.claude/skills/codex-plan-review/SKILL.md
OpenAI Codex CLIで実装プランをレビュー。Plan作成後にユーザー確認前に実行。「プランレビュー」「plan review」などで起動。
npx skillsauth add nomhiro/entire-poc codex-plan-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
OpenAI Codex CLI を使って実装プランの妥当性をレビューする。
codex exec "以下の実装プランをレビューしてください。技術的妥当性、既存アーキテクチャとの整合性、リスク、影響範囲の漏れを指摘してください:
$(cat <plan-file-path>)"
tools
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
testing
AI-driven prior art / patentability search. Use this skill whenever the user asks you to investigate whether an invention idea is patentable, to search for prior art, to check for overlapping patents, or to evaluate novelty / inventive step of a technical concept. Trigger phrases include: "特許調査", "先行技術調査", "特許性を調べて", "先行特許", "prior art search", "patentability", "is this idea patented", "既存特許との重複", "新規性", "進歩性", "クレーム分析". Also trigger when users describe an invention and ask if it's novel or if similar patents exist, even if they don't use the word "patent" explicitly — e.g. "この技術って既にある?", "誰か似たようなもの作ってない?".
tools
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
development
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.