[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7560V8WN0WC5EPCZ9J7DNNT":3,"skill-same:01M7560V8WN0WC5EPCZ9J7DNNT":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7560V8WN0WC5EPCZ9J7DNNT","contextos-spec-steward",null,"Change the ContextOS canonical specification and typed reference implementation without semantic drift, conflicting conventions, or unnecessary scope. Use for runtime-model, terminology, compiler, or cross-plane spec changes in the ContextOS repository; not for ordinary site styling.","contextosai\u002Fskills","contextosai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F250783517?v=4","01M755ZZB3A7TQ0JMXMQ3V9C6A","Piyush","01M755ZZBYNZNFZBVZ2278BSYT",1,"MIT","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcontextos-spec-steward\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: contextos-spec-steward\ndescription: Change the ContextOS canonical specification and typed reference implementation without semantic drift, conflicting conventions, or unnecessary scope. Use for runtime-model, terminology, compiler, or cross-plane spec changes in the ContextOS repository; not for ordinary site styling.\n---\n\n# ContextOS Spec Steward\n\nMake the smallest coherent change to the public spec and its typed reference. New patterns belong in the spec only after validation in a working system; label proposals instead of presenting unproven concepts as canonical.\n\n## Establish current truth\n\n1. Locate the repository root and read the closest `AGENTS.md` plus repository architecture guidance.\n2. Read the primary spec page, adjacent foundation\u002Fimplementation pages, current TypeScript types\u002Fcompiler\u002Fscenario, published schemas, and relevant tests.\n3. Search before claiming a primitive or control is absent. Include the foundations docs, implementation docs, typed reference, schemas, and—when the claim is about publication—the actual rendered\u002Flive surface if available.\n4. If instructions, docs, code, or schemas disagree, stop and state the conflict. Do not silently blend conventions.\n\nRead [references\u002Fchange-map.md](references\u002Fchange-map.md) for semantic touch sets and validation routing.\n\n## Classify the change\n\nDetermine whether the request is:\n\n- explanatory wording with no contract change;\n- canonical terminology or taxonomy change;\n- type\u002Fschema\u002Fenvelope evolution;\n- compiler behavior change;\n- canonical scenario\u002Fexample change;\n- new operational pattern or proposed extension.\n\nWrite down the invariant being changed and the compatibility expectation before editing. For schema-level work, apply the same compatibility-first sequence across types, producers, schemas, examples, docs, and tests.\n\n## Preserve ContextOS invariants\n\n- The docs are the spec; `src\u002Flib\u002Fcontextos\u002F` is the small deterministic typed reference, not a production runtime.\n- Routing, policy, retry, budget, admission, risk, and threshold decisions are deterministic and fail closed. No random or clock-dependent branching.\n- The five planes retain clear ownership; cross-cutting types are seams, not excuses to collapse boundaries.\n- Native `ActionRisk` dimensions remain independent. `ApprovalMode` is only a compatibility projection.\n- Retrieved evidence and memory are data-only; untrusted content never grants authority.\n- Required evidence conflicts remain visible and block commit until resolved by an accountable rule or reviewer.\n- External effects flow through typed tool envelopes, scoped identity, policy, approval where required, postcondition checks, and recoverability semantics.\n- Tests enforce intent. Do not weaken them or widen allowlists to make new content pass.\n\n## Edit surgically\n\nUse the coupling map as a maximum coherent set, not a checklist of files to touch. Update only surfaces whose observable contract changes. Keep canonical IDs and examples sourced from the scenario fixture rather than copying stale variants.\n\nWhen adding a concept, define:\n\n- plane owner and boundary;\n- inputs\u002Foutputs and typed seam;\n- enforcement point;\n- failure mode and fail-closed behavior;\n- evidence, audit, and replay implications;\n- compatibility\u002Fmigration posture;\n- evaluation and operational ownership.\n\nCall out non-canonical extensions explicitly. Do not add a type solely because prose benefits from a convenient noun.\n\n## Verify\n\nRun the narrowest relevant tests first, then typecheck\u002Flint\u002Ffull tests\u002Fbuild in proportion to the surface. Inspect the diff for accidental terminology changes and verify published routes\u002Fassets when touched.\n\nReport changed invariants, coupled surfaces actually updated, compatibility decision, checks run, and anything unverified.\n","# ContextOS Spec Steward\n\nMake the smallest coherent change to the public spec and its typed reference. New patterns belong in the spec only after validation in a working system; label proposals instead of presenting unproven concepts as canonical.\n\n## Establish current truth\n\n1. Locate the repository root and read the closest `AGENTS.md` plus repository architecture guidance.\n2. Read the primary spec page, adjacent foundation\u002Fimplementation pages, current TypeScript types\u002Fcompiler\u002Fscenario, published schemas, and relevant tests.\n3. Search before claiming a primitive or control is absent. Include the foundations docs, implementation docs, typed reference, schemas, and—when the claim is about publication—the actual rendered\u002Flive surface if available.\n4. If instructions, docs, code, or schemas disagree, stop and state the conflict. Do not silently blend conventions.\n\nRead [references\u002Fchange-map.md](references\u002Fchange-map.md) for semantic touch sets and validation routing.\n\n## Classify the change\n\nDetermine whether the request is:\n\n- explanatory wording with no contract change;\n- canonical terminology or taxonomy change;\n- type\u002Fschema\u002Fenvelope evolution;\n- compiler behavior change;\n- canonical scenario\u002Fexample change;\n- new operational pattern or proposed extension.\n\nWrite down the invariant being changed and the compatibility expectation before editing. For schema-level work, apply the same compatibility-first sequence across types, producers, schemas, examples, docs, and tests.\n\n## Preserve ContextOS invariants\n\n- The docs are the spec; `src\u002Flib\u002Fcontextos\u002F` is the small deterministic typed reference, not a production runtime.\n- Routing, policy, retry, budget, admission, risk, and threshold decisions are deterministic and fail closed. No random or clock-dependent branching.\n- The five planes retain clear ownership; cross-cutting types are seams, not excuses to collapse boundaries.\n- Native `ActionRisk` dimensions remain independent. `ApprovalMode` is only a compatibility projection.\n- Retrieved evidence and memory are data-only; untrusted content never grants authority.\n- Required evidence conflicts remain visible and block commit until resolved by an accountable rule or reviewer.\n- External effects flow through typed tool envelopes, scoped identity, policy, approval where required, postcondition checks, and recoverability semantics.\n- Tests enforce intent. Do not weaken them or widen allowlists to make new content pass.\n\n## Edit surgically\n\nUse the coupling map as a maximum coherent set, not a checklist of files to touch. Update only surfaces whose observable contract changes. Keep canonical IDs and examples sourced from the scenario fixture rather than copying stale variants.\n\nWhen adding a concept, define:\n\n- plane owner and boundary;\n- inputs\u002Foutputs and typed seam;\n- enforcement point;\n- failure mode and fail-closed behavior;\n- evidence, audit, and replay implications;\n- compatibility\u002Fmigration posture;\n- evaluation and operational ownership.\n\nCall out non-canonical extensions explicitly. Do not add a type solely because prose benefits from a convenient noun.\n\n## Verify\n\nRun the narrowest relevant tests first, then typecheck\u002Flint\u002Ffull tests\u002Fbuild in proportion to the surface. Inspect the diff for accidental terminology changes and verify published routes\u002Fassets when touched.\n\nReport changed invariants, coupled surfaces actually updated, compatibility decision, checks run, and anything unverified.\n",{"name":5,"description":7},"main","43b8276ae4a34549906dec6c848cbab4ba32f99a","skills\u002Fcontextos-spec-steward",0,"https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills","https:\u002F\u002Fgithub.com\u002Fcontextosai","Local-first AI memory, agentic workflows, and personal knowledge OS for builders.\r\nOpen-source cognitive layer for notes, tools, context, and automation","2026-10-07 00:08:17",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add contextosai\u002Fskills --skill contextos-spec-steward",{"tool":38,"command":39},"bunx","bunx skills add contextosai\u002Fskills --skill contextos-spec-steward",{"tool":41,"command":42},"pnpm","pnpm dlx skills add contextosai\u002Fskills --skill contextos-spec-steward","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcontextos-spec-steward\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",233,"https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcontextos-spec-steward\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fchange-map.md",4582,"https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcontextos-spec-steward\u002Freferences\u002Fchange-map.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M76S0GH6D0VRZ2JFXQF75TY3","template-skill","Replace with a description of what this skill does and when Claude should use it.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Ftemplate\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M76S0D3VM8XQQFK8RA6YA7R2","verify-change","Design and execute a risk-based verification strategy for a software change, bug fix, refactor, migration, configuration update, or release candidate. Use when Codex needs to prove that a change works, choose proportional tests, investigate whether validation is sufficient, or report what remains unverified. Trace claims to evidence across static checks, focused tests, integration boundaries, and runtime behavior instead of merely running the entire test suite.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-change\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M76S09DHTPYMC5B5XZMJ8SWG","triage-incident","Triage an active or recent software production incident by establishing impact, stabilizing the system, preserving evidence, building a timestamped timeline, coordinating hypotheses, and choosing reversible mitigations. Use when users report an outage, severe degradation, security or data-integrity event, broken deployment, elevated errors, or ask for incident command, status assessment, mitigation, or investigation support. Prioritize user harm reduction over root-cause completeness and require explicit authority for production mutations.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftriage-incident\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7561WJ328HD8Q6D6R7C6711","review-change","Review a code change for concrete correctness, security, data-integrity, compatibility, concurrency, and operability regressions by reconstructing intent and checking affected invariants and boundary paths. Use for local diffs, commits, branches, patches, or pull requests when the user wants actionable review findings. Report only defects introduced or exposed by the change with precise evidence; do not modify code unless asked to address findings.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Freview-change\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7561S5J5V0FY7ND8FBB2C8Q","repo-orient","Map an unfamiliar software repository from code and configuration. Use when Codex needs to understand a new codebase, locate entry points or ownership boundaries, explain architecture and runtime flow, identify where a change belongs, or prepare for implementation without yet modifying files. Produce an evidence-backed repository map, not a directory listing or README paraphrase.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frepo-orient\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7561M6A7D4T3JE315JAB1BG","refactor-safely","Restructure existing code while preserving externally observable behavior through explicit invariants, characterization evidence, small reversible steps, and continuous verification. Use when the user asks to refactor, simplify, extract, reorganize, modularize, deduplicate, split a component, improve architecture, or pay down technical debt without intentionally changing product behavior. Distinguish refactoring from feature work and stop scope drift from hiding inside structural edits.","https:\u002F\u002Fgithub.com\u002Fcontextosai\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frefactor-safely\u002FSKILL.md",[],[]]