[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AHBQAHTZGGPC11P24MNDB5":3,"skill-same:01M7AHBQAHTZGGPC11P24MNDB5":46},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7AHBQAHTZGGPC11P24MNDB5","gen-spec",null,"Guided specification generation wizard. Use when adding a new feature, API endpoint, or component, to force a written spec before implementation: validates scope, drafts a structured spec against the six required sections, runs a five-check health validation, and registers it in the project. Also runs standalone as `validate \u003Cpath>` to health-check an existing spec. NOT for: single-file bug fixes, refactors with no new behavior, or documentation-only changes.","SamyakJhaveri\u002Floam","SamyakJhaveri","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39847642?v=4","01M7AH87180VZDSRHE20JD1S32","Samyak Jhaveri","01M7AH871WNGEHDVNXJM2B520R",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fgen-spec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gen-spec\ndisable-model-invocation: true\ndescription: >\n  Guided specification generation wizard. Use when adding a new feature, API\n  endpoint, or component, to force a written spec before implementation:\n  validates scope, drafts a structured spec against the six required sections,\n  runs a five-check health validation, and registers it in the project. Also\n  runs standalone as `validate \u003Cpath>` to health-check an existing spec. NOT\n  for: single-file bug fixes, refactors with no new behavior, or\n  documentation-only changes.\nargument-hint: \"\u003Cfeature-name> | validate \u003Cpath-to-spec>\"\n---\n\n# gen-spec\n\nStructured workflow for generating a specification document before writing any implementation code.\nSpecs-before-code prevents scope drift and makes review cheaper.\n\n## Arguments\n\n`$ARGUMENTS` is one of:\n\n- `\u003Cname>` - feature or component name (e.g. `user-auth`, `batch-processor`), which runs the full generation workflow.\n- `validate \u003Cpath>` - run the spec health check on an existing spec and nothing else (Phase 3 only).\n\n## The six required sections\n\nEvery spec this skill writes or validates has exactly these sections, in this order.\nThis is the template; there is no separate conventions file to consult.\n\n1. **Identity** - the spec's name (kebab-case, matching the filename), one-sentence purpose, status (`draft` \u002F `approved` \u002F `implemented`), and links to related specs, ADRs, or design docs.\n2. **Inputs** - every input the feature consumes: parameters, files, environment, upstream data, and their types and sources. Name where each comes from.\n3. **Behavior** - what the feature does with those inputs, including the ordering that matters, the state it touches, and the error paths. Describe WHAT, not the implementation's HOW.\n4. **Outputs** - what leaves the feature: return values, written files, emitted events, side effects, and their shapes.\n5. **Constraints** - the boundaries that bind this spec specifically: what it must NOT do, what it must not touch, performance or compatibility limits, and explicit non-goals. Generic filler (\"don't write bad code\") does not count as a constraint.\n6. **Acceptance Criteria** - the checkable conditions for \"done\". Each criterion is testable, specific, and independent of the others.\n\n## Workflow\n\n### Phase 1: Scope validation\n\n- Confirm the feature or component boundaries with the user.\n- Identify dependencies and integration points.\n- Search the project for existing specs that overlap, and avoid duplicating them.\n- Review any related interface or stage contracts that already exist.\n- If a decision inside the scope warrants an ADR, apply the three-part test. Write the ADR only when all three hold: the decision is (1) hard to reverse, (2) surprising to a future reader, and (3) a genuine trade-off with real alternatives. Skip ADRs for trivial or self-evident decisions.\n\n### Phase 2: Draft the spec\n\n- Create `specs\u002F\u003Cname>.md`, or the project's established spec location and format (`.yaml` \u002F `.json`) if it has one.\n- Write all six required sections above, in order.\n- Link to related specs, ADRs, or design docs from the Identity section.\n\n### Phase 3: Validate (spec health check)\n\nRun all five checks.\n\n1. **Structure** - all six required sections are present and non-empty: Identity, Inputs, Behavior, Outputs, Constraints, Acceptance Criteria.\n2. **References** - for every file or resource the spec references, verify it exists on disk.\n3. **Criteria quality** - each acceptance criterion is testable, specific, and independent. A criterion nobody can check fails this.\n4. **Naming** - the filename is kebab-case and the Identity name matches the filename.\n5. **Constraints** - the Constraints section is non-empty and carries spec-specific exclusions, not generic boilerplate.