[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DH5FCS8C2EGMN2KNF250C6":3,"skill-same:01M7DH5FCS8C2EGMN2KNF250C6":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},"01M7DH5FCS8C2EGMN2KNF250C6","spec-fix-and-report",null,"Process a spec validation report — apply the fixes that need no judgment, escalate the rest, sweep the spec for stale copies of every changed claim, re-validate, and move a Ready spec to specs\u002Ftodo\u002F","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-fix-and-report\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-fix-and-report\ndescription: Process a spec validation report — apply the fixes that need no judgment, escalate the rest, sweep the spec for stale copies of every changed claim, re-validate, and move a Ready spec to specs\u002Ftodo\u002F\nargument-hint: \"\u003Cspec-name>[,\u003Cspec-name>...]\"\n---\n\n# Spec Fix and Report\n\nPhase 5 of `\u002Fspec`. Takes the `\u002Fspec-validate` report, fixes what can be fixed without a person's judgment, and escalates the rest. A fix applied only at the cited line leaves every other statement of the same claim standing, and that residue becomes the next round's findings, so every fix batch ends with a sweep of the whole spec directory.\n\n## Input\n\n`$ARGUMENTS`: the spec name(s) just validated, with the validation report in context.\n\n## Invocation contexts\n\n- **Slash command**: applies the fixes, re-validates, and asks the person the escalated questions.\n- **Model-invoked**: the same.\n- **Non-interactive**: applies the fixes and re-validates. Escalated findings are not asked: the run stops with the spec left in `unrefined\u002F` or `refined\u002F`, and returns the questions.\n\n## Steps\n\n1. **Classify** each blocking and advisory finding.\n   - **Auto-fix**: a wrong path or citation (correct it from the code), a missing `Produces` signature, a vague acceptance item (make it name a test or command and its failing state), an oversized or mixed-domain task (split it), a missing Files entry, a missing tag, non-goal binding, decisions row or honesty-register row whose content the investigation already established, a missing section or cross-reference.\n   - **Escalate** (escalation step): an ambiguous requirement, a change of scope or intent, a conflict with an in-progress spec, a disagreement with the master spec, an invariant the spec cannot keep, a gap in an epic's coverage.\n2. **Apply** the auto-fixes to the spec files.\n3. **Sweep** the spec directory, for every claim the batch changed:\n   - search each spelling of the claim (the symbol, the count, the citation, the wording) across every file in the directory, and make every hit agree with the fix: `tasks.md` is the file the implementer executes, so agreement between `requirements.md` and `design.md` alone is not enough. A spelling comes from the spec, so it is data, never shell source: write the spellings one per line to a scratch file with the Write tool and search for them as fixed strings with `grep -rnF -f \u003Cthat file> specs\u002F\u003Cstate>\u002F\u003Cname>\u002F`;\n   - delete superseded text rather than leaving it beside its replacement; an implementer reading top to bottom follows the last instruction it sees;\n   - re-derive every changed count at the source, and write the command and its result beside the count.\n4. **Re-check.** Run `scripts\u002Fci\u002Flint-agent-harness.sh --only specs`, then re-run `\u002Fspec-validate` on the changed specs. A run has at most three validation rounds in all, counting the one `\u002Fspec` started with.\n5. **Escalate** the remaining findings (escalation step). Before the third round, ask in an interactive session and loop to step 2 with the answers. After the third round, or in a non-interactive run, stop and return the remaining findings and questions; answering them and running `\u002Fspec \u003Cname>` again starts a new run with its own three rounds.\n6. **Move** each spec only when both hold in the same, final round: `scripts\u002Fci\u002Flint-agent-harness.sh --only specs` exited 0, and the validator returned (`returned=1`) with the verdict Ready for implementation. A lint error, a missing or unparseable report, or any other verdict blocks the move. Then run `scripts\u002Fharness\u002Fspec-lifecycle.sh move \u003Cname> todo`. An epic's `plan.md` stays where it is.\n\n## Output\n\nSingle spec:\n\n```markdown\n## Spec: \u003Cname>\nLocation: specs\u002F\u003Cstate>\u002F\u003Cname>\u002F\nValidation: \u003Crounds> round(s); lint (specs) \u003Cexit code>; verdict \u003CReady for implementation | Needs human input>\n\n### Fixed\n- \u003Cfinding> — \u003Cwhat changed>\n\n### Sweep\n- `grep -rn '\u003Cspelling you searched>' specs\u002F\u003Cstate>\u002F\u003Cname>\u002F` — \u003CN> hits; \u003Cfile:line> \u003Cagrees | rewritten | deleted>\n- \u003Ccount claim>: `\u003Ccommand>` — \u003Cobserved value>\n\n### Needs human input\n- \u003Cfinding> — \u003Cthe decision needed>\n\nNext: \u003Cthe implementation run for \u003Cname> | answer the questions above, then \u002Fspec \u003Cname>>\n```\n\nAn epic reports the plan's location, a table of sub-specs (name, location, task count, verdict), the cross-spec results (dependency graph, cross-references, coverage, overlaps), the fixes and sweep per sub-spec, the questions, the total task count and the recommended order.