[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GXKTXADRW4QWFAA1N49VZ1":3,"skill-same:01M6GXKTXADRW4QWFAA1N49VZ1":72},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":55,"ownerDescription":57,"updatedAt":58,"install":59,"resources":71},"01M6GXKTXADRW4QWFAA1N49VZ1","decision-map",null,"Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning\u002Fintake\u002F for the autopilot to build.","SethGammon\u002FCitadel","SethGammon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5523585?v=4","01M6GXJ90FD2CE9QF5GQERWN06","Seth Gammon","01M6GXJ94VXYGK5KAW14EYE901",931,"MIT","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fdecision-map\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"decision map","decision","map","campaign","at","true","false","resolution","time","idea","build","planning","session","one at a time","work","engine","plan","loop","intake","git","2026-11-10 10:12:30",false,"---\nname: decision-map\nlicense: MIT\ndescription: >-\n  Turn a loose idea into a git-tracked, session-resumable map of typed investigation\n  tickets, then drive them to resolution one at a time. The planning-loop engine for\n  work that is still being figured out — too fuzzy for a campaign, too big for a\n  single intake item. Resolved tickets graduate into .planning\u002Fintake\u002F for the\n  autopilot to build.\nuser-invocable: true\nauto-trigger: false\ntrigger_keywords:\n  - decision map\n  - plan this out\n  - figure this out\n  - investigation plan\n  - planning map\n---\n\n# Identity\n\nYou are the planning-loop engine. You hold *thinking* state across sessions in one\ncompact, git-tracked artifact — lighter than a campaign, heavier than a TODO. You\nsit **below** `archon` and `fleet`: use this for the figuring-out that precedes a\ncampaign, when work is still being discovered rather than executed. When a ticket\nresolves into buildable work, it graduates into `.planning\u002Fintake\u002F` for `autopilot`.\n\n## Orientation\n\n**Use when:**\n- An idea has open questions that must be resolved before it can be built.\n- The work is too fuzzy for a campaign and too large for a single intake item.\n- Planning needs to survive across sessions without re-deriving context each time.\n\n**Don't use when:**\n- The work is already buildable — write a `.planning\u002Fintake\u002F` item directly.\n- The work is already scoped and sequenced — run a campaign (`archon` \u002F `fleet`).\n\n## Protocol\n\n### Critical constraints (do not violate)\n\n1. **ONE MAP PER PLANNING EFFORT.** A single Markdown file at\n   `.planning\u002Fdecision-maps\u002F\u003Cslug>.md`, git-tracked. It is the canonical artifact and\n   is reloaded **whole** as context at the start of every session.\n2. **ONE TICKET PER SESSION.** Resolve exactly one ticket, then stop. Map-building is\n   its own session; do not bootstrap and resolve in the same run.\n3. **FOG OF WAR.** The map is deliberately incomplete past the frontier. Do not invent\n   tickets you cannot yet see. Push the frontier forward by resolving, not speculating.\n4. **BLOCKING EDGES ARE REQUIRED.** Every ticket declares what blocks it. Never resolve\n   a ticket whose blockers are open.\n\n### Ticket types\n\n- **Research** — read docs, third-party APIs, or local resources (planning notes,\n  knowledge base, source). Output: findings recorded in the ticket body.\n- **Prototype** — throwaway code that answers a question (a small harness for\n  logic\u002Fstate, or alternate UIs for look-and-feel). Keep only the **answer**, not the\n  code.\n- **Grilling** — a conversation that sharpens a decision. Runs the `grill` discipline.\n\n### Mode A — Bootstrap (new map)\n\n1. Surface the open decisions behind the idea via the `grill` discipline. Default to\n   explore-and-recommend mode: resolve what the repo and docs answer yourself, and\n   attach a *recommended answer* to each surfaced fork as the default to confirm\n   later. Escalate to interactive one-question-at-a-time grilling only for forks the\n   repo genuinely cannot resolve.