[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DM28JSC3GWEJ82346VGW6":3,"skill-same:01M79DM28JSC3GWEJ82346VGW6":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79DM28JSC3GWEJ82346VGW6","inspire-workspace",null,"Workspace-level validation: the global pre-PR review (orchestrating module + cross-module checks) and vault-structure validation. Use for the required pre-merge gate and top-level structure checks. ADR lifecycle lives in \u002Finspire-adr; the task tracker in \u002Finspire-task.","Genomcore\u002Finspire","Genomcore","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F67845649?v=4","01M79DGNHB5DVE1Q8TC7F3K4FY","01M79DGNM14QF64G5NWT5X00SY",0,"MIT","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inspire-workspace\ndescription: \"Workspace-level validation: the global pre-PR review (orchestrating module + cross-module checks) and vault-structure validation. Use for the required pre-merge gate and top-level structure checks. ADR lifecycle lives in \u002Finspire-adr; the task tracker in \u002Finspire-task.\"\n---\n\n# \u002Finspire-workspace — Workspace-level Operations\n\n## Scope\n\nThis skill owns **workspace-scoped validation** — the cross-cutting checks that\ndon't belong to a single module or feature:\n\n- **Global review** — the pre-merge gate, orchestrating module-level and\n  cross-module checks.\n- **Vault structure** — the `01_spec\u002F` layout, typed extensions, and the tracker's\n  on-disk invariants.\n\nIt does **not** own the artifacts it validates the coherence of: **ADR lifecycle**\nis [`\u002Finspire-adr`](..\u002Finspire-adr\u002FSKILL.md) and the **task tracker** is\n[`\u002Finspire-task`](..\u002Finspire-task\u002FSKILL.md). This skill reads ADRs and tickets to\njudge coherence; it never authors them.\n\nSeveral checks in `review` and `structure` read against the project's **faces**\n(`*.face.md`) and **bundles** (`*.bundle.md`). What `faces:` and `bundles:` mean on an\nartifact, and how scope resolves, are defined once in\n[`_references\u002Fface-scope.md`](..\u002F_references\u002Fface-scope.md); read it before judging\nanything face- or bundle-scoped. A project without screens has no face, and the\nface-scoped checks have nothing to read.\n\n## Invocation\n\n- `\u002Finspire-workspace review` — full vault review\n- `\u002Finspire-workspace review {module1} {module2}` — scoped to selected modules + cross-module checks\n- `\u002Finspire-workspace structure` — validate the `01_spec\u002F` layout, typed extensions, task tracker, vault conventions\n\n## Subcommands in `references\u002F`\n\nEach subcommand's core procedure lives in a reference file. **Before executing\nany subcommand, read every reference file its index row names** — the table\nbelow is an index, not the flow.\n\n| Subcommand | What its reference holds |\n|---|---|\n| [`review`](references\u002Fworkspace-review.md) | the validators, Phases 3–6 + Signals — the cross-cutting checks; the Execution mode, Phases 1–2, the Output format skeleton and the `### Review rules` stay in this file; Phase 2 additionally reads [`inspire-module\u002Freferences\u002Fmodule-review.md`](..\u002Finspire-module\u002Freferences\u002Fmodule-review.md) |\n| [`structure`](references\u002Fworkspace-structure.md) | The full top-level vault checks + their output skeleton |\n\n## Subcommand: review (global)\n\n**REQUIRED** before any PR that modifies files in `inspire_kb\u002F`. Orchestrates a\nfull consistency review across all affected modules and the vault structure.\n\n### Execution mode\n\nThe **checks, severity model, and output are identical** in both modes — only the\nscheduling differs.\n\n- **Sequential (default).** Execute the phases top-to-bottom in this agent — Phases\n  1–2 below, then the validators, Phases 3–6 + Signals in\n  [`references\u002Fworkspace-review.md`](references\u002Fworkspace-review.md).\n- **Workflow (opt-in, when the user enables ultracode \u002F multi-agent).** After\n  Phase 1 (scope), run the bundled workflow at\n  [`review.workflow.mjs`](review.workflow.mjs) via the **Workflow** tool\n  — pass `args: { modules: [\u003Cin-scope slugs>] }` and prefer `scriptPath` with that\n  file's absolute path. It fans the per-module reviews out in parallel, runs a\n  deterministic **completeness gate** (any dropped module review becomes a\n  `critical: review-incomplete` finding — never a silent pass), then a single\n  synthesizer runs the cross-cutting phases over the **full repo** and emits the\n  standard report.