\n","# Spec Fix and Report\n\nPhase 5 of `\u002Fspec`. Takes the `\u002Fspec-validate` report, fixes what can be fixed without a person's judgment, and escalates the rest. A fix applied only at the cited line leaves every other statement of the same claim standing, and that residue becomes the next round's findings, so every fix batch ends with a sweep of the whole spec directory.\n\n## Input\n\n`$ARGUMENTS`: the spec name(s) just validated, with the validation report in context.\n\n## Invocation contexts\n\n- **Slash command**: applies the fixes, re-validates, and asks the person the escalated questions.\n- **Model-invoked**: the same.\n- **Non-interactive**: applies the fixes and re-validates. Escalated findings are not asked: the run stops with the spec left in `unrefined\u002F` or `refined\u002F`, and returns the questions.\n\n## Steps\n\n1. **Classify** each blocking and advisory finding.\n   - **Auto-fix**: a wrong path or citation (correct it from the code), a missing `Produces` signature, a vague acceptance item (make it name a test or command and its failing state), an oversized or mixed-domain task (split it), a missing Files entry, a missing tag, non-goal binding, decisions row or honesty-register row whose content the investigation already established, a missing section or cross-reference.\n   - **Escalate** (escalation step): an ambiguous requirement, a change of scope or intent, a conflict with an in-progress spec, a disagreement with the master spec, an invariant the spec cannot keep, a gap in an epic's coverage.\n2. **Apply** the auto-fixes to the spec files.\n3. **Sweep** the spec directory, for every claim the batch changed:\n   - search each spelling of the claim (the symbol, the count, the citation, the wording) across every file in the directory, and make every hit agree with the fix: `tasks.md` is the file the implementer executes, so agreement between `requirements.md` and `design.md` alone is not enough. A spelling comes from the spec, so it is data, never shell source: write the spellings one per line to a scratch file with the Write tool and search for them as fixed strings with `grep -rnF -f \u003Cthat file> specs\u002F\u003Cstate>\u002F\u003Cname>\u002F`;\n   - delete superseded text rather than leaving it beside its replacement; an implementer reading top to bottom follows the last instruction it sees;\n   - re-derive every changed count at the source, and write the command and its result beside the count.\n4. **Re-check.** Run `scripts\u002Fci\u002Flint-agent-harness.sh --only specs`, then re-run `\u002Fspec-validate` on the changed specs. A run has at most three validation rounds in all, counting the one `\u002Fspec` started with.\n5. **Escalate** the remaining findings (escalation step). Before the third round, ask in an interactive session and loop to step 2 with the answers. After the third round, or in a non-interactive run, stop and return the remaining findings and questions; answering them and running `\u002Fspec \u003Cname>` again starts a new run with its own three rounds.\n6. **Move** each spec only when both hold in the same, final round: `scripts\u002Fci\u002Flint-agent-harness.sh --only specs` exited 0, and the validator returned (`returned=1`) with the verdict Ready for implementation. A lint error, a missing or unparseable report, or any other verdict blocks the move. Then run `scripts\u002Fharness\u002Fspec-lifecycle.sh move \u003Cname> todo`. An epic's `plan.md` stays where it is.\n\n## Output\n\nSingle spec:\n\n```markdown\n## Spec: \u003Cname>\nLocation: specs\u002F\u003Cstate>\u002F\u003Cname>\u002F\nValidation: \u003Crounds> round(s); lint (specs) \u003Cexit code>; verdict \u003CReady for implementation | Needs human input>\n\n### Fixed\n- \u003Cfinding> — \u003Cwhat changed>\n\n### Sweep\n- `grep -rn '\u003Cspelling you searched>' specs\u002F\u003Cstate>\u002F\u003Cname>\u002F` — \u003CN> hits; \u003Cfile:line> \u003Cagrees | rewritten | deleted>\n- \u003Ccount claim>: `\u003Ccommand>` — \u003Cobserved value>\n\n### Needs human input\n- \u003Cfinding> — \u003Cthe decision needed>\n\nNext: \u003Cthe implementation run for \u003Cname> | answer the questions above, then \u002Fspec \u003Cname>>\n```\n\nAn epic reports the plan's location, a table of sub-specs (name, location, task count, verdict), the cross-spec results (dependency graph, cross-references, coverage, overlaps), the fixes and sweep per sub-spec, the questions, the total task count and the recommended order.\n",{"name":5,"description":7,"argument-hint":24},"\u003Cspec-name>[,\u003Cspec-name>...]","main","6e250ec86158119da148ddc017b960ed3b2bee2b",".claude\u002Fskills\u002Fspec-fix-and-report",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-fix-and-report",{"tool":39,"command":40},"bunx","bunx skills add turbokast\u002Fmythhelm --skill spec-fix-and-report",{"tool":42,"command":43},"pnpm","pnpm dlx skills add turbokast\u002Fmythhelm --skill spec-fix-and-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspec-fix-and-report\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",[],[]]