Automatically generate and maintain documentation that compounds knowledge over time, capturing patterns, decisions, and learnings.
/plugin marketplace add KreativReason/merged-end-to-end-ai-dpp---e2e-cli/plugin install kreativreason-e2e-pipeline@kreativreason-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Automatically generate and maintain documentation that compounds knowledge over time, capturing patterns, decisions, and learnings.
Documentation should grow smarter with every feature, not just bigger.
Automatically capture reusable patterns:
## Pattern: API Error Handling
### Context
How we handle errors in API routes.
### Implementation
```typescript
export function apiHandler(handler: Handler) {
return async (req: Request) => {
try {
return await handler(req);
} catch (error) {
if (error instanceof ValidationError) {
return Response.json({ error: error.message }, { status: 400 });
}
console.error(error);
return Response.json({ error: 'Internal error' }, { status: 500 });
}
};
}
export const POST = apiHandler(async (req) => {
const data = await req.json();
// handler logic
});
PR #45 - User Authentication
### Decision Recording
Link patterns to ADRs:
```markdown
## Decision: Use Zod for Validation
### Why
- TypeScript inference
- Runtime validation
- Consistent with API layer
### Alternative Considered
- Yup (less TS support)
- Manual validation (error-prone)
### References
- ADR-0005: Validation Strategy
- Pattern: Form Validation
Maintain searchable index:
{
"patterns": {
"api-error-handling": {
"file": "docs/patterns/api-error-handling.md",
"tags": ["api", "errors", "typescript"],
"usage_count": 15
}
},
"decisions": {
"validation-strategy": {
"file": "docs/adr/ADR-0005.md",
"status": "accepted",
"related_patterns": ["form-validation", "api-validation"]
}
}
}
| Event | Documentation Generated |
|---|---|
| New pattern detected | Pattern doc created |
| Pattern reused | Usage count updated |
| ADR created | Index updated |
| Code review feedback | Learning captured |
/kreativreason:compound capture-pattern "API Error Handling"
/kreativreason:compound find-similar "error handling"
/kreativreason:compound generate-onboarding
{
"artifact_type": "compound_doc",
"action": "pattern_captured|decision_linked|knowledge_indexed",
"data": {
"pattern": {
"name": "API Error Handling",
"category": "backend",
"first_seen": "PR #45",
"usage_count": 1,
"file_created": "docs/patterns/api-error-handling.md"
},
"index_updated": true,
"related_docs": [
"docs/adr/ADR-0005.md",
"docs/patterns/form-validation.md"
]
}
}
/kreativreason:work to capture new patterns/kreativreason:review to link decisionsThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.