITICAL/HIGH: fix immediately
- MODERATE: plan fix within 2 weeks
- LOW: track in Tech Debt Tracker
Observable truth: npm audit shows 0 critical/high vulnerabilities.
Phase 3 — Tech Debt Review
Review CLAUDE.md Tech Debt Tracker section.
For each item:
- Re-evaluate priority (P1/P2/P3)
- Create issues for P1 items
- Archive resolved items
Observable truth: Tech Debt Tracker updated, P1 items have GitHub issues.
Phase 4 — SLO Review
Check actual SLO metrics against targets in CLAUDE.md.
| SLI | Target | Tool |
| Uptime | ≥99.5% | UptimeRobot |
| LCP p75 | ≤2.5s | Vercel Speed Insights |
| Error rate | ≤0.5% | Sentry |
If any SLO is breached:
- Declare an incident (even minor)
- Run
frameworks/INCIDENT-RESPONSE.md - Add to Error History in CLAUDE.md
Observable truth: SLO dashboard reviewed, no unacknowledged breaches.
Phase 5 — Contract Validation
Check that all contracts have a current Last validated date.
grep -l "Last validated" contracts/CONTRACT-*.md | wc -lFor any contract validated > 6 months ago: re-read the primary standard for updates.
Observable truth: All contracts validated within the last 6 months.
Completion
touch .sqwr-last-auditDocument the monthly review outcome in CHANGELOG.md under [Unreleased] as a "chore" entry.
Reference
Full workflow: workflows/WORKFLOW-MONTHLY-REVIEW.md
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.