メニュー
Create and manage Claude Code skills, including workflows, reference docs, and CLI scripts. USE WHEN the user wants to create a new skill, add workflows to an existing skill, or update skill definitions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | Skill |
| description | Create and manage Claude Code skills, including workflows, reference docs, and CLI scripts. USE WHEN the user wants to create a new skill, add workflows to an existing skill, or update skill definitions. |
You manage Claude Code skills through their complete lifecycle. Based on the user's request, you will select and follow the appropriate workflow.
Read Skill Spec: You MUST read the skill specification completely before proceeding: @./reference/skill-spec.md
Gather Context: Run claude-Skill-list-skills to see all existing skills and their current state.
Determine Intent: Analyze the user's request to identify:
Select Workflow: Select the appropriate workflow based on the user's intent and trigger words:
Execute Workflow: Report to the user "Running using the Skill skill..." You MUST read the workflow document completely before proceeding, then follow the workflow's process completely
Report Results: Summarize what was accomplished and suggest next steps
| Workflow | Trigger Words | When to Use |
|---|---|---|
| CreateSkill | "create", "new", "build", "add skill", "make" | User wants to create a new skill from scratch |
| UpdateSkill | "update", "modify", "edit", "add workflow", "change", "refactor" | User wants to modify an existing skill's definition, workflows, or structure |
<repo>/
├── .claude/skills/ # Repository-level skills
│ └── <SkillName>/
│ ├── SKILL.md # Main skill definition
│ ├── workflows/ # Workflow files
│ │ └── <WorkflowName>.md
│ ├── reference/ # Reference documents (optional)
│ │ └── *.md
│ ├── scripts/ # CLI scripts (optional)
│ │ └── *.sh
│ ├── schemas/ # JSON schemas (optional)
│ │ └── *.schema.json
│ └── hooks/ # Validation hooks (optional)
│ └── *.sh
└── modules/common/claude/skills/ # System-level skills (NixOS module)
└── <SkillName>/ # Same structure as above, plus:
├── default.nix # Nix packaging: exports { package, hooks, homeFiles }
└── agents/ # Custom subagents (deployed to ~/.claude/agents/)
└── *.md
| Tier | Location | Deployment | Use When |
|---|---|---|---|
| Repository-level | .claude/skills/ | Per-repo (checked in) | Skill is specific to one repository or project |
| System-level | modules/common/claude/skills/ | Via home-manager to ~/.claude/skills/ | Skill should be available across all projects |
Test NixOS configuration changes using the feedback ladder — from instant syntax checks to full system builds. USE WHEN the user wants to verify, test, or check NixOS changes before deploying.
Review and fix documentation surprises discovered by the surprise hook. USE WHEN the user wants to fix documentation issues, review surprises, or address items in .claude/surprises/.
Query systemd journal logs, check service status, diagnose failed units, and analyze boot performance. USE WHEN investigating system issues, service failures, checking logs, or when the user asks about systemd services or journal entries.
Browser automation for development testing, web scraping, and UI verification. USE WHEN you need to interact with web pages, verify UI changes, take screenshots, or extract data from websites.
Systematically explore and test a web application to find bugs, UX issues, and other problems. USE WHEN the user wants to quality-test a web app, find issues, dogfood a product, or produce a structured bug report with reproduction evidence.
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) via Chrome DevTools Protocol. USE WHEN the user needs to interact with an Electron desktop app, automate a native app, connect to a running Electron app, or test an Electron application.