[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C1CPDFM5JZDZ6CMSTJRHS6":3,"skill-same:01M7C1CPDFM5JZDZ6CMSTJRHS6":50},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7C1CPDFM5JZDZ6CMSTJRHS6","sequence-plans",null,"Use when a project has more than one plan and you need to know which is runnable next — reads a committed manifest, runs a Kahn topological ready-set, and dispatches one plan at a time. Do NOT use for intra-plan step order (that is `write-plan` and `sdd`) or for greenfield spec work (that is `iterate`).","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.kimi-plugin\u002Fskills\u002Fsequence-plans\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sequence-plans\ndescription: Use when a project has more than one plan and you need to know which is runnable next — reads a committed manifest, runs a Kahn topological ready-set, and dispatches one plan at a time. Do NOT use for intra-plan step order (that is `write-plan` and `sdd`) or for greenfield spec work (that is `iterate`).\n---\n\n# Sequencing Plans\n\n## Overview\n\n`write-plan` produces one plan. `sdd` (SDD) executes\none plan and ledgers its own tasks. Neither models the space above one plan.\nThis skill does — with one committed file per project, one CLI, and one loop.\n\nUse it when brainstorming split a spec into more than one plan and each plan\ndepends on the previous one (or on a diamond of previous ones) landing. The\nfirst version of this problem is deterministic and cheap. Nothing here holds\nstate across sessions except the manifest, and the manifest is a git-tracked\nmarkdown file — a fresh session on another machine reads the same answer.\n\n**Announce at start:** \"I'm using the sequence-plans skill to run this plan\nset.\"\n\n## When NOT to use this\n\n- **One plan.** `write-plan` covers it. This skill exists for the\n  cross-plan case.\n- **Intra-plan step order.** SDD's per-task ledger already handles that inside\n  one plan.\n- **Greenfield spec work over a large surface.** `iterate` is\n  the right cluster for that; its state model is per-iteration, and this skill\n  will not help.\n- **Parallel plan dispatch.** Not covered here (`parallel-execution-option`\n  owns the write-ban lift). Run one plan at a time.\n\n## The manifest\n\nOne file per plan set, committed alongside the plans it names:\n`docs\u002Fmoe\u002Fplans\u002F\u003Cproject>-MANIFEST.md`. It is a markdown wrapper around one\nfenced YAML block. Fields:\n\n- `plan_set_id` — optional stable id unique across the manifests in this\n  repository. It must match `[A-Za-z0-9][A-Za-z0-9._-]*` so qualified\n  `\u003Cplan-set-id>\u002F\u003Cplan-id>` references round-trip without ambiguity. When\n  omitted for a legacy manifest, the CLI derives it from the filename by\n  removing `-MANIFEST.md` and validates the derived id with the same grammar.\n- `depends_on_plan_sets` — optional list of plan-set ids that must be wholly\n  `done` before any plan in this set is runnable. Defaults to `[]`. A blocked\n  prerequisite blocks every dependent set transitively.\n- `id` — short label unique in this manifest. Used by `plan-set done` and by\n  every `depends_on` reference. Recommend the plan slug.\n- `plan` — path to the plan markdown, from the repository root.\n- `depends_on` — list of ids that must be `done` before this plan is ready. `[]`\n  when nothing precedes it.\n- `status` — one of `pending`, `running`, `done`, `blocked`. New entries start\n  as `pending`. `blocked` is terminal and propagates: every dependent of a\n  `blocked` node is treated as blocked too, so a plan whose foundation stopped\n  by design is never handed back as \"ready\".\n- `commits` — set by `plan-set done`, not by hand. `\u003Cbase7>..\u003Chead7>` for the\n  range of commits the finished plan produced.\n\nA manifest must contain at least one plan. Empty plan sets are rejected rather\nthan treated as vacuously complete prerequisites.\n\nExample:\n\n````markdown\n# \u003CProject> Plan Set\n\nProse describing the project. `plan-set` reads only the yaml block below.