[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMAXEHDPT17Z68R45SA1JB":3,"skill-same:01M7DMAXEHDPT17Z68R45SA1JB":51},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7DMAXEHDPT17Z68R45SA1JB","openrig-skills",null,"Use when you're operating OpenRig and need the right skill or context for fleet recovery, seat handover, new-seat orientation, a watchdog wake, cross-host reach to an agent on another machine, rig packaging, an OpenRig upgrade, systematic debugging, queue triage, or implementation planning; also use when you don't know what applies or nothing is projected on cold boot.","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\u002Fopenrig-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openrig-skills\ndescription: \"Use when you're operating OpenRig and need the right skill or context for fleet recovery, seat handover, new-seat orientation, a watchdog wake, cross-host reach to an agent on another machine, rig packaging, an OpenRig upgrade, systematic debugging, queue triage, or implementation planning; also use when you don't know what applies or nothing is projected on cold boot.\"\nallowed-tools: Bash(rig:*)\nmetadata:\n  openrig:\n    stage: shipped\n---\n\n# OpenRig skills — the index (start here)\n\nYou're running inside OpenRig. OpenRig ships a set of **skills** — small documents that tell you *when* to do something and *how*. This file is the map: what ships, when to reach for each, and how to load it. If you don't know which skill applies, or nothing is projected into your context, **start here.**\n\n## How OpenRig context works (30 seconds)\n\nSkills are **progressive disclosure**: a skill's *name + description* sit in your context ambiently (the \"hot tier\"); its *body* loads only when you open it. So you don't pre-read everything — you pattern-match a skill's \"when\" to your moment, then open just that one. This file is the index over the whole shipped set. (For bounded procedures, open `agent-operated-workflows`; for ongoing agent-backed applications, open `agent-operated-software`.)\n\nEvery row below names **how to reach the skill** — already-hot, or an exact load path. No row is a dead end.\n\n## Loading an entry on demand — `rig context get`\n\nDon't guess a file path or a name. Go **ask → ref → load** in three steps:\n\n1. **Discover** — run `rig context list` for every shipped entry's **ref** and name. The *when* for\n   each is the index below (or `rig context list --json`, which carries each entry's purpose) — match\n   your moment there.\n2. **Select** — match your moment to a row's *when* and take its **ref**. Refs are canonical full paths\n   that mirror the library layout — `skills\u002F\u003Cnamespace>\u002F\u003Cname>` (e.g. `skills\u002Fcore\u002Frig-lifecycle`,\n   `skills\u002Fprocess\u002Fsystematic-debugging`). A unique bare name (e.g. `watchdog`) also resolves; any\n   slash-bearing ref is an exact lookup and fails loud if it does not exist.\n3. **Load** — `rig context get skills\u002F\u003Cnamespace>\u002F\u003Cname>`:\n\n```\nrig context get skills\u002Fcore\u002Frig-lifecycle\n```\n\nThe router itself is available through both forms it teaches:\n`rig context get openrig-skills` and `rig context get skills\u002Fcore\u002Fopenrig-skills`.\n\nThe content is served **from the installed CLI**, so what you load always matches your running version —\nno path-guessing, no frozen-fork drift. (The daemon assembles the same bundle `rig context preview`\nshows an operator — `get` is the agent-facing pull.)\n\n## The index\n\n> Membership rule (`layout.skills[*].edges.length > 0`): every public skill with at least one product edge in the generated edge layout appears exactly once in this index; no other skill appears.\n\n### Always loaded — the universal spine (open its body when its moment hits)\nThese are auto-delivered to every rig; their name+description are already in your context. Open the body when the \"when\" matches.\n\n- **forming-an-openrig-mental-model** — first boot, or you're unsure how the pieces fit. The runtime mental model.\n- **openrig-operating-model** — you do not know where context or work belongs, or you are about to duplicate knowledge. The two-tree placement and trace-to-root model.\n- **openrig-user** — you need a `rig` CLI command (send \u002F queue \u002F ps \u002F whoami \u002F scope \u002F broadcast). The daily CLI surface.