一键导入
skill-crafting
Create, edit, and refine agent skills through co-development and eval loops. Use for ANY question about skills or request to create/modify them.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Create, edit, and refine agent skills through co-development and eval loops. Use for ANY question about skills or request to create/modify them.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skill-crafting |
| description | Create, edit, and refine agent skills through co-development and eval loops. Use for ANY question about skills or request to create/modify them. |
| triggers | ["skill-crafting","/skill","/skill-crafting","create a skill","create skill","new skill","write a skill","write skill","build a skill","build skill","craft a skill","make a skill","add a skill","edit skill","update skill","modify skill","change skill","improve skill","refine skill","fix skill","agent skill","claude skill","plugin skill","ai skill","skill development","developing skills","skill design","skill structure","skill format","skill spec","skill specification","how do I create a skill","how do I write a skill","how do I make a skill","how do skills work","how does a skill work","what is a skill","what makes a good skill","can I create a skill","can I make a skill","should I create a skill","what should a skill contain","skill best practices","skill triggers","skill frontmatter"] |
Open @references/guide.md and follow it. Do not proceed without it.
Create effective agent skills through iterative co-development. The skill and its outputs improve together until outputs graduate to exemplars.
The guide contains:
Use when resolving zizmor warnings in GitHub Actions workflows, hardening CI pipelines, or pinning actions to SHA hashes. Covers artipacked, template-injection, excessive-permissions, secrets-outside-env, dependabot-execution, and when to suppress vs fix.
Fetch Basecamp project or person activity into day-cached JSON atoms. Uses the Basecamp API with pagination and rate-limit backoff. Part of the recap plugin's activity fetcher pipeline.
Fetch git log from local repos into day-cached JSON atoms. Simplest activity fetcher — no API calls, no pagination. Part of the recap plugin's activity fetcher pipeline.
Fetch GitHub PRs, reviews, issues, and commits into day-cached JSON atoms. Uses the gh CLI for authentication and API calls. Part of the recap plugin's activity fetcher pipeline.
Activity digests — pluggable source fetchers, progressive timescale synthesis, audience-aware composition. Discovers recap:*-activity fetchers, gathers cached activity, synthesizes narrative at daily/weekly/monthly timescales, and composes output for the target audience.
Create install.md files optimized for AI agent execution. Use for ANY question about install.md files or request to create/review installation documentation for autonomous agent use.