github-research

# External Code Research

## Overview

Research external patterns, documentation, and best practices from GitHub and library docs when AI knowledge is insufficient. Use Octocode MCP for GitHub research, Context7 MCP for library documentation, with WebFetch as final fallback.

**Core principle:** Research BEFORE building, not during. External research enhances planning, not execution.

**This skill is ONLY for external research.** Local codebase search is handled by other cc10x tools (Grep/Glob/Read).

## The Iron Law

```
NO EXTERNAL RESEARCH WITHOUT CLEAR AI KNOWLEDGE GAP OR EXPLICIT USER REQUEST
```

If AI training knowledge covers the technology well, skip external research - UNLESS user explicitly asks. This skill is for NEW technologies, complex integrations, unfamiliar APIs, and explicit user requests.

## Rationalization Prevention

| Excuse | Reality |
|--------|---------|
| "I already know this" | Check if post-2024. API may have changed. |
| "Research takes too long" | 30s research prevents 2hr debugging. |
| "Docs are enough" | GitHub shows real implementations, not ideal cases. |
| "I'll research if stuck" | Research BEFORE is faster than research DURING. |
| "Not worth the tokens" | One good pattern saves 10 bad attempts. |

## When to Use

**ALWAYS invoke when:**
- User explicitly requests research ("research X", "how do others", "best practices", "find on github", "use octocode")
- Technology released after 2024 (AI knowledge cutoff)
- Complex integration patterns (auth, payments, real-time)
- Local debugging failed 3+ times with external service errors

**NEVER invoke when:**
- User says "quick" or "simple"
- Standard patterns AI knows well (CRUD, REST, React basics)
- Code review or refactoring tasks
- Technology released before 2024 (unless user explicitly asks)

**The rule:** Trust octocode for HOW. This skill only decides WHEN.

## User Confirmation Gate (REQUIRED)

**BEFORE any research, ask the user:**

```
AskUserQuestion({
  questions: [{