compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup. Use when a non-trivial problem is solved and worth reusing.
Best use case
compound-docs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup. Use when a non-trivial problem is solved and worth reusing.
Teams using compound-docs should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/compound-docs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How compound-docs Compares
| Feature / Agent | compound-docs | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup. Use when a non-trivial problem is solved and worth reusing.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# compound-docs Skill
**Purpose:** Automatically document solved problems to build searchable institutional knowledge with category-based organization (enum-validated problem types).
## Learnings entry (compound)
Append a structured learning entry to `docs/learnings.md` in the project repo.
**Inputs**
- Stage (explore = discovery/insights; shape/develop/review/release/other).
- Title.
- Context links (PR, issue, docs paths).
- Summary and what changed.
- Root cause, fix, prevention.
- Verification evidence (required if code-touching).
**Outputs**
- Updated `docs/learnings.md` (append-only).
**Steps**
1. Open the project repo `docs/learnings.md`.
2. Add a new entry under the matching stage heading.
3. Include required fields and verification evidence if code-touching.
4. Keep history append-only.
**Verification**
- Entry includes date, stage, summary, root cause, fix, prevention, verification, and links.
**Go/No-Go**
- GO if entry is complete and appended under correct stage.
- NO-GO if required fields are missing.
## Overview
This skill captures problem solutions immediately after confirmation, creating structured documentation that serves as a searchable knowledge base for future sessions.
**Organization:** Single-file architecture - each problem documented as one markdown file in its symptom category directory (e.g., `docs/solutions/performance-issues/n-plus-one-briefs.md`). Files use YAML frontmatter for metadata and searchability.
---
## 7-Step Process
### Step 1: Detect Confirmation
**Auto-invoke after phrases:**
- "that worked"
- "it's fixed"
- "working now"
- "problem solved"
- "that did it"
**OR manual:** invoke `compound-docs` skill
**Non-trivial problems only:**
- Multiple investigation attempts needed
- Tricky debugging that took time
- Non-obvious solution
- Future sessions would benefit
**Skip documentation for:**
- Simple typos
- Obvious syntax errors
- Trivial fixes immediately corrected
### Step 2: Gather Context
Extract from conversation history:
**Required information:**
- **Module name**: Which module or component had the problem
- **Symptom**: Observable error/behavior (exact error messages)
- **Investigation attempts**: What didn't work and why
- **Root cause**: Technical explanation of actual problem
- **Solution**: What fixed it (code/config changes)
- **Prevention**: How to avoid in future
**Environment details:**
- Rails version
- Stage (0-6 or post-implementation)
- OS version
- File/line references
**BLOCKING REQUIREMENT:** If critical context is missing (module name, exact error, stage, or resolution steps), ask user and WAIT for response before proceeding to Step 3:
```
I need a few details to document this properly:
1. Which module had this issue? [ModuleName]
2. What was the exact error message or symptom?
3. What stage were you in? (0-6 or post-implementation)
[Continue after user provides details]
```
### Step 3: Check Existing Docs
Search docs/solutions/ for similar issues:
```bash
# Search by error message keywords
grep -r "exact error phrase" docs/solutions/
# Search by symptom category
ls docs/solutions/[category]/
```
**IF similar issue found:**
THEN present decision options:
```
Found similar issue: docs/solutions/[path]
What's next?
1. Create new doc with cross-reference (recommended)
2. Update existing doc (only if same root cause)
3. Other
Choose (1-3): _
```
WAIT for user response, then execute chosen action.
**ELSE** (no similar issue found):
Proceed directly to Step 4 (no user interaction needed).
### Step 4: Generate Filename
Format: `[sanitized-symptom]-[module]-[YYYYMMDD].md`
**Sanitization rules:**
- Lowercase
- Replace spaces with hyphens
- Remove special characters except hyphens
- Truncate to reasonable length (< 80 chars)
**Examples:**
- `missing-include-BriefSystem-20251110.md`
- `parameter-not-saving-state-EmailProcessing-20251110.md`
- `webview-crash-on-resize-Assistant-20251110.md`
### Step 5: Validate YAML Schema
**CRITICAL:** All docs require validated YAML frontmatter with enum validation.
**Validate against schema:**
Load `schema.yaml` and classify the problem against the enum values defined in [yaml-schema.md](./references/yaml-schema.md). Ensure all required fields are present and match allowed values exactly.
**BLOCK if validation fails:**
```
❌ YAML validation failed
Errors:
- problem_type: must be one of schema enums, got "compilation_error"
- severity: must be one of [critical, high, medium, low], got "invalid"
- symptoms: must be array with 1-5 items, got string
Please provide corrected values.
```
**GATE ENFORCEMENT:** Do NOT proceed to Step 6 (Create Documentation) until YAML frontmatter passes all validation rules defined in `schema.yaml`.
### Step 6: Create Documentation
**Determine category from problem_type:** Use the category mapping defined in [yaml-schema.md](./references/yaml-schema.md) (lines 49-61).