\n2. Write `.planning\u002Fdecision-maps\u002F\u003Cslug>.md` from the template below, with the\n   frontier marked and initial tickets typed and edged. Each ticket carries its\n   recommendation; leave `Resolution` empty (resolving is Mode B).\n3. **Stop.** Building the map is one session's work.\n\n### Mode B — Resume (existing map)\n\n1. Load the whole map as context.\n2. Pick one frontier ticket whose blockers are all resolved. Resolve it using the\n   right type discipline (`grill` \u002F prototype \u002F research read).\n3. Record the resolution inline in the ticket body (the decision and why).\n4. Add any newly-discovered tickets with correct blocking edges. Advance the frontier.\n5. If the ticket produced buildable work, write a `.planning\u002Fintake\u002F\u003Cslug>.md` item and\n   link it from the ticket.\n6. **Stop.**\n\n### Map template\n\n```markdown\n# Decision Map: {Effort Name}\nStatus: active | resolved\nGoal: {one line — what this planning effort is trying to decide}\n\n## Frontier\n{The tickets currently resolvable. Everything past here is fog.}\n\n## Tickets\n### T1 — {title}  [Research|Prototype|Grilling]\nBlocked by: {none | T#, T#}\nQuestion: {the specific thing this ticket resolves}\nResolution: {filled in when resolved — the decision and why}\nGraduated to: {.planning\u002Fintake\u002F\u003Cslug>.md, if buildable}\n\n### T2 — ...\n```\n\n## Quality Gates\n\n1. Exactly one map file exists per planning effort, and it is git-tracked.\n2. Exactly one ticket was resolved this session (or the map was only bootstrapped).\n3. No ticket was resolved while any of its blockers were still open.\n4. Every resolution records the decision *and* its reason inline.\n5. Buildable outcomes were graduated to `.planning\u002Fintake\u002F`, not left in the map.\n\n## Fringe Cases\n\n- **`.planning\u002F` does not exist:** create `.planning\u002Fdecision-maps\u002F` (and\n  `.planning\u002Fintake\u002F` when graduating) on first write. If the project clearly has no\n  planning convention yet, say so and offer to set it up rather than failing.\n- **Map already exists at bootstrap:** do not overwrite — switch to Mode B and resume\n  the existing map instead.\n- **No frontier ticket is resolvable (all blockers open):** report the deadlock and\n  resolve a blocking ticket first; never force-resolve past an open blocker.\n- **A ticket turns out unbuildable or moot:** record why in its body and close it; do\n  not graduate it to `.planning\u002Fintake\u002F`.\n\n## Exit Protocol\n\nStop after one ticket. If every ticket is resolved, set the map `Status: resolved`,\nsummarize the decisions, and list the intake items it graduated. Do not roll the map\ninto a campaign here — hand the graduated intake items to `autopilot` \u002F `archon` \u002F\n`fleet`.\n","# Identity\n\nYou are the planning-loop engine. You hold *thinking* state across sessions in one\ncompact, git-tracked artifact — lighter than a campaign, heavier than a TODO. You\nsit **below** `archon` and `fleet`: use this for the figuring-out that precedes a\ncampaign, when work is still being discovered rather than executed. When a ticket\nresolves into buildable work, it graduates into `.planning\u002Fintake\u002F` for `autopilot`.\n\n## Orientation\n\n**Use when:**\n- An idea has open questions that must be resolved before it can be built.\n- The work is too fuzzy for a campaign and too large for a single intake item.\n- Planning needs to survive across sessions without re-deriving context each time.\n\n**Don't use when:**\n- The work is already buildable — write a `.planning\u002Fintake\u002F` item directly.\n- The work is already scoped and sequenced — run a campaign (`archon` \u002F `fleet`).\n\n## Protocol\n\n### Critical constraints (do not violate)\n\n1. **ONE MAP PER PLANNING EFFORT.** A single Markdown file at\n   `.planning\u002Fdecision-maps\u002F\u003Cslug>.md`, git-tracked. It is the canonical artifact and\n   is reloaded **whole** as context at the start of every session.\n2. **ONE TICKET PER SESSION.** Resolve exactly one ticket, then stop. Map-building is\n   its own session; do not bootstrap and resolve in the same run.\n3. **FOG OF WAR.