\n\n```yaml\nplan_set_id: example-project\ndepends_on_plan_sets: []\nplans:\n  - id: schema\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-01-schema.md\n    depends_on: []\n    status: pending\n  - id: reader\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-02-reader.md\n    depends_on: [schema]\n    status: pending\n  - id: writer\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-03-writer.md\n    depends_on: [schema]\n    status: pending\n  - id: server\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-04-server.md\n    depends_on: [reader, writer]\n    status: pending\n```\n````\n\n## The CLI\n\nResolve [skills\u002Fsequence-plans\u002Fscripts\u002Fplan-set.mjs](scripts\u002Fplan-set.mjs) relative to this\nloaded document. It is a plugin-owned Node launcher, not a global executable:\ninvoke the resolved resource with `node`, never as a bare `plan-set` command.\nIt locates the plugin's scheduler independently of the project working\ndirectory and ships in the `moe` plugin alongside this skill.\n\nVerbs:\n\n- `plan-set next [--manifest \u003Cpath>]` — Print every id whose plan and plan-set\n  dependencies are all `done` and whose own status is `pending`. With multiple\n  discovered manifests, output is qualified as `\u003Cplan-set-id>\u002F\u003Cplan-id>`.\n  Scoped output remains the legacy bare id. Blocked nodes, sets, and their\n  transitive dependents never appear.\n- `plan-set done \u003Cid> \u003Cbase>..\u003Chead> [--manifest \u003Cpath>]` — Mark `\u003Cid>` as\n  `done` and record its commit range. In aggregate mode with multiple manifests,\n  `\u003Cid>` must be qualified as `\u003Cplan-set-id>\u002F\u003Cplan-id>`. Fails if the id is\n  unknown, if any plan or plan-set dependency is not `done`, or if the range is\n  not two 7+-char hex SHAs joined by `..`.\n- `plan-set check [--manifest \u003Cpath>]` — Validate: unique ids, all plan files\n  exist, all plan and plan-set dependencies resolve, neither DAG contains a\n  cycle (Kahn), plan-set ids are unique, and no plan path is listed twice even\n  across manifests. Exits non-zero on any failure. A cycle names its nodes on\n  stderr.\n\nIf `--manifest` is omitted, `plan-set` discovers every matching\n`docs\u002Fmoe\u002Fplans\u002F*-MANIFEST.md` in sorted filename order and operates on the\naggregate. If `--manifest` is present, it loads only that manifest and its\ntransitive prerequisite closure. Unrelated malformed siblings therefore do not\npoison a scoped command, while prerequisite completion is still enforced.\n\n## The SessionStart hook\n\n`plan-set-notice` is a bash SessionStart hook that fires on `startup|clear|compact`.\nIt looks in the session's cwd for `docs\u002Fmoe\u002Fplans\u002F*-MANIFEST.md`, and if one or\nmore exist and have runnable plans, it prints the bare or aggregate-qualified\nids and a `plan-set next` command as SessionStart `additionalContext`. Fully\ndeterministic — no model in the loop. Every failure path exits 0; a broken\nnotice must never break a session.\n\nThe hook exists so the cold-start case (\"new session, four plans exist, which\nare done?\") is caught even when the transcript has no history and no skill\ndescription is triggering. `plan-set-notice` announces; this skill carries the\nloop.\n\n## The loop\n\n1. **Confirm the manifest set.** Resolve\n   [skills\u002Fsequence-plans\u002Fscripts\u002Fplan-set.mjs](scripts\u002Fplan-set.mjs) relative to this\n   loaded document, then invoke it as\n   `node \"\u003Cresolved-plan-set.mjs>\" check`\n   before anything else. A cycle, a missing plan file, or a duplicate id is a\n   dead end before the first plan runs, and `check` says which one at once. Use\n   `--manifest docs\u002Fmoe\u002Fplans\u002F\u003Cproject>-MANIFEST.md` only when intentionally\n   scoping to that set and its prerequisites.\n\n2. **Pick the next plan.** Invoke the resolved launcher as\n   `node \"\u003Cresolved-plan-set.mjs>\" next`. `next`\n   returns a set; the loop takes the first line of it.\n\n   ```bash\n   NEXT=$(node \"\u003Cresolved-plan-set.mjs>\" next | head -n 1)\n   ```\n\n   If the output is empty, either everything is `done` (the project is\n   finished) or everything ready is `blocked` (a foundation stopped by design\n   and its dependents cannot run). Do not dispatch in either case.\n\n3. **Dispatch.** Read the plan path for `$NEXT` out of the manifest and hand\n   the plan off to `sdd` (the recommended executor) or\n   `execute-plan` (the no-subagents fallback). Both skills already own\n   their own per-task ledger, so this skill does not track task-level state.