write-agent-skill
把用户的工作流抽成可复用的 agent skill：通过问答抓意图和边界，设计目录与渐进式披露，把要点写进 SKILL.md 并补齐 references/、assets/、scripts/。要新建技能、把经验模块化或审计现有技能时用它，输出规范化、可验证的技能包。特色是有面向部署的检查表和验证环，确保技能既精简又完整。
▸ 展开 SKILL.md 英文原文
Extracts user workflows into self-contained agent skills by interviewing for intent and edge cases, designing modular packages with progressive disclosure (lean SKILL.md body, on-demand references/), writing step-by-step instructions with gotchas and validation loops, structuring directory trees (references/, assets/, scripts/), and enforcing the full spec checklist before deployment. Use whenever the user asks to create a new agent skill, extract expertise into a skill package, build a reusable workflow, audit an existing skill for compliance, or convert rough notes into a structured SKILL.md.
帮我安装这个 skill：https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/write-agent-skill/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/write-agent-skill/SKILL.md"# Agent Skill Engineer - Create Reusable, Modular AI Agent Skills ## How This Skill Works 1. **Interview** to capture intent, scope, inputs/outputs, edge cases, and failure modes. 2. **Design** the directory layout and progressive disclosure plan. 3. **Draft** the SKILL.md body: concise instructions, gotchas, validation loop. 4. **Populate** `references/`, `assets/`, `scripts/` - never cram detail into SKILL.md. 5. **Validate** against the checklist embedded in `templates/skill-template.md` before delivering. > **Progressive disclosure is non-negotiable.** Metadata (~100 tokens) → Body (<5,000 tokens / <500 lines) → On-demand resources loaded only when referenced with a trigger condition.