references
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
02 资源文件 36
- 参考文档afk.md1.9 KB
- 参考文档agent-mode.md1.9 KB
- 参考文档agent.md1.3 KB
- 参考文档agents-md.md1.9 KB
- 参考文档automated-check.md2.0 KB
- 参考文档clearing.md1.5 KB
- 参考文档compaction.md1.7 KB
- 参考文档context-pointer.md2.2 KB
- 参考文档context-window.md1.5 KB
- 参考文档context.md1.8 KB
- 参考文档effort.md2.0 KB
- 参考文档environment.md2.2 KB
- 参考文档grilling.md1.2 KB
- 参考文档harness.md1.7 KB
- 参考文档human-in-the-loop.md1.9 KB
- 参考文档human-review.md1.4 KB
- 参考文档mcp.md2.0 KB
- 参考文档memory-system.md1.6 KB
- 参考文档model.md1.5 KB
- 参考文档parametric-knowledge.md1.7 KB
- 参考文档primary-source.md1.6 KB
- 参考文档progressive-disclosure.md1.5 KB
- 参考文档prototyping.md1.7 KB
- 参考文档secondary-source.md2.2 KB
- 参考文档session.md1.7 KB
- 参考文档smart-zone.md2.1 KB
- 参考文档spec.md1.6 KB
- 参考文档stateful.md2.5 KB
- 参考文档stateless.md1.7 KB
- 参考文档subagent.md1.4 KB
- 参考文档ticket.md1.4 KB
- 参考文档token.md1.9 KB
- 参考文档tool-call.md1.8 KB
- 参考文档tool.md2.2 KB
- 参考文档turn.md1.6 KB
- 参考文档vibe-coding.md1.8 KB
03 SKILL.md 正文
Skill
A teachable capability bundled as a unit: instructions and resources for doing one task well, kept in the environment until a context pointer pulls it into the context window for the task at hand. The unit of progressive disclosure in a harness.
Skills are an open standard, defined at agentskills.io, originally developed by Anthropic and since adopted by most major harnesses, so a skill written once works across them. The format is a folder containing:
- A
SKILL.mdfile: metadata (a name and description, at minimum) plus the instructions themselves - Optionally, scripts the agent can run
- Optionally, templates and reference material the instructions point to
Only the name and description sit in context by default. When the agent's task matches, it loads the rest. Until then, the skill takes up almost no room: a sentence or two of tokens, however large its full instructions are.
This distinguishes skills from AGENTS.md, which is loaded into every session regardless of the task. A skill is read when a particular kind of work comes up (releasing, scaffolding a new service, writing a migration) and ignored the rest of the time.
Avoid: "tool". A tool is what the agent calls; a skill is instructions it reads.
Usage:
"Where should I put the deploy runbook?"
"As a skill: the agent loads it only when the task involves deploys. In AGENTS.md it'd burn tokens on every turn for something we use weekly."
04 同仓库更多 Skills
wait-what
Stop. That last message did not land: re-pitch it.
to-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
teach
Teach the user a new skill or concept, within this workspace.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.