外部ライブラリや他言語で書かれたコードの実装を分析する
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill analyze-code --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Analyze Code?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-analyze-code-claude-skill-registry)More formats (shields.io, HTML) on the badges page.
---
name: analyze_code
description: 外部ライブラリや他言語で書かれたコードの実装を分析する
---
# Analyze External Code
This skill helps in understanding code outside of the main Python source tree.
## Instructions
1. **Locate Source**:
* If analyzing an installed library: Find where it is installed (usually `.venv/lib/pythonX.X/site-packages/`).
* If analyzing non-Python code (e.g. C++, MEDM files): Find the files in the file tree.
2. **Read and Analyze**:
* Use `view_file` to read the implementation.
* For binary files or unknown formats, try to find a parser or read as text if applicable (e.g. MEDM `.adl` files are text).
* Map the external logic to how it interacts with or should be implemented in `gwexpy`.
3. **Report**:
* Explain the data structures, algorithms, or logic flow found.
* Highlight differences with the current `gwexpy` implementation.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...