[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DH3Z74RHX1TNWCVBQ09Y2C":3,"skill-same:01M7DH3Z74RHX1TNWCVBQ09Y2C":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7DH3Z74RHX1TNWCVBQ09Y2C","run-spec-dependency-graph",null,"Parse a spec's tasks.md into its task graph — numbers, agents, budgets, Files, dependencies, completion state — validate it, and report progress, the ready set and deadlock; the mechanism is scripts\u002Fharness\u002Frunspec.py","turbokast\u002Fmythhelm","turbokast","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F335585049?v=4","01M7DGYYSHNA1BW1Y9GJFN6DVC","TurboKast","01M7DGYYT6GTPCFADDKS5ZXM1Y",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frun-spec-dependency-graph\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run-spec-dependency-graph\ndescription: Parse a spec's tasks.md into its task graph — numbers, agents, budgets, Files, dependencies, completion state — validate it, and report progress, the ready set and deadlock; the mechanism is scripts\u002Fharness\u002Frunspec.py\nargument-hint: \"\u003Cspec-name>\"\n---\n\n# Run Spec — Dependency Graph\n\nHow `\u002Frun-spec` reads the task graph. The parser is `scripts\u002Fharness\u002Frunspec.py`; this page says what it extracts and what each field means for scheduling.\n\n## Input\n\n`$ARGUMENTS`: the spec name. `\u002Frun-spec` also reads this page inline.\n\n## Invocation contexts\n\n- **Slash command**: parses the spec's `tasks.md` and prints the graph and progress.\n- **Model-invoked**: the same.\n- **Non-interactive**: the same. Read-only; a parse failure is returned, never guessed around.\n\n## What the parser extracts\n\n`python3 scripts\u002Fharness\u002Frunspec.py tasks specs\u002F\u003Cstate>\u002F\u003Cspec>\u002Ftasks.md` prints one object per `### Task N — \u003Cname>` block outside code fences:\n\n| Field | Source | Scheduling meaning |\n|---|---|---|\n| `number`, `name` | the heading | the task's identity in branches, titles and events |\n| `agent` | first word of `Domain\u002Fagent` | the dispatch's `subagent_type`; `maintainer` is the operator's |\n| `budget` | first word of `Budget` | `standard` or `complex`; sets the dispatch's budget line |\n| `depends` | `Depends on` (task numbers outside parenthesised notes; `None` is empty) | edges; a task with no `Depends on` depends on the task listed before it, the first task on none |\n| `files` | backticked paths in `Files`, outside parenthesised notes | the overlap check for parallel dispatch; globs and directories count |\n| `heading_complete`, `status_complete`, `complete` | ` ✅ COMPLETED` in the heading; a Status starting with `✅` | complete when either holds |\n| `blocked` | a `Blocked` field | never dispatched; reported |\n| `pr` | `PR #\u003Cn>` in Status | the task's merged pull request |\n\n## Validation\n\n`scripts\u002Fci\u002Flint-agent-harness.sh --only specs` is the gate: required fields present, `Depends on` naming existing tasks, no cycle. `runspec.py status` repeats the cycle check (`\"cycle\": true`) and lists tasks whose dependencies it cannot read under `unresolvable`; either stops the run as a spec defect.\n\n## Progress and the ready set\n\n`python3 scripts\u002Fharness\u002Frunspec.py status \u003Ctasks.md> [--in-flight N,M]` prints:\n\n- `complete`, `incomplete`, `in_flight` (the tasks you passed that are still incomplete);\n- `ready`: incomplete, not blocked, not in flight, every dependency complete;\n- `waiting`, `blocked`, `unresolvable`;\n- `deadlock`: tasks remain, none is ready and none is in flight;\n- `marker_mismatch`: tasks complete by only one of heading and Status, for the completion clerk.\n\nScheduling reads `tasks.md` **on origin\u002Fmain** for completion (`runspec.py deps-merged`): a dependency is satisfied when its merged pull request put the ✅ there, because every worker starts from origin\u002Fmain. `python3 scripts\u002Fharness\u002Frunspec.py closure \u003Ctasks.md> \u003CN>` gives a task's transitive dependencies, whose hand-off sections go into its dispatch.\n\n## Worked example\n\n```text\nTask 1  (no Depends on: first task)        → depends []\nTask 2  Depends on: Task 1                 → depends [1]\nTask 3  Depends on: Task 1                 → depends [1]\nTask 4  (no Depends on)                    → depends [3]   the task before it\nTask 5  Depends on: Task 2, Task 4 (after both land) → depends [2, 4]\n```\n\nNothing complete: ready `[1]`. After Task 1 merges: ready `[2, 3]`, a parallel batch when their Files are disjoint. After 2 and 3: ready `[4]`. After 4: ready `[5]`. If Task 3 were `Blocked`, then 4 and 5 could never start: after Task 2, nothing is ready or in flight, so `deadlock` is true and the run stops naming Task 3.\n\n## Output\n\nThe `status` JSON, or the parser's error.\n","# Run Spec — Dependency Graph\n\nHow `\u002Frun-spec` reads the task graph. The parser is `scripts\u002Fharness\u002Frunspec.py`; this page says what it extracts and what each field means for scheduling.\n\n## Input\n\n`$ARGUMENTS`: the spec name. `\u002Frun-spec` also reads this page inline.\n\n## Invocation contexts\n\n- **Slash command**: parses the spec's `tasks.md` and prints the graph and progress.\n- **Model-invoked**: the same.\n- **Non-interactive**: the same. Read-only; a parse failure is returned, never guessed around.