[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DH5N1WJC0HKCWHC7Z102P3":3,"skill-same:01M7DH5N1WJC0HKCWHC7Z102P3":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},"01M7DH5N1WJC0HKCWHC7Z102P3","spec-investigate",null,"Ground a planned spec in the codebase before any scoping or writing — the master-spec sections, the invariants, the domains, the existing packages and data flows, and conflicting specs","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\u002Fspec-investigate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-investigate\ndescription: Ground a planned spec in the codebase before any scoping or writing — the master-spec sections, the invariants, the domains, the existing packages and data flows, and conflicting specs\nargument-hint: \"\u003Cspec-name | \\\"feature description\\\">\"\n---\n\n# Spec Investigate\n\nPhase 1 of `\u002Fspec`, and the phase that decides the spec's quality. It reads; it writes nothing. Its findings feed scoping and creation, and are deliberately **not** passed to the validator, whose value is a reading uninfluenced by this one.\n\n## Input\n\n`$ARGUMENTS`: a description, or the name of a spec in `refined\u002F` whose `requirements.md` is then the ground truth.\n\n## Invocation contexts\n\n- **Slash command**: investigates and prints the findings.\n- **Model-invoked**: the same, normally from `\u002Fspec`.\n- **Non-interactive**: the same. Read-only, so there is nothing to confirm; a question only a person can answer is recorded as an open question, not asked.\n\n## Steps\n\n1. **Read the normative context.**\n   - The master-spec sections the change implements or touches (resolve the named revision through `docs\u002Fspec\u002FREADME.md`; use its table of contents, read the sections, not the whole file). Note every MUST, invariant and gate that applies.\n   - `knowledge\u002Finvariants.md`: the invariants the change can reach, and how a task cites them.\n   - `knowledge\u002Fdomains.md`: the domains and agents the paths will involve.\n   - Decision records under `docs\u002Fdecisions\u002F` in the same area, so the spec does not re-argue a settled choice.\n   - `.claude\u002Fskills\u002Fspec-decomposition\u002FSKILL.md`, for what the tasks will need to know.\n2. **Read the code**, not file names.\n   - The packages involved: `go doc .\u002Finternal\u002F\u003Cpkg>` for the exported surface, then the functions themselves. Record exact signatures, return shapes and failure cases for everything the design will call or change.\n   - Trace each affected flow end to end: CLI command → admission or supervisor → workspace, journal or adapter → back to output and exit code.\n   - Find the existing patterns the change must follow or replace (search for similar features), and the tests that cover the area today.\n   - For every count or absence the spec will state (\"the two callers\", \"no code writes X\"), run the search and record the command and its hits (`.claude\u002Frules\u002Fspec-premise-grounding.md`).\n   - Optional dossier (advisory): when the impacted directories hold more than about 30 files, run `\u002Fvendor-consult muse dossier` over them. Treat every claim in the answer as a pointer: open it at its `file:line` and confirm it before it enters the findings. An `unavailable` result is recorded and skipped.\n3. **Find the seams.** Which parts could ship independently? What is the smallest first step that is useful alone? Which contract (a type, an interface, a schema) must land before its consumers?\n4. **Research the unknowns.** For an external tool or native harness behaviour, read its current documentation and record the version and the source; what cannot be settled becomes an open question with a conservative default.\n5. **Scan for conflicts** in every lifecycle state: `specs\u002Fin-progress\u002F` (highest risk), `specs\u002Funfinalized\u002F`, `specs\u002Ftodo\u002F`, `specs\u002Frefined\u002F`, `specs\u002Funrefined\u002F`; and `specs\u002Fdone\u002F` for decisions to reuse. Note any spec that edits the same files or packages.