\n- **applying-a-permission-policy** — a rig or seat has a permission policy attached, or you're setting one up: translate it into the live harness configuration.\n- **claude-compaction-restore** — you just compacted (Claude). Restore from durable evidence before resuming real work.\n- **delegating-work** — deciding who should do a task: you, a spawned subagent, or a durable peer seat that already holds the context.\n- **loading-addressable-markdown** — a task names Markdown as `path#h2-slug` or `path#h2-slug\u002Fh3-slug` outside the context-pack library.\n- **session-compaction-and-restore** — preparing for, or recovering from, compaction (any runtime). The write- and read-side protocol.\n- **queue-handoff** — you're passing durable work to another seat or ending your turn. The queue is the work ledger, not chat.\n- **refocusing** — a long-running seat may have lost the product outcome, crossed a major boundary, or compacted and needs a fresh path-based trace.\n- **seat-continuity-and-handover** — handing your seat's work across a restart or to another owner.\n- **orienting-to-an-inherited-seat** — you just inherited an existing seat through a planned handover and need to verify its identity, state, and testimony.\n- **retiring-and-inheriting-a-seat** — you're planning a seat transition and need to retire the current occupant into a fresh successor without losing continuity.\n- **mission-slice-sop** — you're working a mission\u002Fslice (the SDLC: intent → mini-requirements + proof contract → build → QA → proof). The operating manual.\n- **messaging-the-human** — composing a message to the human. Plain language, no insider jargon.\n- **agent-operated-workflows** — a bounded real-world procedure needs an agent to interpret state and operate exact tools, or you are deciding whether ordinary code should own the loop.\n- **agent-operated-software** — you are designing or operating an ongoing application whose live backend includes OpenRig agents.\n- **software-for-agents** — compatibility redirect for the former `agent-operated-software` name; remove in 0.6.0.\n- **openrig-skills** — this index (you're reading it). Always loaded; the entry point to everything below.\n\n### Load when your role or task calls for it (repo-shipped, profile-selected)\nThese ship in the OpenRig repo and reach a seat when its profile selects them. To use one, select it in your profile's `uses.skills`, or open it directly at `packages\u002Fdaemon\u002Fspecs\u002Fagents\u002Fshared\u002Fskills\u002Fcore\u002F\u003Cskill>\u002FSKILL.md`.\n\n- **openrig-software-factory** — a user wants continuing reviewed work: manual\u002Fteam, queue-only orchestration or an explicit Workflow; add one or two seats to the running starter when useful, with context, ownership, concurrency, spend and permission limits. Load `rig context get skills\u002Fcore\u002Fopenrig-software-factory\u002FSKILL.md`.\n- **openrig-architect** — authoring a rig or topology (NOT for changing OpenRig itself — that's `developing-openrig`).\n- **openrig-cmux** — driving the `cmux` terminal provider.\n- **openrig-herdr** — opening\u002Fmanaging seat terminals via the default proof-gated provider.\n- **agent-startup-and-context-ingestion** — a seat is booting and ingesting its startup context.\n- **topology-mutation-and-seat-management** — adding, removing, renaming seats or otherwise mutating rig topology.\n- **rig-lifecycle** — rig up \u002F down \u002F pause \u002F resume lifecycle operations.\n- **rig-bundles-and-shareable-artifacts** — packaging or installing a rig bundle \u002F shareable artifact.\n- **cross-host-rig-commands** — reaching seats or queues on another host (`--host`).\n- **openrig-upgrade** — upgrading OpenRig or the daemon.\n- **agent-starters** — composing an agent's starter context \u002F priming packs.\n- **specification-system** — authoring or reading AgentSpecs and rig specs.\n- **human-in-the-loop** — deciding when to involve the human vs. proceed on your own authority.\n- **watchdog** — monitoring or recovering a seat (health, restore, stuck state).\n- **session-source-fork** — forking a session's source\u002Fcontext.\n- **context-engineering** — designing context systems. Provisional and non-normative: current OpenRig skills, explicit rulings, and measured practice outrank it on any conflict.\n\nPod handbooks (load when you're in that pod):\n- **orchestration-team** — you're orchestrating a rig: dispatching, monitoring, keeping the loop moving.