Agent Skills › rohitg00/ai-engineering-from-scratch › skill-invocation-router

skill-invocation-router

GitHub

用于设计、测试和评估 Agent Skill 目录中不同调用渠道（人类、模型、程序等）的激活策略与路由逻辑，确保调用的可审计性与合规性。

phases/13-tools-and-protocols/25-skill-invocation-and-routing/outputs/skill-invocation-router/SKILL.md rohitg00/ai-engineering-from-scratch

触发场景

需要为 Agent Skill 配置明确的调用激活策略模拟和验证技能调用的准入规则与评分机制

安装

npx skills add rohitg00/ai-engineering-from-scratch --skill skill-invocation-router -g -y

更多选项

非标准路径

npx skills add https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/phases/13-tools-and-protocols/25-skill-invocation-and-routing/outputs/skill-invocation-router -g -y

不安装直接使用

npx skills use rohitg00/ai-engineering-from-scratch@skill-invocation-router

指定 Agent (Claude Code)

npx skills add rohitg00/ai-engineering-from-scratch --skill skill-invocation-router -a claude-code -g -y

安装 repo 全部 skill

npx skills add rohitg00/ai-engineering-from-scratch --all -g -y

预览 repo 内 skill

npx skills add rohitg00/ai-engineering-from-scratch --list

SKILL.md

Frontmatter

{
    "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."
}

Skill invocation router

Use this skill when a host needs an auditable activation policy rather than one undifferentiated invocable flag.

Read references/invocation-model.md and classify the requested channel.
Review assets/host-policy.json as 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.