Agent skill
exit-review
End-of-session learning classification. Reviews accumulated learnings and classifies each as GREEN (generic, goes to global wiki), YELLOW (project-specific, goes to project wiki), or RED (sensitive, discarded). Triggered at session end via Stop hook. Use when: (1) session ending, (2) manual review of learnings. Triggers: /exit-review, 'review learnings', 'classify learnings'.
Install this agent skill to your Project
npx add-skill https://github.com/alfredolopez80/multi-agent-ralph-loop/tree/main/.claude/skills/exit-review
SKILL.md
Exit Review — Session Learning Classification v3.0
Classify accumulated learnings before session ends.
Classification
| Color | Meaning | Destination | Example |
|---|---|---|---|
| GREEN | Generic (useful for any project) | $VAULT_DIR/global/wiki/{category}/ |
"Use zod for runtime validation" |
| YELLOW | Project-specific | $VAULT_DIR/projects/{project}/wiki/ |
"Hook sanitize-secrets.js uses 28 patterns" |
| RED | Contains secrets or sensitive info | DISCARDED (never saved) | "API key is sk-..." |
Workflow
- Read accumulated learnings from session buffer
- For each learning:
a. Classify as GREEN/YELLOW/RED
b. If GREEN: write to
$VAULT_DIR/global/wiki/{category}/c. If YELLOW: write to$VAULT_DIR/projects/{project}/wiki/d. If RED: discard with warning - Update vault indices
Learning Format
---
type: learning
classification: GREEN
source: session-2026-04-04
confidence: 0.3
sessions_confirmed: 1
category: typescript
---
# Use zod for runtime validation at API boundaries
Runtime validation with zod catches type mismatches that TypeScript alone misses at API boundaries.
Particularly useful for external API responses where the shape is not guaranteed.
## Evidence
- Used successfully in auth endpoint validation
- Caught 3 type mismatches in first session
Trigger
- Automatically triggered by
Stopevent viasession-end-handoff.sh - Can be invoked manually:
/exit-review
Integration
session-accumulator.shcollects learnings during session- This skill classifies them at session end
vault-graduation.shpromotes high-confidence ones to rules at next SessionStart
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
browser-test
Browser testing using Chrome DevTools MCP and Playwright for visual verification. Start dev server, navigate, screenshot, Lighthouse audit, console errors, network check. Use when: (1) verifying frontend changes, (2) accessibility auditing, (3) performance testing, (4) visual regression. Triggers: /browser-test, 'test in browser', 'visual test', 'lighthouse audit'.
crafting-effective-readmes
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
stop-slop
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.
bugs
Bug hunting with Codex CLI Use when: (1) /bugs is invoked, (2) task relates to bugs functionality.
adversarial
Multi-Agent Adversarial Analysis System for code security
senior-software-engineer
Global skill enforcing senior software engineering best practices
Didn't find tool you were looking for?