\n- **development-team** — you're on the dev pod: building and shipping product changes.\n- **review-team** — you're reviewing: fresh scrutiny, anti-slop, empirical verification.\n- **oversight-team** — you're in an oversight pod: monitor boundaries and route findings without taking over the work.\n\nProduct-management craft (load when shaping\u002Freviewing work):\n- **requirements-writer** — turning intent into clear requirements.\n- **plan-review** — reviewing a plan before it's built.\n- **exec-summary** — writing a decision-ready summary for a human.\n- **office-hours** — running a structured advisory \u002F decision session.\n- **context-builder** — assembling the context a task or seat needs.\n- **backlog-capture** — capturing and shaping backlog items.\n- **ui-mockup** — producing a UI mockup for a slice.\n\n### Vendored craft — load when you're coding (ships with upstream provenance)\nGeneral engineering skills OpenRig ships as vendored copies. Open when the task matches; they carry \"modified by OpenRig\" provenance.\n\n- **verification-before-completion** — about to claim done \u002F passing \u002F fixed: run the check and read the output first.\n- **systematic-debugging** — debugging: find the root cause before the fix.\n- **agent-browser** — driving a browser (screenshot \u002F screencast) from an agent.\n- **frontend-design** — designing frontend \u002F UI.\n- **dogfood** — web-QA \u002F dogfooding a shipped UI.\n\n## When OpenRig itself misbehaves\n\nRun `rig context get help`: the one help guide for your installed version, from symptom to next step, known problems,\nand a useful report to the OpenRig team if you are still stuck. If `rig` won't run, read\n`daemon\u002Fdocs\u002Freference\u002Fhelp.md` inside the installed `@openrig\u002Fcli` package, or https:\u002F\u002Fwww.openrig.dev\u002Fhelp\u002Fagents\n(the same text).\n\n## Developing OpenRig itself\n\nIf you're changing OpenRig's own source in a clone of the openrig repository, use that repository's\n`developing-openrig` skill (in the checkout's `.claude\u002Fskills\u002F` or `.agents\u002Fskills\u002F`). It maps the architecture, the\nareas where a small change has a large effect, and which tests to run before a pull request.\n\n## Need more than what ships here?\n\nThis index covers the **shipped** surface. Your project, rig or machine may add its own skills and routers. Check the\nskills your working directory loads before concluding that something doesn't exist.\n","# OpenRig skills — the index (start here)\n\nYou're running inside OpenRig. OpenRig ships a set of **skills** — small documents that tell you *when* to do something and *how*. This file is the map: what ships, when to reach for each, and how to load it. If you don't know which skill applies, or nothing is projected into your context, **start here.**\n\n## How OpenRig context works (30 seconds)\n\nSkills are **progressive disclosure**: a skill's *name + description* sit in your context ambiently (the \"hot tier\"); its *body* loads only when you open it. So you don't pre-read everything — you pattern-match a skill's \"when\" to your moment, then open just that one. This file is the index over the whole shipped set. (For bounded procedures, open `agent-operated-workflows`; for ongoing agent-backed applications, open `agent-operated-software`.)\n\nEvery row below names **how to reach the skill** — already-hot, or an exact load path. No row is a dead end.\n\n## Loading an entry on demand — `rig context get`\n\nDon't guess a file path or a name. Go **ask → ref → load** in three steps:\n\n1. **Discover** — run `rig context list` for every shipped entry's **ref** and name. The *when* for\n   each is the index below (or `rig context list --json`, which carries each entry's purpose) — match\n   your moment there.\n2. **Select** — match your moment to a row's *when* and take its **ref**. Refs are canonical full paths\n   that mirror the library layout — `skills\u002F\u003Cnamespace>\u002F\u003Cname>` (e.g. `skills\u002Fcore\u002Frig-lifecycle`,\n   `skills\u002Fprocess\u002Fsystematic-debugging`). A unique bare name (e.g. `watchdog`) also resolves; any\n   slash-bearing ref is an exact lookup and fails loud if it does not exist.\n3. **Load** — `rig context get skills\u002F\u003Cnamespace>\u002F\u003Cname>`:\n\n```\nrig context get skills\u002Fcore\u002Frig-lifecycle\n```\n\nThe router itself is available through both forms it teaches:\n`rig context get openrig-skills` and `rig context get skills\u002Fcore\u002Fopenrig-skills`.