\n\nInvariants both modes MUST preserve: **read-only** (flag, never edit, never invoke\na fix-skill); ADR-propagation alignment is judged by reading each ADR's\n`Status` + `Decision` — design-workspace coherence (features + screen spec + horizontal\nprototype + specs) is required at *every* maturity, and higher maturities add\n*external* evidence checkable only by pointer (`prototyped` → a `**Prototype:**`\npointer to an external functional prototype; `implemented` → a codebase reference);\nand the output uses the exact skeleton in **Output format** below.\n\n### Phase 1 — Identify scope\n\n- If modules are specified, use those. Otherwise, find every `*.module.md` under\n  `inspire_kb\u002F01_spec\u002F`: each one is a module, and its id is the file name without\n  `.module.md`.\n- For each module in scope, delegate to `\u002Finspire-module review {module}`.\n\n### Phase 2 — Module reviews\n\nFor each module in scope, the module review performs the checks in\n[`inspire-module\u002Freferences\u002Fmodule-review.md`](..\u002Finspire-module\u002Freferences\u002Fmodule-review.md)\n— referenced, never restated.\n\n### Output format\n\n```markdown\n# Global Review | {date}\n\n## Scope\n- Modules reviewed: {list}\n- Validators: `review.sh inspire_kb` — {PASS | N errors, M warnings}\n\n## Summary\n{X} issues: {critical} critical, {important} important, {minor} minor\nDrift items pending: {N}\n\n## By Module\n### {module}\n- [{severity}] {description} — {file}:{line} | Fix: `\u002F{skill}`\n\n## Cross-Module\n- [{severity}] {description}\n\n## Vault Structure\n## Prototype Component Adoption\n- {Component}: {adopted}\u002F{total} pages\n- {Component} — {shell}: {adopted}\u002F{total} pages   (one line per shell, from 2+ faces)\n## Catalog Coherence\n- Patterns: {total} defined, {used}, {orphan}\n- Components: {total} defined, {used}, {orphan}\n- Design system variance: reported under Signals\n\n## Signals\n{`.inspire\u002Fbin\u002Ftrust.sh report` output, verbatim}\n- Design system: {N} per-face variant section(s), {L} lines\n\n## OK\n```\n\n### Review rules\n\n1. **Be thorough.** This is the pre-merge gate.\n2. **Be specific.** Every finding includes a file path + line number.\n3. **Prioritize by impact.** Critical = broken refs, missing files, a module review\n   that did not complete (`review-incomplete`, see **Execution mode**), ADR\n   consequences not reflected within their maturity's reach. Important = stale\n   content, missing coverage, legacy structure. Minor = naming, formatting.\n4. **No false positives.** If unsure, note as \"verify\".\n5. **Actionable.** Every finding suggests the skill to invoke.\n6. **Delegate deep dives.** For complex feature-level issues, suggest\n   `\u002Finspire-feature review {id}`.\n7. **Pending drift is not failure.** Prototype drift and pending component adoption\n   are `important`, not `critical`, unless they contradict an ADR within its\n   maturity's reach.\n8. **An undeclared contradiction is drift, not an override.** Where two layers\n   answer one question differently, the narrower artifact wins only where it\n   declares the departure in the open; otherwise the wider rule holds and the\n   contradiction is a finding routed to the narrower artifact's owning skill\n   ([`_references\u002Fauthority.md`](..\u002F_references\u002Fauthority.md)). Report the same\n   departure declared in a third artifact as a decision sitting at the wrong rung,\n   and name the skill that would move it — `\u002Finspire-adr` for the product,\n   `\u002Finspire-lesson` for the runtime. This does not soften rule 7: nothing below the\n   decision rung has a place to declare an ADR departure, so contradicting a current\n   ADR within its maturity's reach is never an override and escalates exactly as\n   rule 7 says.\n9. **Signals are measurements, not findings.** This is the single statement of how\n   every signal is treated — the trust report's groups and the design-system\n   variance count alike. They are reported every run, including when nothing is\n   wrong; they carry no severity of their own, and never above `important` where one\n   is shown; no fix routing beyond the owning skill; never file a ticket from one;\n   never block the pre-PR gate on one. They re-appear for as long as they stay true\n   ([trust-stamps](..