\n\n## What the parser extracts\n\n`python3 scripts\u002Fharness\u002Frunspec.py tasks specs\u002F\u003Cstate>\u002F\u003Cspec>\u002Ftasks.md` prints one object per `### Task N — \u003Cname>` block outside code fences:\n\n| Field | Source | Scheduling meaning |\n|---|---|---|\n| `number`, `name` | the heading | the task's identity in branches, titles and events |\n| `agent` | first word of `Domain\u002Fagent` | the dispatch's `subagent_type`; `maintainer` is the operator's |\n| `budget` | first word of `Budget` | `standard` or `complex`; sets the dispatch's budget line |\n| `depends` | `Depends on` (task numbers outside parenthesised notes; `None` is empty) | edges; a task with no `Depends on` depends on the task listed before it, the first task on none |\n| `files` | backticked paths in `Files`, outside parenthesised notes | the overlap check for parallel dispatch; globs and directories count |\n| `heading_complete`, `status_complete`, `complete` | ` ✅ COMPLETED` in the heading; a Status starting with `✅` | complete when either holds |\n| `blocked` | a `Blocked` field | never dispatched; reported |\n| `pr` | `PR #\u003Cn>` in Status | the task's merged pull request |\n\n## Validation\n\n`scripts\u002Fci\u002Flint-agent-harness.sh --only specs` is the gate: required fields present, `Depends on` naming existing tasks, no cycle. `runspec.py status` repeats the cycle check (`\"cycle\": true`) and lists tasks whose dependencies it cannot read under `unresolvable`; either stops the run as a spec defect.\n\n## Progress and the ready set\n\n`python3 scripts\u002Fharness\u002Frunspec.py status \u003Ctasks.md> [--in-flight N,M]` prints:\n\n- `complete`, `incomplete`, `in_flight` (the tasks you passed that are still incomplete);\n- `ready`: incomplete, not blocked, not in flight, every dependency complete;\n- `waiting`, `blocked`, `unresolvable`;\n- `deadlock`: tasks remain, none is ready and none is in flight;\n- `marker_mismatch`: tasks complete by only one of heading and Status, for the completion clerk.\n\nScheduling reads `tasks.md` **on origin\u002Fmain** for completion (`runspec.py deps-merged`): a dependency is satisfied when its merged pull request put the ✅ there, because every worker starts from origin\u002Fmain. `python3 scripts\u002Fharness\u002Frunspec.py closure \u003Ctasks.md> \u003CN>` gives a task's transitive dependencies, whose hand-off sections go into its dispatch.\n\n## Worked example\n\n```text\nTask 1  (no Depends on: first task)        → depends []\nTask 2  Depends on: Task 1                 → depends [1]\nTask 3  Depends on: Task 1                 → depends [1]\nTask 4  (no Depends on)                    → depends [3]   the task before it\nTask 5  Depends on: Task 2, Task 4 (after both land) → depends [2, 4]\n```\n\nNothing complete: ready `[1]`. After Task 1 merges: ready `[2, 3]`, a parallel batch when their Files are disjoint. After 2 and 3: ready `[4]`. After 4: ready `[5]`. If Task 3 were `Blocked`, then 4 and 5 could never start: after Task 2, nothing is ready or in flight, so `deadlock` is true and the run stops naming Task 3.\n\n## Output\n\nThe `status` JSON, or the parser's error.\n",{"name":5,"description":7,"argument-hint":24},"\u003Cspec-name>","main","6e250ec86158119da148ddc017b960ed3b2bee2b",".claude\u002Fskills\u002Frun-spec-dependency-graph",1,"https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm","https:\u002F\u002Fgithub.com\u002Fturbokast","https:\u002F\u002Fturbokast.com","2026-11-10 17:37:03",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add turbokast\u002Fmythhelm --skill run-spec-dependency-graph",{"tool":39,"command":40},"bunx","bunx skills add turbokast\u002Fmythhelm --skill run-spec-dependency-graph",{"tool":42,"command":43},"pnpm","pnpm dlx skills add turbokast\u002Fmythhelm --skill run-spec-dependency-graph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frun-spec-dependency-graph\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DH77QH78C95S7A5V1GFKKF","mythhelm-deliver-backlog","Coordinate a MYTHHELM backlog run with the shared stage checks and maintainer checkpoints.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-deliver-backlog\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DH748EXYG9RVBWPBJ73M27","mythhelm-bootstrap","Orient a Grok Build session in the MYTHHELM repository before task or spec work.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-bootstrap\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DH70XJE0DZA4T5DYR1TWKZ","vendor-consult","Run one advisory stage consult (premise-ground, spec-validate, task-review, change-review, stuck-oracle, dossier) with an optional external vendor, then adjudicate the answer at its anchors","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvendor-consult\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DH6X9HSQ308P5FNDSKYR5R","update-docs","Bring README, docs\u002F, knowledge\u002F, WORKFLOW.md and CLAUDE.md in line with what a shipped spec or a merged change actually did — find every statement the change made stale, fix it where readers look, and add only the new facts they need","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DH6T82XR40XQFNRTN4AHGN","triage","Score an idea or a GitHub issue against the master spec's stages, gates and commitments, check it for duplicates, and recommend whether it becomes a backlog card; read-only","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DH6Q17PM4ESX978QYFV6H6","test-driven-development","Red-green-refactor for Go — use when implementing any feature, bug fix or behaviour change, before writing implementation code","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]