\n\nThe content is served **from the installed CLI**, so what you load always matches your running version —\nno path-guessing, no frozen-fork drift. (The daemon assembles the same bundle `rig context preview`\nshows an operator — `get` is the agent-facing pull.)\n\n## The index\n\n> Membership rule (`layout.skills[*].edges.length > 0`): every public skill with at least one product edge in the generated edge layout appears exactly once in this index; no other skill appears.\n\n### Always loaded — the universal spine (open its body when its moment hits)\nThese are auto-delivered to every rig; their name+description are already in your context. Open the body when the \"when\" matches.\n\n- **forming-an-openrig-mental-model** — first boot, or you're unsure how the pieces fit. The runtime mental model.\n- **openrig-operating-model** — you do not know where context or work belongs, or you are about to duplicate knowledge. The two-tree placement and trace-to-root model.\n- **openrig-user** — you need a `rig` CLI command (send \u002F queue \u002F ps \u002F whoami \u002F scope \u002F broadcast). The daily CLI surface.\n- **applying-a-permission-policy** — a rig or seat has a permission policy attached, or you're setting one up: translate it into the live harness configuration.\n- **claude-compaction-restore** — you just compacted (Claude). Restore from durable evidence before resuming real work.\n- **delegating-work** — deciding who should do a task: you, a spawned subagent, or a durable peer seat that already holds the context.\n- **loading-addressable-markdown** — a task names Markdown as `path#h2-slug` or `path#h2-slug\u002Fh3-slug` outside the context-pack library.\n- **session-compaction-and-restore** — preparing for, or recovering from, compaction (any runtime). The write- and read-side protocol.\n- **queue-handoff** — you're passing durable work to another seat or ending your turn. The queue is the work ledger, not chat.\n- **refocusing** — a long-running seat may have lost the product outcome, crossed a major boundary, or compacted and needs a fresh path-based trace.\n- **seat-continuity-and-handover** — handing your seat's work across a restart or to another owner.\n- **orienting-to-an-inherited-seat** — you just inherited an existing seat through a planned handover and need to verify its identity, state, and testimony.\n- **retiring-and-inheriting-a-seat** — you're planning a seat transition and need to retire the current occupant into a fresh successor without losing continuity.\n- **mission-slice-sop** — you're working a mission\u002Fslice (the SDLC: intent → mini-requirements + proof contract → build → QA → proof). The operating manual.\n- **messaging-the-human** — composing a message to the human. Plain language, no insider jargon.\n- **agent-operated-workflows** — a bounded real-world procedure needs an agent to interpret state and operate exact tools, or you are deciding whether ordinary code should own the loop.\n- **agent-operated-software** — you are designing or operating an ongoing application whose live backend includes OpenRig agents.\n- **software-for-agents** — compatibility redirect for the former `agent-operated-software` name; remove in 0.6.0.\n- **openrig-skills** — this index (you're reading it). Always loaded; the entry point to everything below.\n\n### Load when your role or task calls for it (repo-shipped, profile-selected)\nThese ship in the OpenRig repo and reach a seat when its profile selects them. To use one, select it in your profile's `uses.skills`, or open it directly at `packages\u002Fdaemon\u002Fspecs\u002Fagents\u002Fshared\u002Fskills\u002Fcore\u002F\u003Cskill>\u002FSKILL.md`.\n\n- **openrig-software-factory** — a user wants continuing reviewed work: manual\u002Fteam, queue-only orchestration or an explicit Workflow; add one or two seats to the running starter when useful, with context, ownership, concurrency, spend and permission limits. Load `rig context get skills\u002Fcore\u002Fopenrig-software-factory\u002FSKILL.md`.\n- **openrig-architect** — authoring a rig or topology (NOT for changing OpenRig itself — that's `developing-openrig`).\n- **openrig-cmux** — driving the `cmux` terminal provider.\n- **openrig-herdr** — opening\u002Fmanaging seat terminals via the default proof-gated provider.