\u002F_references\u002Ftrust-stamps.md#report)).\n10. **Consult the task tracker.** Known items in `inspire_kb\u002F99_tracker\u002Ftickets\u002F`\n   are flagged `(tracked: TASK-{id})`. Use `\u002Finspire-task list`.\n11. **Required follow-up skills.** When flagging drift, name the mandatory fix skill:\n   - Prototype drift → `\u002Finspire-prototype`\n   - screen spec drift → `\u002Finspire-screens`\n   - Feature drift → `\u002Finspire-module update` or `\u002Finspire-feature update`\n   - ADR misalignment → `\u002Finspire-adr update`\n   - A face or bundle finding, or an unresolved `faces:` \u002F `bundles:` id → `\u002Finspire-face review`\n   - A process finding → `\u002Finspire-process review`\n\n## Subcommand: structure\n\nThe full procedure — the top-level vault checks and their output skeleton —\nlives in [`references\u002Fworkspace-structure.md`](references\u002Fworkspace-structure.md).\n\n## Rules\n\n> **Output language.** Write review reports and findings in the project's declared\n> `output_language` (default English), per\n> [`_references\u002Foutput-language.md`](..\u002F_references\u002Foutput-language.md). Applies\n> whatever language the conversation is in; machine-read tokens (frontmatter\n> keys\u002Fvalues, link paths, filenames) stay verbatim.\n\n> **Writing contract.** Review reports and findings follow\n> [`_references\u002Fwriting-style.md`](..\u002F_references\u002Fwriting-style.md).\n\n> **Lesson capture.** At a natural pause, when the operator's feedback should\n> change how this skill behaves, offer `\u002Finspire-lesson note` — never auto-write\n> a lesson. Protocol and ticket-vs-lesson routing:\n> [`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md).\n\n1. **`review` and `structure` are read-only.** They suggest and flag; they never\n   edit files or invoke a fix-skill.\n2. **Consult the task tracker.** Known items live in\n   `inspire_kb\u002F99_tracker\u002Ftickets\u002F` (`\u002Finspire-task list`); don't re-report them as\n   new findings.\n3. **Git discipline is shared.** Branch\u002Fcommit\u002FPR conventions, merge-conflict\n   auditing, and the git safety protocol live in\n   [`_references\u002Fgit-conventions.md`](..\u002F_references\u002Fgit-conventions.md) (sensible\n   defaults; the project's `CLAUDE.md` overrides). Follow it whenever the operator\n   asks for a branch, commit, or PR — and never commit\u002Fpush on your own initiative.\n\n## Related skills\n\n- `\u002Finspire-adr` — ADR lifecycle (create \u002F update \u002F promote \u002F supersede). Review\n  judges whether ADR consequences propagated; `\u002Finspire-adr` authors them.\n- `\u002Finspire-task` — the task tracker. `structure` validates its on-disk invariants;\n  `\u002Finspire-task` operates the tickets.\n- `\u002Finspire-module`, `\u002Finspire-feature` — the module\u002Ffeature reviews this\n  orchestrates and delegates deep dives to.\n- `\u002Finspire-face` — owns faces and bundles and is the diagnostic for their\n  coherence. Review flags `faces:` and `bundles:` values that don't resolve and\n  screens that bind actions their face does not reach; the fix is that skill's.\n- `\u002Finspire-process` — owns processes; review reports `process-shape` findings and\n  routes them there.\n","# \u002Finspire-workspace — Workspace-level Operations\n\n## Scope\n\nThis skill owns **workspace-scoped validation** — the cross-cutting checks that\ndon't belong to a single module or feature:\n\n- **Global review** — the pre-merge gate, orchestrating module-level and\n  cross-module checks.\n- **Vault structure** — the `01_spec\u002F` layout, typed extensions, and the tracker's\n  on-disk invariants.\n\nIt does **not** own the artifacts it validates the coherence of: **ADR lifecycle**\nis [`\u002Finspire-adr`](..\u002Finspire-adr\u002FSKILL.md) and the **task tracker** is\n[`\u002Finspire-task`](..\u002Finspire-task\u002FSKILL.md). This skill reads ADRs and tickets to\njudge coherence; it never authors them.