[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EN6J4GRSWKFAGN8JS0F6AA":3,"skill-same:01M7EN6J4GRSWKFAGN8JS0F6AA":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7EN6J4GRSWKFAGN8JS0F6AA","skill-invocation-router",null,"Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.","411tmnd-star\u002Fpyburticapa","411tmnd-star","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227161520?v=4","01M7EN4ZEDRG3BF0XAVY9EWC11","01M7EN4ZGRCMK2293MCDKE0RXV",0,"MIT","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\r\nname: skill-invocation-router\r\ndescription: Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.\r\nlicense: MIT\r\nmetadata:\r\n  lesson: \"25\"\r\n---\r\n\r\n# Skill invocation router\r\n\r\nUse this skill when a host needs an auditable activation policy rather than one undifferentiated `invocable` flag.\r\n\r\n1. Read `references\u002Finvocation-model.md` and classify the requested channel.\r\n2. Review `assets\u002Fhost-policy.json` as an example adapter configuration, not a portable standard.\r\n3. Run `python3 scripts\u002Fsimulate_invocation.py --policy assets\u002Fhost-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]`.\r\n4. For a human, application, skill, or harness request, require an exact discovered name and its channel-specific allowlist.\r\n5. For a skill caller, also require caller identity, a non-cyclic target, and a bounded composition depth.\r\n6. For a model or autonomous agent request, remove candidates that the actor or recognized host extensions make ineligible.\r\n7. Score only the remaining descriptions. Select the strongest eligible match or abstain when no eligible candidate clears the threshold.\r\n8. Return the JSON decision with the adapter, channel, score, and policy reason.\r\n\r\nActivation loads instructions. It does not approve tools, filesystem changes, network access, secret use, or bundled scripts.\r\n","# Skill invocation router\r\n\r\nUse this skill when a host needs an auditable activation policy rather than one undifferentiated `invocable` flag.\r\n\r\n1. Read `references\u002Finvocation-model.md` and classify the requested channel.\r\n2. Review `assets\u002Fhost-policy.json` as an example adapter configuration, not a portable standard.\r\n3. Run `python3 scripts\u002Fsimulate_invocation.py --policy assets\u002Fhost-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]`.\r\n4. For a human, application, skill, or harness request, require an exact discovered name and its channel-specific allowlist.\r\n5. For a skill caller, also require caller identity, a non-cyclic target, and a bounded composition depth.\r\n6. For a model or autonomous agent request, remove candidates that the actor or recognized host extensions make ineligible.\r\n7. Score only the remaining descriptions. Select the strongest eligible match or abstain when no eligible candidate clears the threshold.\r\n8. Return the JSON decision with the adapter, channel, score, and policy reason.\r\n\r\nActivation loads instructions. It does not approve tools, filesystem changes, network access, secret use, or bundled scripts.\r\n",{"name":5,"license":14,"metadata":23,"description":7},{"lesson":24},"25","main","32daff07c322ae4d9381a45a2b3fda5d01496c77","python_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa","https:\u002F\u002Fgithub.com\u002F411tmnd-star","2026-10-19 02:07:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add 411tmnd-star\u002Fpyburticapa --skill skill-invocation-router",{"tool":37,"command":38},"bunx","bunx skills add 411tmnd-star\u002Fpyburticapa --skill skill-invocation-router",{"tool":40,"command":41},"pnpm","pnpm dlx skills add 411tmnd-star\u002Fpyburticapa --skill skill-invocation-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002FSKILL.md",true,[45,51,57],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"assets\u002Fhost-policy.json","ASSET","资产文件",420,"https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002Fassets\u002Fhost-policy.json",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finvocation-model.md","REFERENCE","参考文档",1413,"https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002Freferences\u002Finvocation-model.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fsimulate_invocation.py","SCRIPT","脚本",7222,"https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002Fscripts\u002Fsimulate_invocation.py",[64,71,78,83,90,97],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7EN7BAEA1P7Q4DMS5M01ZMD","skill-release-gate","Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcourse\u002Fai_engineering\u002Fphases\u002F13-tools-and-protocols\u002F27-skill-evals-packaging-and-portability\u002Foutputs\u002Fskill-release-gate\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7EN78JGB07MJQ7XM2FQA23W","skill-safety-reviewer","Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcourse\u002Fai_engineering\u002Fphases\u002F13-tools-and-protocols\u002F26-skill-permissions-sandboxes-and-trust\u002Foutputs\u002Fskill-safety-reviewer\u002FSKILL.md",[],[],{"skillNo":79,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7EN751M878KKQ5W4PFE9D9Q","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcourse\u002Fai_engineering\u002Fphases\u002F13-tools-and-protocols\u002F25-skill-invocation-and-routing\u002Foutputs\u002Fskill-invocation-router\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7EN71TK8V72WAQ5KWC2Z8EN","skill-catalog-builder","Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bodies.","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcourse\u002Fai_engineering\u002Fphases\u002F13-tools-and-protocols\u002F24-skill-discovery-and-progressive-disclosure\u002Foutputs\u002Fskill-catalog-builder\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7EN6ZNWJQ4XS7R5QDWE7P3Y","skill-contract-reviewer","Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcourse\u002Fai_engineering\u002Fphases\u002F13-tools-and-protocols\u002F22-skills-and-agent-sdks\u002Foutputs\u002Fskill-contract-reviewer\u002FSKILL.md",[],[],{"skillNo":98,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7EN6R9WXTB69MKC71RW925V","https:\u002F\u002Fgithub.com\u002F411tmnd-star\u002Fpyburticapa\u002Fblob\u002Fmain\u002Fpython_skills\u002Fcorpus\u002Fagents_and_tools\u002Fskills\u002F27-skill-evals-packaging-and-portability\u002Foutputs\u002Fskill-release-gate\u002FSKILL.md",[],[]]