\n- **agent-startup-and-context-ingestion** — a seat is booting and ingesting its startup context.\n- **topology-mutation-and-seat-management** — adding, removing, renaming seats or otherwise mutating rig topology.\n- **rig-lifecycle** — rig up \u002F down \u002F pause \u002F resume lifecycle operations.\n- **rig-bundles-and-shareable-artifacts** — packaging or installing a rig bundle \u002F shareable artifact.\n- **cross-host-rig-commands** — reaching seats or queues on another host (`--host`).\n- **openrig-upgrade** — upgrading OpenRig or the daemon.\n- **agent-starters** — composing an agent's starter context \u002F priming packs.\n- **specification-system** — authoring or reading AgentSpecs and rig specs.\n- **human-in-the-loop** — deciding when to involve the human vs. proceed on your own authority.\n- **watchdog** — monitoring or recovering a seat (health, restore, stuck state).\n- **session-source-fork** — forking a session's source\u002Fcontext.\n- **context-engineering** — designing context systems. Provisional and non-normative: current OpenRig skills, explicit rulings, and measured practice outrank it on any conflict.\n\nPod handbooks (load when you're in that pod):\n- **orchestration-team** — you're orchestrating a rig: dispatching, monitoring, keeping the loop moving.\n- **development-team** — you're on the dev pod: building and shipping product changes.\n- **review-team** — you're reviewing: fresh scrutiny, anti-slop, empirical verification.\n- **oversight-team** — you're in an oversight pod: monitor boundaries and route findings without taking over the work.\n\nProduct-management craft (load when shaping\u002Freviewing work):\n- **requirements-writer** — turning intent into clear requirements.\n- **plan-review** — reviewing a plan before it's built.\n- **exec-summary** — writing a decision-ready summary for a human.\n- **office-hours** — running a structured advisory \u002F decision session.\n- **context-builder** — assembling the context a task or seat needs.\n- **backlog-capture** — capturing and shaping backlog items.\n- **ui-mockup** — producing a UI mockup for a slice.\n\n### Vendored craft — load when you're coding (ships with upstream provenance)\nGeneral engineering skills OpenRig ships as vendored copies. Open when the task matches; they carry \"modified by OpenRig\" provenance.\n\n- **verification-before-completion** — about to claim done \u002F passing \u002F fixed: run the check and read the output first.\n- **systematic-debugging** — debugging: find the root cause before the fix.\n- **agent-browser** — driving a browser (screenshot \u002F screencast) from an agent.\n- **frontend-design** — designing frontend \u002F UI.\n- **dogfood** — web-QA \u002F dogfooding a shipped UI.\n\n## When OpenRig itself misbehaves\n\nRun `rig context get help`: the one help guide for your installed version, from symptom to next step, known problems,\nand a useful report to the OpenRig team if you are still stuck. If `rig` won't run, read\n`daemon\u002Fdocs\u002Freference\u002Fhelp.md` inside the installed `@openrig\u002Fcli` package, or https:\u002F\u002Fwww.openrig.dev\u002Fhelp\u002Fagents\n(the same text).\n\n## Developing OpenRig itself\n\nIf you're changing OpenRig's own source in a clone of the openrig repository, use that repository's\n`developing-openrig` skill (in the checkout's `.claude\u002Fskills\u002F` or `.agents\u002Fskills\u002F`). It maps the architecture, the\nareas where a small change has a large effect, and which tests to run before a pull request.\n\n## Need more than what ships here?\n\nThis index covers the **shipped** surface. Your project, rig or machine may add its own skills and routers. Check the\nskills your working directory loads before concluding that something doesn't exist.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27},{"openrig":25},{"stage":26},"shipped","Bash(rig:*)","main","60438a272b68d091eddb01aad6e399af4996d536","agents\u002Fshared\u002Fskills\u002Fcore\u002Fopenrig-skills",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill openrig-skills",{"tool":43,"command":44},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill openrig-skills",{"tool":46,"command":47},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill openrig-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Fagents\u002Fshared\u002Fskills\u002Fcore\u002Fopenrig-skills\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[]]