\n\nSeveral checks in `review` and `structure` read against the project's **faces**\n(`*.face.md`) and **bundles** (`*.bundle.md`). What `faces:` and `bundles:` mean on an\nartifact, and how scope resolves, are defined once in\n[`_references\u002Fface-scope.md`](..\u002F_references\u002Fface-scope.md); read it before judging\nanything face- or bundle-scoped. A project without screens has no face, and the\nface-scoped checks have nothing to read.\n\n## Invocation\n\n- `\u002Finspire-workspace review` — full vault review\n- `\u002Finspire-workspace review {module1} {module2}` — scoped to selected modules + cross-module checks\n- `\u002Finspire-workspace structure` — validate the `01_spec\u002F` layout, typed extensions, task tracker, vault conventions\n\n## Subcommands in `references\u002F`\n\nEach subcommand's core procedure lives in a reference file. **Before executing\nany subcommand, read every reference file its index row names** — the table\nbelow is an index, not the flow.\n\n| Subcommand | What its reference holds |\n|---|---|\n| [`review`](references\u002Fworkspace-review.md) | the validators, Phases 3–6 + Signals — the cross-cutting checks; the Execution mode, Phases 1–2, the Output format skeleton and the `### Review rules` stay in this file; Phase 2 additionally reads [`inspire-module\u002Freferences\u002Fmodule-review.md`](..\u002Finspire-module\u002Freferences\u002Fmodule-review.md) |\n| [`structure`](references\u002Fworkspace-structure.md) | The full top-level vault checks + their output skeleton |\n\n## Subcommand: review (global)\n\n**REQUIRED** before any PR that modifies files in `inspire_kb\u002F`. Orchestrates a\nfull consistency review across all affected modules and the vault structure.\n\n### Execution mode\n\nThe **checks, severity model, and output are identical** in both modes — only the\nscheduling differs.\n\n- **Sequential (default).** Execute the phases top-to-bottom in this agent — Phases\n  1–2 below, then the validators, Phases 3–6 + Signals in\n  [`references\u002Fworkspace-review.md`](references\u002Fworkspace-review.md).\n- **Workflow (opt-in, when the user enables ultracode \u002F multi-agent).** After\n  Phase 1 (scope), run the bundled workflow at\n  [`review.workflow.mjs`](review.workflow.mjs) via the **Workflow** tool\n  — pass `args: { modules: [\u003Cin-scope slugs>] }` and prefer `scriptPath` with that\n  file's absolute path. It fans the per-module reviews out in parallel, runs a\n  deterministic **completeness gate** (any dropped module review becomes a\n  `critical: review-incomplete` finding — never a silent pass), then a single\n  synthesizer runs the cross-cutting phases over the **full repo** and emits the\n  standard report.\n\nInvariants both modes MUST preserve: **read-only** (flag, never edit, never invoke\na fix-skill); ADR-propagation alignment is judged by reading each ADR's\n`Status` + `Decision` — design-workspace coherence (features + screen spec + horizontal\nprototype + specs) is required at *every* maturity, and higher maturities add\n*external* evidence checkable only by pointer (`prototyped` → a `**Prototype:**`\npointer to an external functional prototype; `implemented` → a codebase reference);\nand the output uses the exact skeleton in **Output format** below.\n\n### Phase 1 — Identify scope\n\n- If modules are specified, use those. Otherwise, find every `*.module.md` under\n  `inspire_kb\u002F01_spec\u002F`: each one is a module, and its id is the file name without\n  `.module.md`.\n- For each module in scope, delegate to `\u002Finspire-module review {module}`.\n\n### Phase 2 — Module reviews\n\nFor each module in scope, the module review performs the checks in\n[`inspire-module\u002Freferences\u002Fmodule-review.md`](..\u002Finspire-module\u002Freferences\u002Fmodule-review.md)\n— referenced, never restated.\n\n### Output format\n\n```markdown\n# Global Review | {date}\n\n## Scope\n- Modules reviewed: {list}\n- Validators: `review.sh inspire_kb` — {PASS | N errors, M warnings}\n\n## Summary\n{X} issues: {critical} critical, {important} important, {minor} minor\nDrift items pending: {N}\n\n## By Module\n### {module}\n- [{severity}] {description} — {file}:{line} | Fix: `\u002F{skill}`\n\n## Cross-Module\n- [{severity}] {description}\n\n## Vault Structure\n## Prototype Component Adoption\n- {Component}: {adopted}\u002F{total} pages\n- {Component} — {shell}: {adopted}\u002F{total} pages   (one line per shell, from 2+ faces)\n## Catalog Coherence\n- Patterns: {total} defined, {used}, {orphan}\n- Components: {total} defined, {used}, {orphan}\n- Design system variance: reported under Signals\n\n## Signals\n{`.inspire\u002Fbin\u002Ftrust.sh report` output, verbatim}\n- Design system: {N} per-face variant section(s), {L} lines\n\n## OK\n```\n\n### Review rules\n\n1. **Be thorough.