Problem documentation methodology for compounding team knowledge. Captures solved problems with structured metadata for searchability, pattern detection, and prevention.
Documents solved problems with structured metadata to prevent recurrence and inform future work.
npx claudepluginhub dlabs/claude-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/category-taxonomy.mdreferences/yaml-schema.mdThis skill provides the methodology for documenting solved problems so they compound into team knowledge over time. Every solved problem becomes a searchable, referenceable document that helps prevent recurrence and informs future work.
/blueprint-dev:bp:compound — after solving a problemSolve problem → /compound → docs/solutions/ → /plan reads solutions → avoids repeating mistakes
The research-scout agent (used in /plan) searches docs/solutions/ before planning new features. This closes the loop — past learnings compound into future plans.
| Agent | Extracts | Output |
|---|---|---|
| context-analyzer | Problem metadata: module, symptom, environment, timeline | Problem Context section |
| solution-extractor | Root cause, code changes, verification | Root Cause + Solution sections |
| related-docs-finder | Cross-references in docs/solutions/ | Related Solutions section |
| prevention-strategist | Tests, lint rules, monitoring to prevent recurrence | Prevention section |
| category-classifier | Category, severity, tags for searchability | YAML frontmatter |
---
title: "Brief description"
date: YYYY-MM-DD
category: {enum}
severity: {enum}
module: {name}
tags: [tag1, tag2, tag3]
root_cause: "One-line root cause"
prevention: "One-line prevention"
---
## Problem Context
{From context-analyzer}
## Root Cause
{From solution-extractor}
## Solution
{From solution-extractor}
## Prevention Strategy
{From prevention-strategist}
## Related Solutions
{From related-docs-finder}
references/yaml-schema.md — YAML frontmatter enum validationreferences/category-taxonomy.md — Category definitions and tagging guidelinesActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.