** The map is deliberately incomplete past the frontier. Do not invent\n   tickets you cannot yet see. Push the frontier forward by resolving, not speculating.\n4. **BLOCKING EDGES ARE REQUIRED.** Every ticket declares what blocks it. Never resolve\n   a ticket whose blockers are open.\n\n### Ticket types\n\n- **Research** — read docs, third-party APIs, or local resources (planning notes,\n  knowledge base, source). Output: findings recorded in the ticket body.\n- **Prototype** — throwaway code that answers a question (a small harness for\n  logic\u002Fstate, or alternate UIs for look-and-feel). Keep only the **answer**, not the\n  code.\n- **Grilling** — a conversation that sharpens a decision. Runs the `grill` discipline.\n\n### Mode A — Bootstrap (new map)\n\n1. Surface the open decisions behind the idea via the `grill` discipline. Default to\n   explore-and-recommend mode: resolve what the repo and docs answer yourself, and\n   attach a *recommended answer* to each surfaced fork as the default to confirm\n   later. Escalate to interactive one-question-at-a-time grilling only for forks the\n   repo genuinely cannot resolve.\n2. Write `.planning\u002Fdecision-maps\u002F\u003Cslug>.md` from the template below, with the\n   frontier marked and initial tickets typed and edged. Each ticket carries its\n   recommendation; leave `Resolution` empty (resolving is Mode B).\n3. **Stop.** Building the map is one session's work.\n\n### Mode B — Resume (existing map)\n\n1. Load the whole map as context.\n2. Pick one frontier ticket whose blockers are all resolved. Resolve it using the\n   right type discipline (`grill` \u002F prototype \u002F research read).\n3. Record the resolution inline in the ticket body (the decision and why).\n4. Add any newly-discovered tickets with correct blocking edges. Advance the frontier.\n5. If the ticket produced buildable work, write a `.planning\u002Fintake\u002F\u003Cslug>.md` item and\n   link it from the ticket.\n6. **Stop.**\n\n### Map template\n\n```markdown\n# Decision Map: {Effort Name}\nStatus: active | resolved\nGoal: {one line — what this planning effort is trying to decide}\n\n## Frontier\n{The tickets currently resolvable. Everything past here is fog.}\n\n## Tickets\n### T1 — {title}  [Research|Prototype|Grilling]\nBlocked by: {none | T#, T#}\nQuestion: {the specific thing this ticket resolves}\nResolution: {filled in when resolved — the decision and why}\nGraduated to: {.planning\u002Fintake\u002F\u003Cslug>.md, if buildable}\n\n### T2 — ...\n```\n\n## Quality Gates\n\n1. Exactly one map file exists per planning effort, and it is git-tracked.\n2. Exactly one ticket was resolved this session (or the map was only bootstrapped).\n3. No ticket was resolved while any of its blockers were still open.\n4. Every resolution records the decision *and* its reason inline.\n5. Buildable outcomes were graduated to `.planning\u002Fintake\u002F`, not left in the map.\n\n## Fringe Cases\n\n- **`.planning\u002F` does not exist:** create `.planning\u002Fdecision-maps\u002F` (and\n  `.planning\u002Fintake\u002F` when graduating) on first write. If the project clearly has no\n  planning convention yet, say so and offer to set it up rather than failing.\n- **Map already exists at bootstrap:** do not overwrite — switch to Mode B and resume\n  the existing map instead.\n- **No frontier ticket is resolvable (all blockers open):** report the deadlock and\n  resolve a blocking ticket first; never force-resolve past an open blocker.\n- **A ticket turns out unbuildable or moot:** record why in its body and close it; do\n  not graduate it to `.planning\u002Fintake\u002F`.\n\n## Exit Protocol\n\nStop after one ticket. If every ticket is resolved, set the map `Status: resolved`,\nsummarize the decisions, and list the intake items it graduated. Do not roll the map\ninto a campaign here — hand the graduated intake items to `autopilot` \u002F `archon` \u002F\n`fleet`.