\n\n## Output\n\nFindings for the next phases, kept in the session:\n\n```text\nMaster spec: \u003C§ sections>; invariants in reach: \u003CI-IDs>; gates: \u003CG-IDs>\nPackages and facts: \u003Cpath:line — fact>, one per line, each opened\nFlows traced: \u003Cflow — path:line chain>\nSeams: \u003Cindependent parts and the contracts between them>\nConflicts: \u003Cspec — overlapping files> | none\nOpen questions: \u003Cquestion — conservative default — who decides>\n```\n","# Spec Investigate\n\nPhase 1 of `\u002Fspec`, and the phase that decides the spec's quality. It reads; it writes nothing. Its findings feed scoping and creation, and are deliberately **not** passed to the validator, whose value is a reading uninfluenced by this one.\n\n## Input\n\n`$ARGUMENTS`: a description, or the name of a spec in `refined\u002F` whose `requirements.md` is then the ground truth.\n\n## Invocation contexts\n\n- **Slash command**: investigates and prints the findings.\n- **Model-invoked**: the same, normally from `\u002Fspec`.\n- **Non-interactive**: the same. Read-only, so there is nothing to confirm; a question only a person can answer is recorded as an open question, not asked.\n\n## Steps\n\n1. **Read the normative context.**\n   - The master-spec sections the change implements or touches (resolve the named revision through `docs\u002Fspec\u002FREADME.md`; use its table of contents, read the sections, not the whole file). Note every MUST, invariant and gate that applies.\n   - `knowledge\u002Finvariants.md`: the invariants the change can reach, and how a task cites them.\n   - `knowledge\u002Fdomains.md`: the domains and agents the paths will involve.\n   - Decision records under `docs\u002Fdecisions\u002F` in the same area, so the spec does not re-argue a settled choice.\n   - `.claude\u002Fskills\u002Fspec-decomposition\u002FSKILL.md`, for what the tasks will need to know.\n2. **Read the code**, not file names.\n   - The packages involved: `go doc .\u002Finternal\u002F\u003Cpkg>` for the exported surface, then the functions themselves. Record exact signatures, return shapes and failure cases for everything the design will call or change.\n   - Trace each affected flow end to end: CLI command → admission or supervisor → workspace, journal or adapter → back to output and exit code.\n   - Find the existing patterns the change must follow or replace (search for similar features), and the tests that cover the area today.\n   - For every count or absence the spec will state (\"the two callers\", \"no code writes X\"), run the search and record the command and its hits (`.claude\u002Frules\u002Fspec-premise-grounding.md`).\n   - Optional dossier (advisory): when the impacted directories hold more than about 30 files, run `\u002Fvendor-consult muse dossier` over them. Treat every claim in the answer as a pointer: open it at its `file:line` and confirm it before it enters the findings. An `unavailable` result is recorded and skipped.\n3. **Find the seams.** Which parts could ship independently? What is the smallest first step that is useful alone? Which contract (a type, an interface, a schema) must land before its consumers?\n4. **Research the unknowns.** For an external tool or native harness behaviour, read its current documentation and record the version and the source; what cannot be settled becomes an open question with a conservative default.\n5. **Scan for conflicts** in every lifecycle state: `specs\u002Fin-progress\u002F` (highest risk), `specs\u002Funfinalized\u002F`, `specs\u002Ftodo\u002F`, `specs\u002Frefined\u002F`, `specs\u002Funrefined\u002F`; and `specs\u002Fdone\u002F` for decisions to reuse. Note any spec that edits the same files or packages.\n\n## Output\n\nFindings for the next phases, kept in the session:\n\n```text\nMaster spec: \u003C§ sections>; invariants in reach: \u003CI-IDs>; gates: \u003CG-IDs>\nPackages and facts: \u003Cpath:line — fact>, one per line, each opened\nFlows traced: \u003Cflow — path:line chain>\nSeams: \u003Cindependent parts and the contracts between them>\nConflicts: \u003Cspec — overlapping files> | none\nOpen questions: \u003Cquestion — conservative default — who decides>\n```\n",{"name":5,"description":7,"argument-hint":24},"\u003Cspec-name | \"feature description\">","main","6e250ec86158119da148ddc017b960ed3b2bee2b",".claude\u002Fskills\u002Fspec-investigate",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 spec-investigate",{"tool":39,"command":40},"bunx","bunx skills add turbokast\u002Fmythhelm --skill spec-investigate",{"tool":42,"command":43},"pnpm","pnpm dlx skills add turbokast\u002Fmythhelm --skill spec-investigate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspec-investigate\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",[],[]]