\n\n4. **Record completion.** When the plan finishes cleanly, capture the branch's\n   base and head SHAs and mark it done:\n\n   ```bash\n   node \"\u003Cresolved-plan-set.mjs>\" done \"$NEXT\" \\\n     \"$(git merge-base main HEAD | cut -c1-7)..$(git rev-parse --short HEAD)\"\n   ```\n\n   Add `--manifest` only for a scoped, bare-id workflow.\n\n   `done` refuses to run if `$NEXT`'s dependencies are not all `done` — a\n   safeguard against marking things done out of order.\n\n5. **Loop.** Return to step 2.\n\n## When to mark a plan `blocked`\n\n`blocked` is terminal and propagates. Use it when a plan has stopped by\ndesign — the spec changed, the approach is being reconsidered, an external\ndependency is not going to land. Do NOT use it as a synonym for \"in progress\"\nor \"waiting for review\": those are `running`.\n\nThe reason `blocked` matters is that its dependents are still `pending` in the\nfile. A naive \"artifact exists = done\" reader hands the agent a plan whose\nfoundation was never built. `plan-set next` never returns a dependent of a\n`blocked` node.\n\nEdit the manifest by hand to mark a plan `blocked`; there is no CLI verb for\nit, on purpose — it is a decision, not a state transition.\n\n## Design notes\n\n- **`next` returns a ready set, not a single id.** The loop takes the first of\n  it. The set is the seam a later cross-plan scheduler would read, once the parallel-write\n  ban is lifted. Nothing here requires that ban lifted.\n- **The CLI lives under `hooks\u002F`, not this skill's directory.** SessionStart\n  invokes the adjacent notice before any skill body is loaded. Keeping both\n  runtime pieces together also gives every generated harness the same stable\n  plugin-relative path.\n- **`plan-set` is Node, not bash.** Kahn's algorithm plus per-line YAML\n  parsing over a mutable file is short in JS and painful in bash. Node ships\n  with every harness this fork targets.\n- **The manifest is a markdown wrapper around one YAML block, not a bare YAML\n  file.** The wrapper is where humans write the prose that says what the\n  project is for. `plan-set` reads the yaml block and ignores everything\n  outside it.\n","# Sequencing Plans\n\n## Overview\n\n`write-plan` produces one plan. `sdd` (SDD) executes\none plan and ledgers its own tasks. Neither models the space above one plan.\nThis skill does — with one committed file per project, one CLI, and one loop.\n\nUse it when brainstorming split a spec into more than one plan and each plan\ndepends on the previous one (or on a diamond of previous ones) landing. The\nfirst version of this problem is deterministic and cheap. Nothing here holds\nstate across sessions except the manifest, and the manifest is a git-tracked\nmarkdown file — a fresh session on another machine reads the same answer.\n\n**Announce at start:** \"I'm using the sequence-plans skill to run this plan\nset.\"\n\n## When NOT to use this\n\n- **One plan.** `write-plan` covers it. This skill exists for the\n  cross-plan case.\n- **Intra-plan step order.** SDD's per-task ledger already handles that inside\n  one plan.\n- **Greenfield spec work over a large surface.** `iterate` is\n  the right cluster for that; its state model is per-iteration, and this skill\n  will not help.\n- **Parallel plan dispatch.** Not covered here (`parallel-execution-option`\n  owns the write-ban lift). Run one plan at a time.\n\n## The manifest\n\nOne file per plan set, committed alongside the plans it names:\n`docs\u002Fmoe\u002Fplans\u002F\u003Cproject>-MANIFEST.md`. It is a markdown wrapper around one\nfenced YAML block. Fields:\n\n- `plan_set_id` — optional stable id unique across the manifests in this\n  repository. It must match `[A-Za-z0-9][A-Za-z0-9._-]*` so qualified\n  `\u003Cplan-set-id>\u002F\u003Cplan-id>` references round-trip without ambiguity. When\n  omitted for a legacy manifest, the CLI derives it from the filename by\n  removing `-MANIFEST.md` and validates the derived id with the same grammar.\n- `depends_on_plan_sets` — optional list of plan-set ids that must be wholly\n  `done` before any plan in this set is runnable. Defaults to `[]`. A blocked\n  prerequisite blocks every dependent set transitively.