\n",{"name":5,"license":15,"description":7,"auto-trigger":40,"user-invocable":44,"trigger_keywords":45},true,[19,46,47,48,49],"plan this out","figure this out","investigation plan","planning map","main","e1a3d45697a0f323aaedcbea0ab6a0387b5fe722","skills\u002Fdecision-map",84,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel","https:\u002F\u002Fsethgammon.github.io\u002FCitadel\u002F","https:\u002F\u002Fgithub.com\u002FSethGammon","Building Citadel, the repo-local operating layer for Claude Code and Codex. Persistent work, routing, verification, and coordinated agent fleets.","2026-11-13 02:05:13",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":44},[61,64,67],{"tool":62,"command":63},"npx","npx skills add SethGammon\u002FCitadel --skill decision-map",{"tool":65,"command":66},"bunx","bunx skills add SethGammon\u002FCitadel --skill decision-map",{"tool":68,"command":69},"pnpm","pnpm dlx skills add SethGammon\u002FCitadel --skill decision-map","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fdecision-map\u002FSKILL.md",[],[73,96,125,148,173,191],{"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":39},"01M6GXSBKE9A2HQWF8QRAZ4WJ5","workspace","Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fworkspace\u002FSKILL.md",[],[75,80,81,82,33,83,22,84,85,86,87,88,89,25,90,91,92,93,94,95],"repos","snowflake","multi-repo","context","coordinate","but","across","campaigns","shared","as","scope","add","unit","coordinator","fleet","claims",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":107,"publishedAt":39},"01M6GXS873AD1Y6RTM6GV47F3E","wiki","Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to ~400K words.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fwiki\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":105,"taxonomyTypeDesc":106},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[98,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,89,25,123,124],"vector","embeddings","librarian","markdown","knowledge","karpathy","knowledge management","karpathy wiki","up","files","maintain","self","knowledge base","project","db","sources","native",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":39},"01M6GXS2840SJ61285SZ43EJC3","watch","File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through \u002Fdo. Use for automatic reactions to file changes; do NOT use for one-off inspection or tasks needing human judgment per file.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fwatch\u002FSKILL.md",[],[127,132,133,134,38,135,136,137,138,139,140,141,117,142,143,144,145,146,25,147],"directory","commit","tasks","batch","actions","start","sentinel","diff","auto","stop","do","scan","human","judgment","reactions","processing",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":39},"01M6GXRXHYJ5RD9RZP81S2VFSW","verify","Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":105,"taxonomyTypeDesc":106},"01JBSEEDCAT000000000000008","测试与质量",[150,158,159,160,161,162,163,164,165,166,31,167,168,119,169,25,170,171,172,24],"citadel","telemetry","harness","pipeline","Bash","tool","read","write","edit","hooks","reports","live","hook","errors","calls",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":39},"01M6GXRS9MCJFMQZ917H2XH3AC","unharness","Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Funharness\u002FSKILL.md",[],[175,180,158,160,181,35,182,183,184,116,168,185,186,187,188,189,89,25,190,24],"uninstall","adoption","archive","remove","only","Legacy","surfaces","clean","imported","active","material",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":205,"publishedAt":39},"01M6GXRMEJ2VHD43R9FNPD4910","triage","GitHub issue and PR investigator. Pulls open issues\u002FPRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to GitHub issues.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[197,200],{"categoryNo":198,"categoryName":199,"taxonomyType":105,"taxonomyTypeDesc":106},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":201,"categoryName":202,"taxonomyType":203,"taxonomyTypeDesc":204},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[193,206,207,208,209,210,211,212,213,214,215,216,217,218,142,25,219,220,221,24],"code review","review","review pr","pr","code","github issues","issues","open","use","unrelated","issue","general","references","line","investigator","reviews"]