Research external documentation and best practices. Use when user says "look up the docs for this library", "research best practices for implementing caching", "how do other projects handle authentication", "check the official documentation for this API", "compare our implementation with industry standards", or "what's the recommended way to structure this".
Scanned 2/12/2026
Install via CLI
openskills install Uniswap/ai-toolkit---
description: Research external documentation and best practices. Use when user says "look up the docs for this library", "research best practices for implementing caching", "how do other projects handle authentication", "check the official documentation for this API", "compare our implementation with industry standards", or "what's the recommended way to structure this".
allowed-tools: WebSearch, WebFetch, Read, Glob, Grep, Bash(git ls-files:*), Bash(git log:*), Task(subagent_type:researcher)
model: opus
---
# Topic Researcher
Research topics by combining web documentation with internal codebase analysis.
## When to Activate
- User asks about external documentation
- Best practices research needed
- Comparing implementations with industry standards
- Learning about libraries or frameworks
- Understanding how other projects solve problems
- Documentation lookup needed
## Quick Process
1. **Parse Query**: Extract topic, sources, codebase context
2. **Web Search**: Find relevant documentation and resources
3. **Codebase Analysis**: Analyze related patterns and implementations
4. **Synthesize**: Combine findings from both sources
5. **Recommend**: Provide actionable insights
## Input Parsing
Extract from request:
- `query`: Main research question or topic
- `sources`: Specific sources mentioned (e.g., "check MDN", "anthropic docs")
- `codebase_context`: Related files/patterns to analyze
## Output Format
Return structured findings:
- **Summary**: Executive summary of findings
- **Key Findings**: Main discoveries from research
- **Codebase Insights**: Relevant patterns from code
- **Recommendations**: Actionable next steps
- **Warnings**: Important gotchas or risks
- **References**: Sources consulted with links
## Examples
```
"Research how Claude Code subagents handle tool permissions"
"Check anthropic docs for MCP protocol and compare with our implementation"
"Best practices for TypeScript monorepo with Nx"
```
## Delegation
Invokes the **researcher** agent with query, sources, and codebase context.
No comments yet. Be the first to comment!
Create Mermaid diagrams for flowcharts, sequences, ERDs, and
Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
Review a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact such as HTML or Markdown. Use when asked to analyze a PR, explain a contributor's design decisions, compare it with similar systems, or prepare a merge recommendation.
Generate the stable Paperclip release changelog at releases/vYYYY.MDD.P.md by reading commits, changesets, and merged PR context since the last stable tag.