** This is the pre-merge gate.\n2. **Be specific.** Every finding includes a file path + line number.\n3. **Prioritize by impact.** Critical = broken refs, missing files, a module review\n   that did not complete (`review-incomplete`, see **Execution mode**), ADR\n   consequences not reflected within their maturity's reach. Important = stale\n   content, missing coverage, legacy structure. Minor = naming, formatting.\n4. **No false positives.** If unsure, note as \"verify\".\n5. **Actionable.** Every finding suggests the skill to invoke.\n6. **Delegate deep dives.** For complex feature-level issues, suggest\n   `\u002Finspire-feature review {id}`.\n7. **Pending drift is not failure.** Prototype drift and pending component adoption\n   are `important`, not `critical`, unless they contradict an ADR within its\n   maturity's reach.\n8. **An undeclared contradiction is drift, not an override.** Where two layers\n   answer one question differently, the narrower artifact wins only where it\n   declares the departure in the open; otherwise the wider rule holds and the\n   contradiction is a finding routed to the narrower artifact's owning skill\n   ([`_references\u002Fauthority.md`](..\u002F_references\u002Fauthority.md)). Report the same\n   departure declared in a third artifact as a decision sitting at the wrong rung,\n   and name the skill that would move it — `\u002Finspire-adr` for the product,\n   `\u002Finspire-lesson` for the runtime. This does not soften rule 7: nothing below the\n   decision rung has a place to declare an ADR departure, so contradicting a current\n   ADR within its maturity's reach is never an override and escalates exactly as\n   rule 7 says.\n9. **Signals are measurements, not findings.** This is the single statement of how\n   every signal is treated — the trust report's groups and the design-system\n   variance count alike. They are reported every run, including when nothing is\n   wrong; they carry no severity of their own, and never above `important` where one\n   is shown; no fix routing beyond the owning skill; never file a ticket from one;\n   never block the pre-PR gate on one. They re-appear for as long as they stay true\n   ([trust-stamps](..\u002F_references\u002Ftrust-stamps.md#report)).\n10. **Consult the task tracker.** Known items in `inspire_kb\u002F99_tracker\u002Ftickets\u002F`\n   are flagged `(tracked: TASK-{id})`. Use `\u002Finspire-task list`.\n11. **Required follow-up skills.** When flagging drift, name the mandatory fix skill:\n   - Prototype drift → `\u002Finspire-prototype`\n   - screen spec drift → `\u002Finspire-screens`\n   - Feature drift → `\u002Finspire-module update` or `\u002Finspire-feature update`\n   - ADR misalignment → `\u002Finspire-adr update`\n   - A face or bundle finding, or an unresolved `faces:` \u002F `bundles:` id → `\u002Finspire-face review`\n   - A process finding → `\u002Finspire-process review`\n\n## Subcommand: structure\n\nThe full procedure — the top-level vault checks and their output skeleton —\nlives in [`references\u002Fworkspace-structure.md`](references\u002Fworkspace-structure.md).\n\n## Rules\n\n> **Output language.** Write review reports and findings in the project's declared\n> `output_language` (default English), per\n> [`_references\u002Foutput-language.md`](..\u002F_references\u002Foutput-language.md). Applies\n> whatever language the conversation is in; machine-read tokens (frontmatter\n> keys\u002Fvalues, link paths, filenames) stay verbatim.\n\n> **Writing contract.** Review reports and findings follow\n> [`_references\u002Fwriting-style.md`](..\u002F_references\u002Fwriting-style.md).\n\n> **Lesson capture.** At a natural pause, when the operator's feedback should\n> change how this skill behaves, offer `\u002Finspire-lesson note` — never auto-write\n> a lesson. Protocol and ticket-vs-lesson routing:\n> [`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md).