\n- `id` — short label unique in this manifest. Used by `plan-set done` and by\n  every `depends_on` reference. Recommend the plan slug.\n- `plan` — path to the plan markdown, from the repository root.\n- `depends_on` — list of ids that must be `done` before this plan is ready. `[]`\n  when nothing precedes it.\n- `status` — one of `pending`, `running`, `done`, `blocked`. New entries start\n  as `pending`. `blocked` is terminal and propagates: every dependent of a\n  `blocked` node is treated as blocked too, so a plan whose foundation stopped\n  by design is never handed back as \"ready\".\n- `commits` — set by `plan-set done`, not by hand. `\u003Cbase7>..\u003Chead7>` for the\n  range of commits the finished plan produced.\n\nA manifest must contain at least one plan. Empty plan sets are rejected rather\nthan treated as vacuously complete prerequisites.\n\nExample:\n\n````markdown\n# \u003CProject> Plan Set\n\nProse describing the project. `plan-set` reads only the yaml block below.\n\n```yaml\nplan_set_id: example-project\ndepends_on_plan_sets: []\nplans:\n  - id: schema\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-01-schema.md\n    depends_on: []\n    status: pending\n  - id: reader\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-02-reader.md\n    depends_on: [schema]\n    status: pending\n  - id: writer\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-03-writer.md\n    depends_on: [schema]\n    status: pending\n  - id: server\n    plan: docs\u002Fmoe\u002Fplans\u002F2026-01-04-server.md\n    depends_on: [reader, writer]\n    status: pending\n```\n````\n\n## The CLI\n\nResolve [skills\u002Fsequence-plans\u002Fscripts\u002Fplan-set.mjs](scripts\u002Fplan-set.mjs) relative to this\nloaded document. It is a plugin-owned Node launcher, not a global executable:\ninvoke the resolved resource with `node`, never as a bare `plan-set` command.\nIt locates the plugin's scheduler independently of the project working\ndirectory and ships in the `moe` plugin alongside this skill.\n\nVerbs:\n\n- `plan-set next [--manifest \u003Cpath>]` — Print every id whose plan and plan-set\n  dependencies are all `done` and whose own status is `pending`. With multiple\n  discovered manifests, output is qualified as `\u003Cplan-set-id>\u002F\u003Cplan-id>`.\n  Scoped output remains the legacy bare id. Blocked nodes, sets, and their\n  transitive dependents never appear.\n- `plan-set done \u003Cid> \u003Cbase>..\u003Chead> [--manifest \u003Cpath>]` — Mark `\u003Cid>` as\n  `done` and record its commit range. In aggregate mode with multiple manifests,\n  `\u003Cid>` must be qualified as `\u003Cplan-set-id>\u002F\u003Cplan-id>`. Fails if the id is\n  unknown, if any plan or plan-set dependency is not `done`, or if the range is\n  not two 7+-char hex SHAs joined by `..`.\n- `plan-set check [--manifest \u003Cpath>]` — Validate: unique ids, all plan files\n  exist, all plan and plan-set dependencies resolve, neither DAG contains a\n  cycle (Kahn), plan-set ids are unique, and no plan path is listed twice even\n  across manifests. Exits non-zero on any failure. A cycle names its nodes on\n  stderr.\n\nIf `--manifest` is omitted, `plan-set` discovers every matching\n`docs\u002Fmoe\u002Fplans\u002F*-MANIFEST.md` in sorted filename order and operates on the\naggregate. If `--manifest` is present, it loads only that manifest and its\ntransitive prerequisite closure. Unrelated malformed siblings therefore do not\npoison a scoped command, while prerequisite completion is still enforced.\n\n## The SessionStart hook\n\n`plan-set-notice` is a bash SessionStart hook that fires on `startup|clear|compact`.\nIt looks in the session's cwd for `docs\u002Fmoe\u002Fplans\u002F*-MANIFEST.md`, and if one or\nmore exist and have runnable plans, it prints the bare or aggregate-qualified\nids and a `plan-set next` command as SessionStart `additionalContext`. Fully\ndeterministic — no model in the loop. Every failure path exits 0; a broken\nnotice must never break a session.\n\nThe hook exists so the cold-start case (\"new session, four plans exist, which\nare done?\") is caught even when the transcript has no history and no skill\ndescription is triggering. `plan-set-notice` announces; this skill carries the\nloop.