**Create documentation file:**
```bash
PROBLEM_TYPE="[from validated YAML]"
CATEGORY="[mapped from problem_type]"
FILENAME="[generated-filename].md"
DOC_PATH="docs/solutions/${CATEGORY}/${FILENAME}"
# Create directory if needed
mkdir -p "docs/solutions/${CATEGORY}"
# Write documentation using template from assets/resolution-template.md
# (Content populated with Step 2 context and validated YAML frontmatter)
```
**Result:**
- Single file in category directory
- Enum validation ensures consistent categorization
**Create documentation:** Populate the structure from `assets/resolution-template.md` with context gathered in Step 2 and validated YAML frontmatter from Step 5.
### Step 7: Cross-Reference & Critical Pattern Detection
If similar issues found in Step 3:
**Update existing doc:**
```bash
# Add Related Issues link to similar doc
echo "- See also: [$FILENAME]($REAL_FILE)" >> [similar-doc.md]
```
**Update new doc:**
Already includes cross-reference from Step 6.
**Update patterns if applicable:**
If this represents a common pattern (3+ similar issues):
```bash
# Add to docs/solutions/patterns/common-solutions.md
cat >> docs/solutions/patterns/common-solutions.md << 'EOF'
## [Pattern Name]
**Common symptom:** [Description]
**Root cause:** [Technical explanation]
**Solution pattern:** [General approach]
**Examples:**
- [Link to doc 1]
- [Link to doc 2]
- [Link to doc 3]
EOF
```
**Critical Pattern Detection (Optional Proactive Suggestion):**
If this issue has automatic indicators suggesting it might be critical:
- Severity: `critical` in YAML
- Affects multiple modules OR foundational stage (Stage 2 or 3)
- Non-obvious solution
Then in the decision menu (Step 8), add a note:
```
💡 This might be worth adding to Required Reading (Option 2)
```
But **NEVER auto-promote**. User decides via decision menu (Option 2).
**Template for critical pattern addition:**
When user selects Option 2 (Add to Required Reading), use the template from `assets/critical-pattern-template.md` to structure the pattern entry. Number it sequentially based on existing patterns in `docs/solutions/patterns/critical-patterns.md`.
---
## Decision Menu After Capture
After successful documentation, present options and WAIT for user 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 (critical-patterns.md)
3. Link related issues - Connect to similar problems
4. Add to existing skill - Add to a learning skill (e.g., hotwire-native)
5. Create new skill - Extract into new learning skill
6. View documentation - See what was captured
7. Other
```
**Handle responses:**
**Option 1: Continue workflow**
- Return to calling skill/workflow
- Documentation is complete
**Option 2: Add to Required Reading** ⭐ PRIMARY PATH FOR CRITICAL PATTERNS
User selects this when:
- System made this mistake multiple times across different modules
- Solution is non-obvious but must be followed every time
- Foundational requirement (Rails, Rails API, threading, etc.)
Action:
1. Extract pattern from the documentation
2. Format as ❌ WRONG vs ✅ CORRECT with code examples
3. Add to `docs/solutions/patterns/critical-patterns.md`
4. Add cross-reference back to this doc
5. Confirm: "✓ Added to Required Reading. All subagents will see this pattern before code generation."
**Option 3: Link related issues**
- Prompt: "Which doc to link? (provide filename or describe)"
- Search docs/solutions/ for the doc
- Add cross-reference to both docs
- Confirm: "✓ Cross-reference added"
**Option 4: Add to existing skill**
User selects this when the documented solution relates to an existing learning skill:
Action:
1. Prompt: "Which skill? (hotwire-native, etc.)"
2. Determine which reference file to update (resources.md, patterns.md, or examples.md)
3. Add link and brief description to appropriate section
4. Confirm: "✓ Added to [skill-name] skill in [file]"
Example: For Hotwire Native Tailwind variants solution:
- Add to `hotwire-native/references/resources.md` under "Project-Specific Resources"
- Add to `hotwire-native/references/examples.md` with link to solution doc
**Option 5: Create new skill**
User selects this when the solution represents the start of a new learning domain:
Action:
1. Prompt: "What should the new skill be called? (e.g., stripe-billing, email-processing)"
2. Use `skill-creator` skill to scaffold `[skill-name]`
3. Create initial reference files with this solution as first example
4. Confirm: "✓ Created new [skill-name] skill with this solution as first example"
**Option 6: View documentation**
- Display the created documentation
- Present decision menu again
**Option 7: Other**
- Ask what they'd like to do
---
## Integration Points
**Invoked by:**
- /compound command (primary interface)
- Manual invocation in conversation after solution confirmed
- Can be triggered by detecting confirmation phrases like "that worked", "it's fixed", etc.
**Invokes:**
- None (terminal skill - does not delegate to other skills)
**Handoff expectations:**
All context needed for documentation should be present in conversation history before invocation.
