claude-code-skills

Name: claude-code-skills
Rating: 73 (1 reviews)
Author: lldxflwb

lldxflwb/claude-code-skills

This repository provides a collection of extension skills for Claude Code, featuring offline documentation for the Claude Agent SDK, multi-model support via Codex, and TikZ diagram rendering.

29 3MITUpdated 2026-08-13

Good

View on GitHub Open source file

Overview

The claude-code-skills collection equips AI assistants and developers with specialized modules to enhance Claude Code workflows. It includes a comprehensive offline documentation guide for the Claude Agent SDK across Python and TypeScript, tools to invoke external AI models like OpenAI Codex for adversarial planning and code reviews, and utilities for compiling and previewing TikZ diagrams with built-in HTTP servers.

Capabilities

▸Offline documentation querying for Claude Agent SDK APIs, hooks, and subagents
▸Automated documentation syncing via update scripts
▸Adversarial plan review loops between Claude and Codex
▸TikZ-to-SVG compilation and HTTP preview rendering

Best for

Building custom AI agents using the Claude Agent SDK in Python or TypeScript, Reviewing code and adversarial plans by integrating GPT-based models as secondary supervisors, Rendering and previewing LaTeX TikZ diagrams locally with browser support, Bridging separate Claude sessions or running isolated sub-processes

Works with

Claude CodeCursor

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%77 → +15.4

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%85 → +12.8

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%37 → +4.4

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%75 → +7.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%39 → +3.1

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%50 → +2.5

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total72.7 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Executes local scripts and subprocesses including npm packages and Python routines. Ensure all external command-line dependencies come from trusted sources.