compound-docs
Document solved problems for team reuse. Provides process knowledge for /ia-compound. Use when documenting a resolved issue, writing up lessons learned, capturing a post-mortem, adding to the knowledge base, or building searchable institutional knowledge after debugging.
How do I install this agent skill?
npx skills add https://github.com/iliaal/ai-skills --skill compound-docsIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides a workflow for documenting resolved technical issues by extracting context from conversation history and validating it with a local Python script. It depends on the PyYAML library. While it includes validation and sanitization steps, the skill processes untrusted conversation data, which creates a low-risk surface for indirect prompt injection.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
compound-docs
Process
Single-file architecture -- one markdown file per problem in its symptom category directory (e.g., docs/solutions/performance-issues/n-plus-one-briefs.md), with YAML frontmatter for metadata.
Follow the 7-step documentation capture process. For full details, see documentation-process.md.
- Detect confirmation -- Auto-invoke after "that worked", "it's fixed", etc. Skip trivial fixes.
- Gather context -- Extract module, symptom, investigation attempts, root cause, solution, prevention. BLOCK if critical context missing.
- Check existing docs -- Search
docs/solutions/for similar issues. If found, offer: new doc with cross-reference, update existing, or other. - Generate filename -- Format:
[sanitized-symptom]-[module]-[YYYYMMDD].md - Validate YAML -- Save the draft to a temporary Markdown file, then run validate-frontmatter.sh against it. The validator requires Python 3 and PyYAML; report a missing dependency rather than claiming validation. If invalid, fix the frontmatter and re-run until it passes.
- Create documentation -- Write file to
docs/solutions/[category]/[filename].mdusing resolution-template.md. - Cross-reference -- Link related issues. Detect critical patterns (3+ similar issues).
Capture gate (step 1): capture only if, without this doc, a future engineer reading the final code, tests, comments, CLAUDE.md/AGENTS.md, and existing docs or skills would still repeat the mistake or redo the investigation. Skip when any of those already carries the lesson.
Decision Menu
After successful documentation, present the options below via AskUserQuestion (Claude Code; load with ToolSearch select:AskUserQuestion if not loaded) or request_user_input (Codex), falling back to the numbered menu in chat, and WAIT for the user's response:
Solution documented
File created:
- docs/solutions/[category]/[filename].md
What's next?
1. Continue workflow (recommended)
2. Add to Required Reading - Promote to critical patterns
3. Link related issues - Connect to similar problems
4. Add to existing skill - Add to a learning skill
5. Create new skill - Extract into new learning skill
6. View documentation - See what was captured
7. Other
For detailed response handling, see documentation-process.md.
Success Criteria
- YAML frontmatter validated (all required fields, correct formats)
- File created in
docs/solutions/[category]/[filename].md - Enum values match schema exactly
- Code examples included in solution section
- Cross-references added if related issues found
- User presented with decision menu and action confirmed
References
- documentation-process.md - Full 7-step process with validation gates
- yaml-schema.md - YAML frontmatter schema and enum values
- quality-guidelines.md - Quality standards, execution rules, error handling
- example-scenario.md - Complete walkthrough of documenting an N+1 query fix
- resolution-template.md - Template for documentation files
- critical-pattern-template.md - Template for critical pattern entries
- validate-frontmatter.sh - Validate YAML frontmatter against schema
- validate-frontmatter.py - Safe YAML parser and field validation; install its dependency with
python3 -m pip install PyYAMLwhen authorized
Integration
- Stale-learning review (
/ia-compound-refreshin Claude Code) -- reviewsdocs/solutions/for entries that have aged out
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/iliaal/ai-skills/compound-docs">View compound-docs on skillZs</a>