---
## Success Criteria
Documentation is successful when ALL of the following are true:
- ✅ YAML frontmatter validated (all required fields, correct formats)
- ✅ File created in docs/solutions/[category]/[filename].md
- ✅ Enum values match schema.yaml exactly
- ✅ Code examples included in solution section
- ✅ Cross-references added if related issues found
- ✅ User presented with decision menu and action confirmed
---
## Error Handling
**Missing context:**
- Ask user for missing details
- Don't proceed until critical info provided
**YAML validation failure:**
- Show specific errors
- Present retry with corrected values
- BLOCK until valid
**Similar issue ambiguity:**
- Present multiple matches
- Let user choose: new doc, update existing, or link as duplicate
**Module not in modules documentation:**
- Warn but don't block
- Proceed with documentation
- Suggest: "Add [Module] to modules documentation if not there"
---
## Execution Guidelines
**MUST do:**
- Validate YAML frontmatter (BLOCK if invalid per Step 5 validation gate)
- Extract exact error messages from conversation
- Include code examples in solution section
- Create directories before writing files (`mkdir -p`)
- Ask user and WAIT if critical context missing
**MUST NOT do:**
- Skip YAML validation (validation gate is blocking)
- Use vague descriptions (not searchable)
- Omit code examples or cross-references
---
## Quality Guidelines
**Good documentation has:**
- ✅ Exact error messages (copy-paste from output)
- ✅ Specific file:line references
- ✅ Observable symptoms (what you saw, not interpretations)
- ✅ Failed attempts documented (helps avoid wrong paths)
- ✅ Technical explanation (not just "what" but "why")
- ✅ Code examples (before/after if applicable)
- ✅ Prevention guidance (how to catch early)
- ✅ Cross-references (related issues)
**Avoid:**
- ❌ Vague descriptions ("something was wrong")
- ❌ Missing technical details ("fixed the code")
- ❌ No context (which version? which file?)
- ❌ Just code dumps (explain why it works)
- ❌ No prevention guidance
- ❌ No cross-references
---
## Example Scenario
**User:** "That worked! The N+1 query is fixed."
**Skill activates:**
1. **Detect confirmation:** "That worked!" triggers auto-invoke
2. **Gather context:**
- Module: Brief System
- Symptom: Brief generation taking >5 seconds, N+1 query when loading email threads
- Failed attempts: Added pagination (didn't help), checked background job performance
- Solution: Added eager loading with `includes(:emails)` on Brief model
- Root cause: Missing eager loading causing separate database query per email thread
3. **Check existing:** No similar issue found
4. **Generate filename:** `n-plus-one-brief-generation-BriefSystem-20251110.md`
5. **Validate YAML:**
```yaml
module: Brief System
date: 2025-11-10
problem_type: performance_issue
component: rails_model
symptoms:
- "N+1 query when loading email threads"
- "Brief generation taking >5 seconds"
root_cause: missing_include
severity: high
tags: [n-plus-one, eager-loading, performance]
```
✅ Valid
6. **Create documentation:**
- `docs/solutions/performance-issues/n-plus-one-brief-generation-BriefSystem-20251110.md`
7. **Cross-reference:** None needed (no similar issues)
**Output:**
```
✓ Solution documented
File created:
- docs/solutions/performance-issues/n-plus-one-brief-generation-BriefSystem-20251110.md
What's next?
1. Continue workflow (recommended)
2. Add to Required Reading - Promote to critical patterns (critical-patterns.md)
3. Link related issues - Connect to similar problems
4. Add to existing skill - Add to a learning skill (e.g., hotwire-native)
5. Create new skill - Extract into new learning skill
6. View documentation - See what was captured
7. Other
```
---
## Future Enhancements
**Not in Phase 7 scope, but potential:**
- Search by date range
- Filter by severity
- Tag-based search interface
- Metrics (most common issues, resolution time)
- Export to shareable format (community knowledge sharing)
- Import community solutionsRelated Skills
framework-docs-researcher
Use this agent when you need to gather comprehensive documentation and best practices for frameworks, libraries, or dependencies in your project. This includes fetching official documentation, exploring source code, identifying version-specific constraints, and understanding implementation patterns.
docs-list
Run `scripts/docs-list.ts` to list `docs/` markdown + frontmatter summary/read_when. Use when auditing docs coverage.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
modular-skills-architect
Map and refactor an agent context ecosystem: skills, commands/workflows, hooks, agent files, AGENTS.md templates, and docs. Output system map, module/dependency design, Register updates, and a concrete split/consolidate/rename/delete plan. Use when routing or ownership is messy.
heal-skill
This skill should be used when fixing incorrect SKILL.md files with outdated instructions or APIs.
create-agent-skills
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
agent-native-audit
Comprehensive agent-native architecture audit with scored principles and multi-slice review. Use for system-wide health checks or periodic audits.
write-judge-prompt
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
validate-evaluator
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
generate-synthetic-data
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
evaluate-rag
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.
eval-audit
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).