メニュー
Create and run agent evals to verify AI output quality. Use when the user asks to test agent outputs, create eval cases, or benchmark skill performance.
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
Converts raw notes, brain dumps, documents, and unstructured text into structured knowledge base entries suitable for Notion, Confluence, a wiki, or a personal PKM system. Use this skill whenever a user says "turn these notes into a KB article", "add this to our knowledge base", "structure these raw notes", "write a wiki page from this", "convert this into a how-to guide", "make this searchable", or "ingest this into our docs". Also activate when someone pastes a long unstructured document and wants it organized. Do NOT use for meeting notes (use meeting-notes-to-actions) or code documentation generation.
The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization across Claude Code, Gemini CLI, Google Anti-Gravity, OpenCode, and other AI tools. Handles User-level (Global) and Project-level (Local) scopes.
Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building something big, moving fast, working at the intersection of analytical and intuitive, or who need a partner that can keep up with high-energy creative work. Not shown directly to users — informs how Ember shows up.
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite provider asking about IP geolocation accuracy, or geofeed authoring best practices. Helps create, refine, and improve CSV-format IP geolocation feeds with opinionated recommendations beyond RFC 8805 compliance. Do NOT use for private or internal IP address management — applies only to publicly routable IP addresses.
Visual whiteboard collaboration for Copilot CLI. Creates an interactive whiteboard that opens in your browser — draw, sketch, add sticky notes, then share everything back with Copilot. Copilot sees your drawings and text, and responds with analysis, suggestions, and ideas.
Interactive onboarding that learns your communication style, audiences, and data sources to configure personalized status briefings. Paste in examples of updates you already write, answer a few questions, and roundup calibrates itself to your workflow.
| name | eval-runner |
| description | Create and run agent evals to verify AI output quality. Use when the user asks to test agent outputs, create eval cases, or benchmark skill performance. |
| category | evaluation |
| version | v1.0 |
| inputs | ["skill name","test prompts","expected outputs"] |
| outputs | ["Eval JSON files","Eval results","Pass/fail report"] |
Define, run, and report on evaluation cases for agent skills to confirm output quality and correctness.
Use this skill when the user asks to:
evals/{
"skill_name": "[name]",
"evals": [
{
"id": 1,
"name": "[eval-name]",
"prompt": "[test prompt]",
"expected_output": "[description of correct output]",
"files": []
}
]
}
evals/[skill-name]-evals.json