\n\nReport exactly this shape:\n\n```\n=== SPEC CHECK: \u003Cname> ===\nStructure:   [PASS\u002FFAIL]\nReferences:  [PASS\u002FFAIL]\nCriteria:    [PASS\u002FFAIL]\nNaming:      [PASS\u002FFAIL]\nConstraints: [PASS\u002FFAIL]\n```\n\nEvery FAIL gets a one-line diagnosis naming what is missing or wrong.\nFix all failures before proceeding to Phase 4.\n\n### Phase 4: Review\n\n- Run an adversarial plan review over the spec (the `\u002Fplan-review` skill, if installed, or a blind reviewer subagent otherwise).\n- Address the findings before marking the spec ready.\n- Get user sign-off on the final spec.\n\n### Phase 5: Register\n\n- Add the spec to the project's spec index, if one exists.\n- Cross-reference it from the routing docs (`CONTEXT.md`, `CLAUDE.md`, or equivalent) for the area it governs.\n- The spec is now the source of truth for implementation.\n\n## Validate mode\n\nWhen `$ARGUMENTS` starts with `validate`, run **only Phase 3** against the named spec file and report PASS\u002FFAIL with diagnosis.\nSkip the generation phases entirely; write nothing.\n\nSearch order for the spec path: `specs\u002F`, `docs\u002Fspecs\u002F`, `docs\u002Fcontracts\u002F`, then the literal path as given.\n\n## Principles\n\n- A spec is a contract, not a wishlist. Every statement should be verifiable.\n- Acceptance criteria are the spec's value. If they are vague, the spec is vague.\n- The spec drives implementation, not the reverse. Never retrofit a spec to match code already written.\n- Keep specs DRY against interface contracts: a spec describes WHAT, a contract describes HOW.\n","# gen-spec\n\nStructured workflow for generating a specification document before writing any implementation code.\nSpecs-before-code prevents scope drift and makes review cheaper.\n\n## Arguments\n\n`$ARGUMENTS` is one of:\n\n- `\u003Cname>` - feature or component name (e.g. `user-auth`, `batch-processor`), which runs the full generation workflow.\n- `validate \u003Cpath>` - run the spec health check on an existing spec and nothing else (Phase 3 only).\n\n## The six required sections\n\nEvery spec this skill writes or validates has exactly these sections, in this order.\nThis is the template; there is no separate conventions file to consult.\n\n1. **Identity** - the spec's name (kebab-case, matching the filename), one-sentence purpose, status (`draft` \u002F `approved` \u002F `implemented`), and links to related specs, ADRs, or design docs.\n2. **Inputs** - every input the feature consumes: parameters, files, environment, upstream data, and their types and sources. Name where each comes from.\n3. **Behavior** - what the feature does with those inputs, including the ordering that matters, the state it touches, and the error paths. Describe WHAT, not the implementation's HOW.\n4. **Outputs** - what leaves the feature: return values, written files, emitted events, side effects, and their shapes.\n5. **Constraints** - the boundaries that bind this spec specifically: what it must NOT do, what it must not touch, performance or compatibility limits, and explicit non-goals. Generic filler (\"don't write bad code\") does not count as a constraint.\n6. **Acceptance Criteria** - the checkable conditions for \"done\". Each criterion is testable, specific, and independent of the others.\n\n## Workflow\n\n### Phase 1: Scope validation\n\n- Confirm the feature or component boundaries with the user.\n- Identify dependencies and integration points.\n- Search the project for existing specs that overlap, and avoid duplicating them.\n- Review any related interface or stage contracts that already exist.\n- If a decision inside the scope warrants an ADR, apply the three-part test. Write the ADR only when all three hold: the decision is (1) hard to reverse, (2) surprising to a future reader, and (3) a genuine trade-off with real alternatives. Skip ADRs for trivial or self-evident decisions.\n\n### Phase 2: Draft the spec\n\n- Create `specs\u002F\u003Cname>.md`, or the project's established spec location and format (`.yaml` \u002F `.json`) if it has one.\n- Write all six required sections above, in order.\n- Link to related specs, ADRs, or design docs from the Identity section.\n\n### Phase 3: Validate (spec health check)\n\nRun all five checks.\n\n1. **Structure** - all six required sections are present and non-empty: Identity, Inputs, Behavior, Outputs, Constraints, Acceptance Criteria.\n2. **References** - for every file or resource the spec references, verify it exists on disk.\n3. **Criteria quality** - each acceptance criterion is testable, specific, and independent. A criterion nobody can check fails this.\n4. **Naming** - the filename is kebab-case and the Identity name matches the filename.\n5. **Constraints** - the Constraints section is non-empty and carries spec-specific exclusions, not generic boilerplate.