KS
Killer-Skills

external-researcher — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude Code and AutoGPT requiring advanced external knowledge retrieval for library and framework research All Mighty Antigravity

totoroyyb totoroyyb
[0]
[0]
Updated: 3/4/2026

Quality Score

Top 5%
34
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add totoroyyb/amag/external-researcher

Agent Capability Analysis

The external-researcher MCP Server by totoroyyb is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for AI Agents like Claude Code and AutoGPT requiring advanced external knowledge retrieval for library and framework research

Core Value

Empowers agents to surface concrete guidance from official documentation and production OSS examples, leveraging protocols for finding authoritative external knowledge on specific libraries, frameworks, and tools, and facilitating best practices for library decisions

Capabilities Granted for external-researcher MCP Server

Searching official documentation for unfamiliar libraries
Finding production OSS examples for specific external dependencies
Determining best practices for library decisions

! Prerequisites & Limits

  • Requires internet access for searching external resources
  • Limited to publicly available official documentation and OSS examples
Project
SKILL.md
3.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

External Researcher

Protocol for finding authoritative external knowledge. When activated, shift into reference-finding mode: search official docs, find production OSS examples, and surface concrete guidance — not tutorials, not blog posts.

When to Activate

  • Working with an unfamiliar library, framework, or tool
  • User mentions a specific external dependency
  • Best practices needed for a library decision
  • Finding OSS implementations to learn from before designing something
  • "How do I use [library] correctly?" or "What does [framework feature] actually do?"

Key trigger phrases:

  • "How do I use [library]?"
  • "What's the best practice for [framework feature]?"
  • "Why does [external dependency] behave this way?"
  • "Find examples of [technology] usage"
  • Working with an npm/pip/cargo package you haven't used before

Loaded by:

  • /plan Step 1 (Build from Scratch, Architecture, Research intents)
  • /ultrawork for unfamiliar technology
  • Default behavior when user mentions external library

Core Pattern

Always prefer in this order:

  1. Official docs — canonical API reference, config options, migration guides
  2. Production OSS (1000+ stars) — real implementations, not tutorials
  3. Changelog/issues — for gotchas, breaking changes, known bugs

Never cite:

  • Personal blog posts as authoritative (as supplementary evidence only)
  • Tutorials as API reference
  • Stack Overflow as the primary source for library design decisions

Search Patterns

For Library/Framework Docs

search_web("{library} official documentation API reference")
search_web("{library} {specific feature} best practices")
read_url_content({official_docs_url})

Focus on:

  • API signatures with parameter types and defaults
  • Recommended usage patterns
  • Pitfalls and common mistakes sections
  • Version compatibility (check if docs match the version in use)

For Production OSS Examples

search_web("{feature} site:github.com stars:>1000")
search_web("{library} example implementation production")

Focus on:

  • Architecture choices, not surface-level patterns
  • Edge case handling
  • Error strategies
  • What 2-3 quality implementations have in common (consensus pattern)

For Gotchas and Migration

search_web("{library} {version} breaking changes migration")
search_web("{library} common mistakes pitfalls")

Focus on:

  • API changes between versions
  • Performance gotchas
  • Security considerations

Synthesis Format

Source: [URL — official docs / OSS / other]
Key finding: [What to do / API signature / pattern]
Pitfall: [What to avoid]
Version note: [Any version-specific considerations]
Confidence: HIGH (official docs) / MEDIUM (OSS pattern) / LOW (community)

Quality Bar

  • Always verify the version of docs matches the project's dependency version
  • When official docs and OSS patterns conflict — follow official docs, note the discrepancy
  • Production code (GitHub, verified OSS) > tutorials > blog posts
  • Cite the specific URL + section, not just "I found online"
  • If docs are ambiguous: note it explicitly, don't fabricate certainty

Related Skills

Looking for an alternative to external-researcher or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication