[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMC77NYTH154FGR6SNPECX":3,"skill-same:01M7DMC77NYTH154FGR6SNPECX":63},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M7DMC77NYTH154FGR6SNPECX","specification-system",null,"Use when authoring rig specs, agent specs, workflow specs, startup\u002Fcontext fragments, operating-mode declarations, or designing the user spec library. Covers the 4 failure modes (spec instantiates topology but not workflow\u002Fmode; spec depends on local paths and fails on another host; agents modify specs as one-off files instead of preserving reusable intent; validation proves YAML shape but not whether topology can run) and the validation-vs-runtime-realization distinction.","mvschwarz\u002Fopenrig-world","mvschwarz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F171890339?v=4","01M7DM95A4N5936P8G2FTSPMY7","Mike Schwarz","01M7DM95AX80NY8HZA7XXDYAZR",16,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Fagents\u002Fshared\u002Fskills\u002Fcore\u002Fspecification-system\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: specification-system\ndescription: Use when authoring rig specs, agent specs, workflow specs, startup\u002Fcontext fragments, operating-mode declarations, or designing the user spec library. Covers the 4 failure modes (spec instantiates topology but not workflow\u002Fmode; spec depends on local paths and fails on another host; agents modify specs as one-off files instead of preserving reusable intent; validation proves YAML shape but not whether topology can run) and the validation-vs-runtime-realization distinction.\nmetadata:\n  cli_surfaces_referenced:\n    - agent\n    - bundle\n    - spec\n    - specs\n  openrig:\n    stage: factory-approved\n    sibling_skills:\n      - rig-lifecycle\n      - topology-mutation-and-seat-management\n      - seat-scaling-and-specialization\n      - cross-host-rig-commands\n      - sidecar-operator\n      - rig-bundles-and-shareable-artifacts\n      - extension-and-user-workspace\n---\n\n# Specification System\n\nThe declarative primitive family for OpenRig intent: **rig specs, agent\nspecs, workflow specs, startup\u002Fcontext fragments, operating-mode\ndeclarations, and the user spec library that stores and reuses them.**\n\nSpecs are how humans and agents describe **repeatable topology and\nbehavior** without re-explaining it in chat. They are also shareable\nartifacts: a user should be able to publish a spec or spec family so\nanother user can instantiate the same rig shape, role structure, or\nworkflow pattern.\n\n**Without a dependable spec primitive, OpenRig depends on manual\nstartup prompts and tribal memory.** That blocks repeatability, product\ndemos, rig bundles, and autonomous rig construction.\n\n## Use this when\n\n- Authoring a RigSpec \u002F AgentSpec \u002F workflow spec\n- Designing a startup\u002Fcontext fragment\n- Reasoning about spec-library lifecycle (validation, sharing, upgrade semantics)\n- Auditing a spec for portability (does it run on another host?)\n- Distinguishing spec vs bundle vs extension cleanly\n\n## Don't use this when\n\n- The work is one-off and won't be reused. Manual rig assembly is fine for one-shot work.\n- The intent is to package a topology + workflow as a shareable artifact. That's `rig-bundles-and-shareable-artifacts`.\n- The intent is to add runtime behavior. That's `extension-and-user-workspace`.\n\n## Failure modes (4)\n\n1. **A spec can instantiate a topology but not the workflow or operating mode needed to use it.** Topology is necessary but not sufficient — workflow and operating mode must be declared too.\n2. **A shared spec depends on local paths or hidden startup fragments and fails on another host.** Specs must be self-describing for portability.\n3. **Agents modify specs as one-off files instead of preserving reusable user\u002Flibrary intent.** Specs are reusable; treating each instance as one-off destroys the primitive's value.\n4. **Validation proves YAML shape but not whether the declared topology can actually run.** Structural validation is not enough; runtime realization is the real proof.\n\n## Proof standard\n\nProof should:\n\n1. Author a spec\n2. Validate it (structural)\n3. Install it (into spec library)\n4. Instantiate it on a **clean OpenRig environment**\n5. Show **both structural validation AND runtime realization**\n\nValidation alone is insufficient.\n\n## Spec \u002F bundle \u002F extension boundary\n\n| Concept | Declares | Example |\n|---|---|---|\n| **Spec** | Topology \u002F role \u002F workflow shape (declarative intent) | `rig.yaml`, `agent.yaml`, `workflow.yaml` |\n| **Bundle** | Spec(s) + supporting fragments packaged for shareable instantiation | A Velocity Team bundle |\n| **Extension** | Runtime behavior added to user workspace | RigX command, custom view |\n\nDon't conflate them. The contract should distinguish spec, bundle, and\nextension cleanly.\n\n## Currently shipped surfaces\n\nOpenRig already has:\n\n- RigSpec \u002F AgentSpec authoring (`agent.yaml`, `rig.yaml` formats; see `openrig-architect` skill)\n- Workflow specs (markdown\u002FYAML files, daemon read-through cache via `workflow_specs` table; see `workflow-runtime` skill)\n- Bundle\u002Fspec command surface (`rig bundle \u002F spec \u002F agent \u002F specs ls\u002Fshow\u002Fpreview\u002Fadd\u002Fsync\u002Fremove\u002Frename`)\n- Spec library (filesystem-backed at `packages\u002Fdaemon\u002Fspecs\u002F` + `~\u002F.openrig\u002Fspecs\u002F` per cli-reference.md)\n\nNot yet shipped:\n- Spec library lifecycle (validation, sharing, upgrade) treated as a first-class primitive\n- Cross-host spec sharing\n- Marketplace \u002F public registry\n\n## See also\n\n- `openrig-architect` skill — RigSpec \u002F AgentSpec authoring discipline\n- `workflow-runtime` skill — workflow spec authoring + transactional-scribe contract\n- `rig-bundles-and-shareable-artifacts` skill — bundle is the packaged form of specs\n- `extension-and-user-workspace` skill — extensions add runtime behavior; specs declare intent\n- `openrig\u002Fdocs\u002Freference\u002Frig-spec.md` (product reference doc) — RigSpec format specification\n- `openrig\u002Fdocs\u002Freference\u002Fagent-spec.md` (product reference doc) — AgentSpec format specification\n","# Specification System\n\nThe declarative primitive family for OpenRig intent: **rig specs, agent\nspecs, workflow specs, startup\u002Fcontext fragments, operating-mode\ndeclarations, and the user spec library that stores and reuses them.**\n\nSpecs are how humans and agents describe **repeatable topology and\nbehavior** without re-explaining it in chat. They are also shareable\nartifacts: a user should be able to publish a spec or spec family so\nanother user can instantiate the same rig shape, role structure, or\nworkflow pattern.\n\n**Without a dependable spec primitive, OpenRig depends on manual\nstartup prompts and tribal memory.** That blocks repeatability, product\ndemos, rig bundles, and autonomous rig construction.\n\n## Use this when\n\n- Authoring a RigSpec \u002F AgentSpec \u002F workflow spec\n- Designing a startup\u002Fcontext fragment\n- Reasoning about spec-library lifecycle (validation, sharing, upgrade semantics)\n- Auditing a spec for portability (does it run on another host?)\n- Distinguishing spec vs bundle vs extension cleanly\n\n## Don't use this when\n\n- The work is one-off and won't be reused. Manual rig assembly is fine for one-shot work.\n- The intent is to package a topology + workflow as a shareable artifact. That's `rig-bundles-and-shareable-artifacts`.\n- The intent is to add runtime behavior. That's `extension-and-user-workspace`.\n\n## Failure modes (4)\n\n1. **A spec can instantiate a topology but not the workflow or operating mode needed to use it.** Topology is necessary but not sufficient — workflow and operating mode must be declared too.\n2. **A shared spec depends on local paths or hidden startup fragments and fails on another host.** Specs must be self-describing for portability.\n3. **Agents modify specs as one-off files instead of preserving reusable user\u002Flibrary intent.** Specs are reusable; treating each instance as one-off destroys the primitive's value.\n4. **Validation proves YAML shape but not whether the declared topology can actually run.** Structural validation is not enough; runtime realization is the real proof.\n\n## Proof standard\n\nProof should:\n\n1. Author a spec\n2. Validate it (structural)\n3. Install it (into spec library)\n4. Instantiate it on a **clean OpenRig environment**\n5. Show **both structural validation AND runtime realization**\n\nValidation alone is insufficient.\n\n## Spec \u002F bundle \u002F extension boundary\n\n| Concept | Declares | Example |\n|---|---|---|\n| **Spec** | Topology \u002F role \u002F workflow shape (declarative intent) | `rig.yaml`, `agent.yaml`, `workflow.yaml` |\n| **Bundle** | Spec(s) + supporting fragments packaged for shareable instantiation | A Velocity Team bundle |\n| **Extension** | Runtime behavior added to user workspace | RigX command, custom view |\n\nDon't conflate them. The contract should distinguish spec, bundle, and\nextension cleanly.\n\n## Currently shipped surfaces\n\nOpenRig already has:\n\n- RigSpec \u002F AgentSpec authoring (`agent.yaml`, `rig.yaml` formats; see `openrig-architect` skill)\n- Workflow specs (markdown\u002FYAML files, daemon read-through cache via `workflow_specs` table; see `workflow-runtime` skill)\n- Bundle\u002Fspec command surface (`rig bundle \u002F spec \u002F agent \u002F specs ls\u002Fshow\u002Fpreview\u002Fadd\u002Fsync\u002Fremove\u002Frename`)\n- Spec library (filesystem-backed at `packages\u002Fdaemon\u002Fspecs\u002F` + `~\u002F.openrig\u002Fspecs\u002F` per cli-reference.md)\n\nNot yet shipped:\n- Spec library lifecycle (validation, sharing, upgrade) treated as a first-class primitive\n- Cross-host spec sharing\n- Marketplace \u002F public registry\n\n## See also\n\n- `openrig-architect` skill — RigSpec \u002F AgentSpec authoring discipline\n- `workflow-runtime` skill — workflow spec authoring + transactional-scribe contract\n- `rig-bundles-and-shareable-artifacts` skill — bundle is the packaged form of specs\n- `extension-and-user-workspace` skill — extensions add runtime behavior; specs declare intent\n- `openrig\u002Fdocs\u002Freference\u002Frig-spec.md` (product reference doc) — RigSpec format specification\n- `openrig\u002Fdocs\u002Freference\u002Fagent-spec.md` (product reference doc) — AgentSpec format specification\n",{"name":5,"metadata":24,"description":7},{"openrig":25,"cli_surfaces_referenced":35},{"stage":26,"sibling_skills":27},"factory-approved",[28,29,30,31,32,33,34],"rig-lifecycle","topology-mutation-and-seat-management","seat-scaling-and-specialization","cross-host-rig-commands","sidecar-operator","rig-bundles-and-shareable-artifacts","extension-and-user-workspace",[36,37,38,39],"agent","bundle","spec","specs","main","60438a272b68d091eddb01aad6e399af4996d536","agents\u002Fshared\u002Fskills\u002Fcore\u002Fspecification-system",4,"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world","https:\u002F\u002Fgithub.com\u002Fmvschwarz","https:\u002F\u002Fopenrig.dev","Building OpenRig. Running rogue AI civilizations. Debugging their coordination problems.","2026-11-12 13:31:38",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill specification-system",{"tool":55,"command":56},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill specification-system",{"tool":58,"command":59},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill specification-system","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Fagents\u002Fshared\u002Fskills\u002Fcore\u002Fspecification-system\u002FSKILL.md",true,[],[64,71,78,85,92,99],{"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},"01M7DMSEDCRREMBJF57RQB59HC","notes","Use when taking notes.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Ftools\u002Ftest\u002Ffixtures\u002Finstall-verify\u002Fbundle\u002Fagents\u002Fteam\u002Fskills\u002Fnotes\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},"01M7DMSBZP9WE8MC09JDXFCR2F","software-for-agents","Use when older OpenRig instructions name software-for-agents or describe agent-in-the-middle or studio software under the former skill name.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsoftware-for-agents\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},"01M7DMS55VHEAGPXMHZJ7FX94R","session-compaction-and-restore","Use when reasoning about what survives compaction\u002Fcontext-loss\u002Frestart\u002Fseat-refresh, designing a high-fidelity restore packet, or distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild. Covers the 4 failure modes that prevent honest restore (compacted seat drops hot potato; restore packet preserves details but loses product intent; runtime resume mistaken for handover or fork; rebuilt seat starts with stale instructions).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\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},"01M7DMRYQK0JTV7MMVHFWZ0BW0","seat-continuity-and-handover","Use when replacing a seat's occupant (rebuild\u002Fhandover\u002Fswap), reasoning about stable-seat-identity vs fluid-occupant-identity, choosing an old-occupant disposition (retire\u002Fadvise\u002Fshadow), or recording provenance for an occupant change. Two independent outcomes (continuityOutcome + seatBindingOutcome) and the 5 failure modes that prevent silent dishonesty.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fseat-continuity-and-handover\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},"01M7DMRP6RRGCJZSH9CE3PC1MY","retiring-and-inheriting-a-seat","Use when you are a sitting agent near your context threshold (~85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure), physical-seat continuity, the do-not-over-inherit framing, the optional warm-handoff window, and wake-v0 (consulting a retired predecessor). NOT for unplanned compaction\u002Fcrash recovery (session-compaction-and-restore \u002F claude-compaction-restore) and NOT the seat-binding primitive mechanics (seat-continuity-and-handover).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7DMRJGN6Z8TZDR7JNHXH6KX","refocusing","Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Frefocusing\u002FSKILL.md",[],[]]