skill-invocation-router
Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 7.9w
- Forks
- 1.4w
01 前言 Front Matter
- name
- skill-invocation-router
- license
- MIT
- metadata
- { "lesson": "25" }
- description
- Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.
02 资源文件 9
- 资产文件assets/host-policy.json406 B
- 参考文档references/action-patterns-connectors.md16.5 KB
- 参考文档references/action-patterns-core.md14.9 KB
- 参考文档references/action-patterns-data.md22.5 KB
- 参考文档references/build-patterns.md2.7 KB
- 参考文档references/flow-schema.md4.7 KB
- 参考文档references/invocation-model.md1.4 KB
- 参考文档references/trigger-types.md4.4 KB
- 脚本scripts/simulate_invocation.py6.9 KB
03 SKILL.md 正文
Skill invocation router
Use this skill when a host needs an auditable activation policy rather than one undifferentiated invocable flag.
- Read
references/invocation-model.mdand classify the requested channel. - Review
assets/host-policy.jsonas an example adapter configuration, not a portable standard. - Run
python3 scripts/simulate_invocation.py --policy assets/host-policy.json --actor ACTOR --name NAME --description DESCRIPTION --query QUERY [--explicit-name NAME] [--caller-name NAME] [--depth N] [--user-invocable true|false] [--disable-model-invocation true|false]. - For a human, application, skill, or harness request, require an exact discovered name and its channel-specific allowlist.
- For a skill caller, also require caller identity, a non-cyclic target, and a bounded composition depth.
- For a model or autonomous agent request, remove candidates that the actor or recognized host extensions make ineligible.
- Score only the remaining descriptions. Select the strongest eligible match or abstain when no eligible candidate clears the threshold.
- Return the JSON decision with the adapter, channel, score, and policy reason.
Activation loads instructions. It does not approve tools, filesystem changes, network access, secret use, or bundled scripts.
04 同仓库更多 Skills
write-manual
Writes a long technical manual that explains one subject at one pinned version, from its purpose to each request and response. Every listing comes from an offline capture, every claim traces to a ranked source, and an audit must report TOTAL 0. Use it for "write a manual", "write a 101 manual for <subject>", "manual.json", "add a manual section", "build a capture kit", "audit the manual", or "pin a spec version and document it".
start-learning
One-time onboarding for the AI Engineering from Scratch curriculum (542 lessons, 20 phases). Interviews the learner, runs the placement quiz, and writes LEARNING.md, a persistent study plan the learn skill drives. Trigger phrases: "start learning", "set up the course", "begin the curriculum", "onboard me", "create my learning plan"
motion-figure
Builds figures that move or respond to the reader, in three tiers: SMIL animations and slider widgets inside lessons, interactive mechanism figures that show the named parts of a real system with a computed verdict, and ordered dither bands in the course palette. Triggers: "animated figure", "add a slider widget", "interactive figure", "show how this system works", "make this diagram move", "dither masthead", "mechanism figure", "figure fence".
mcpa-certification
AI-native tutor and onboarding workflow for the MCPA (Model Context Protocol Associate) certification in AI Engineering from Scratch. Use when a learner wants to prepare for the MCPA, resume their certification path, learn the next lesson interactively, run and verify practical labs, take the diagnostic or a full mock, or remediate weak exam domains from GitHub with Claude Code, Codex, ChatGPT, Cursor, or another agent.
lesson-screen
Opens a lesson screen in the browser next to the terminal while a course tutor teaches. It shows the lesson's registered figures, code traces with real values, and clickable predictions. It also builds a figure for the lesson on the fly with the course figure skills and any figure skill the host has installed: a blueprint, a mechanism, an isometric machine, or a 3D model. Clicks return to the tutor as events. Trigger phrases: "open the lesson screen", "show me this visually", "show this in 3D", "draw the architecture", "visualize this lesson", "build a figure for this lesson", "lesson screen".
learn
Interactive lesson tutor for the AI Engineering from Scratch curriculum. Reads LEARNING.md, fetches the next lesson, teaches it section by section in the terminal, quizzes at the end, and records progress. Works cloned or entirely over raw.githubusercontent.com — no setup required. Trigger phrases: "next lesson", "teach me", "continue the course", "let's learn", "resume learning"