\n\nReport exactly this shape:\n\n```\n=== SPEC CHECK: \u003Cname> ===\nStructure:   [PASS\u002FFAIL]\nReferences:  [PASS\u002FFAIL]\nCriteria:    [PASS\u002FFAIL]\nNaming:      [PASS\u002FFAIL]\nConstraints: [PASS\u002FFAIL]\n```\n\nEvery FAIL gets a one-line diagnosis naming what is missing or wrong.\nFix all failures before proceeding to Phase 4.\n\n### Phase 4: Review\n\n- Run an adversarial plan review over the spec (the `\u002Fplan-review` skill, if installed, or a blind reviewer subagent otherwise).\n- Address the findings before marking the spec ready.\n- Get user sign-off on the final spec.\n\n### Phase 5: Register\n\n- Add the spec to the project's spec index, if one exists.\n- Cross-reference it from the routing docs (`CONTEXT.md`, `CLAUDE.md`, or equivalent) for the area it governs.\n- The spec is now the source of truth for implementation.\n\n## Validate mode\n\nWhen `$ARGUMENTS` starts with `validate`, run **only Phase 3** against the named spec file and report PASS\u002FFAIL with diagnosis.\nSkip the generation phases entirely; write nothing.\n\nSearch order for the spec path: `specs\u002F`, `docs\u002Fspecs\u002F`, `docs\u002Fcontracts\u002F`, then the literal path as given.\n\n## Principles\n\n- A spec is a contract, not a wishlist. Every statement should be verifiable.\n- Acceptance criteria are the spec's value. If they are vague, the spec is vague.\n- The spec drives implementation, not the reverse. Never retrofit a spec to match code already written.\n- Keep specs DRY against interface contracts: a spec describes WHAT, a contract describes HOW.\n",{"name":5,"description":24,"argument-hint":25,"disable-model-invocation":26},"Guided specification generation wizard. Use when adding a new feature, API endpoint, or component, to force a written spec before implementation: validates scope, drafts a structured spec against the six required sections, runs a five-check health validation, and registers it in the project. Also runs standalone as `validate \u003Cpath>` to health-check an existing spec. NOT for: single-file bug fixes, refactors with no new behavior, or documentation-only changes.\n","\u003Cfeature-name> | validate \u003Cpath-to-spec>",true,"main","85a41de587b98bb440cccf78f081a6bee67fe90e","cultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fgen-spec","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri","2026-11-15 04:06:30",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":26},[35,38,41],{"tool":36,"command":37},"npx","npx skills add SamyakJhaveri\u002Floam --skill gen-spec",{"tool":39,"command":40},"bunx","bunx skills add SamyakJhaveri\u002Floam --skill gen-spec",{"tool":42,"command":43},"pnpm","pnpm dlx skills add SamyakJhaveri\u002Floam --skill gen-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fcultivation\u002Fparked\u002Fsam-cc-setup\u002Fskills\u002Fgen-spec\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7AHGVPTGK3JGQ9XYG5XJ6PR","verify-loam","Prove a Loam change in a real rendered project: copier-render this checkout, then drive headless and interactive Claude Code sessions, stubbed Codex runs and copier updates in the render and capture hook, memory, deny-rule, update and check evidence. Use before shipping any seed, hook, settings or copier.yml change.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.claude\u002Fskills\u002Fverify-loam\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7AHGEDXX7GWJ32S9BZAEWAJ","hypothesis-tree","Persistent hypothesis tree for multi-step, multi-session investigations. Use when a \"why does X fail\" question branches into sub-hypotheses that must survive across sessions, or when falsifiable claims need tracking with dated, linked evidence. Maintains one markdown file with add, update, review, and prune subcommands, each gated on verifying the cited evidence file exists and supports the claim. NOT for a single-session bug hunt, a one-command question, or general note-taking.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fhypothesis-tree\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7AHGADA1CX9M0B0QSFJYGW5","fable-prompting","Which Claude Fable 5.2 guide sections you can act on from a session, and which Claude Code already injects. Use before writing a Fable session prompt or brief.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Ffable-prompting\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AHG7AGBSQ6HH04C70TSM8H","catchup","Read-only session bootstrap briefing of git state, commits, handoff, tasks and red flags. Use when resuming work, starting a fresh session, or unsure of project state.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fseed\u002F.agents\u002Fskills\u002Fcatchup\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AHG52XX2N7AT7JNHS6MN1S","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AHG00SXGAGJA7C6XA193J6","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FSamyakJhaveri\u002Floam\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Farchitecture-working\u002Ftooling\u002Fmattpocock-skills\u002Fwizard\u002FSKILL.md",[],[]]