\n\n## The loop\n\n1. **Confirm the manifest set.** Resolve\n   [skills\u002Fsequence-plans\u002Fscripts\u002Fplan-set.mjs](scripts\u002Fplan-set.mjs) relative to this\n   loaded document, then invoke it as\n   `node \"\u003Cresolved-plan-set.mjs>\" check`\n   before anything else. A cycle, a missing plan file, or a duplicate id is a\n   dead end before the first plan runs, and `check` says which one at once. Use\n   `--manifest docs\u002Fmoe\u002Fplans\u002F\u003Cproject>-MANIFEST.md` only when intentionally\n   scoping to that set and its prerequisites.\n\n2. **Pick the next plan.** Invoke the resolved launcher as\n   `node \"\u003Cresolved-plan-set.mjs>\" next`. `next`\n   returns a set; the loop takes the first line of it.\n\n   ```bash\n   NEXT=$(node \"\u003Cresolved-plan-set.mjs>\" next | head -n 1)\n   ```\n\n   If the output is empty, either everything is `done` (the project is\n   finished) or everything ready is `blocked` (a foundation stopped by design\n   and its dependents cannot run). Do not dispatch in either case.\n\n3. **Dispatch.** Read the plan path for `$NEXT` out of the manifest and hand\n   the plan off to `sdd` (the recommended executor) or\n   `execute-plan` (the no-subagents fallback). Both skills already own\n   their own per-task ledger, so this skill does not track task-level state.\n\n4. **Record completion.** When the plan finishes cleanly, capture the branch's\n   base and head SHAs and mark it done:\n\n   ```bash\n   node \"\u003Cresolved-plan-set.mjs>\" done \"$NEXT\" \\\n     \"$(git merge-base main HEAD | cut -c1-7)..$(git rev-parse --short HEAD)\"\n   ```\n\n   Add `--manifest` only for a scoped, bare-id workflow.\n\n   `done` refuses to run if `$NEXT`'s dependencies are not all `done` — a\n   safeguard against marking things done out of order.\n\n5. **Loop.** Return to step 2.\n\n## When to mark a plan `blocked`\n\n`blocked` is terminal and propagates. Use it when a plan has stopped by\ndesign — the spec changed, the approach is being reconsidered, an external\ndependency is not going to land. Do NOT use it as a synonym for \"in progress\"\nor \"waiting for review\": those are `running`.\n\nThe reason `blocked` matters is that its dependents are still `pending` in the\nfile. A naive \"artifact exists = done\" reader hands the agent a plan whose\nfoundation was never built. `plan-set next` never returns a dependent of a\n`blocked` node.\n\nEdit the manifest by hand to mark a plan `blocked`; there is no CLI verb for\nit, on purpose — it is a decision, not a state transition.\n\n## Design notes\n\n- **`next` returns a ready set, not a single id.** The loop takes the first of\n  it. The set is the seam a later cross-plan scheduler would read, once the parallel-write\n  ban is lifted. Nothing here requires that ban lifted.\n- **The CLI lives under `hooks\u002F`, not this skill's directory.** SessionStart\n  invokes the adjacent notice before any skill body is loaded. Keeping both\n  runtime pieces together also gives every generated harness the same stable\n  plugin-relative path.\n- **`plan-set` is Node, not bash.** Kahn's algorithm plus per-line YAML\n  parsing over a mutable file is short in JS and painful in bash. Node ships\n  with every harness this fork targets.\n- **The manifest is a markdown wrapper around one YAML block, not a bare YAML\n  file.** The wrapper is where humans write the prose that says what the\n  project is for. `plan-set` reads the yaml block and ignores everything\n  outside it.\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe\u002F.kimi-plugin\u002Fskills\u002Fsequence-plans",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill sequence-plans",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill sequence-plans",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill sequence-plans","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.kimi-plugin\u002Fskills\u002Fsequence-plans\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fplan-set.mjs","SCRIPT","脚本",741,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002F.kimi-plugin\u002Fskills\u002Fsequence-plans\u002Fscripts\u002Fplan-set.mjs",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]