\n\n1. **`review` and `structure` are read-only.** They suggest and flag; they never\n   edit files or invoke a fix-skill.\n2. **Consult the task tracker.** Known items live in\n   `inspire_kb\u002F99_tracker\u002Ftickets\u002F` (`\u002Finspire-task list`); don't re-report them as\n   new findings.\n3. **Git discipline is shared.** Branch\u002Fcommit\u002FPR conventions, merge-conflict\n   auditing, and the git safety protocol live in\n   [`_references\u002Fgit-conventions.md`](..\u002F_references\u002Fgit-conventions.md) (sensible\n   defaults; the project's `CLAUDE.md` overrides). Follow it whenever the operator\n   asks for a branch, commit, or PR — and never commit\u002Fpush on your own initiative.\n\n## Related skills\n\n- `\u002Finspire-adr` — ADR lifecycle (create \u002F update \u002F promote \u002F supersede). Review\n  judges whether ADR consequences propagated; `\u002Finspire-adr` authors them.\n- `\u002Finspire-task` — the task tracker. `structure` validates its on-disk invariants;\n  `\u002Finspire-task` operates the tickets.\n- `\u002Finspire-module`, `\u002Finspire-feature` — the module\u002Ffeature reviews this\n  orchestrates and delegates deep dives to.\n- `\u002Finspire-face` — owns faces and bundles and is the diagnostic for their\n  coherence. Review flags `faces:` and `bundles:` values that don't resolve and\n  screens that bind actions their face does not reach; the fix is that skill's.\n- `\u002Finspire-process` — owns processes; review reports `process-shape` findings and\n  routes them there.\n",{"name":5,"description":7},"main","bf5124558fc1203b1fe5aea2d2ae38cfba34939b","plugin\u002Fbase\u002Fskills\u002Finspire-workspace",1,"https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire","https:\u002F\u002Finspire.openbims.dev","https:\u002F\u002Fgithub.com\u002FGenomcore","https:\u002F\u002Fgenomcore.com","2026-11-13 22:27:32",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Genomcore\u002Finspire --skill inspire-workspace",{"tool":38,"command":39},"bunx","bunx skills add Genomcore\u002Finspire --skill inspire-workspace",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Genomcore\u002Finspire --skill inspire-workspace","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002FSKILL.md",true,[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fworkspace-review.md","REFERENCE","参考文档",6677,"https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002Freferences\u002Fworkspace-review.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fworkspace-structure.md",5248,"https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002Freferences\u002Fworkspace-structure.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"review.workflow.mjs","SCRIPT","脚本",6104,"https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002Freview.workflow.mjs",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M79DMDSD4Z004V0CB01EYKT4","update","Update this project's INSPIRE runtime to the installed plugin's version: report drift, re-materialize unchanged files, and refuse to clobber local edits. Use after \u002Fplugin update inspire reports a newer base.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M79DMAENSXPJJPWTRA9CMBV0","migrate","Move this project's knowledge base from the layered layout (01_adr, 02_modules, 03_features, 04_domain, 05_screens and the surface roster) to the concept layout under inspire_kb\u002F01_spec\u002F, where every artifact has a typed extension, and convert its [[wikilinks]] to relative Markdown links. Run once, on purpose, after \u002Finspire:update reports the layered layout or counts wikilinks. Rebuilds nothing that is already built.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fmigrate\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M79DM6HZ7YN9M3WGXVN64AW1","init","Install the INSPIRE runtime into this repository: materialize the skills, validators, hooks and knowledge-base skeleton, register the hooks, and freeze the runtime version. Run once per project. Use when setting up INSPIRE in a new or existing repo.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Finit\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M79DKYPKA8TKJCW1GF0W2WAN","inspire-task","Task tracker: create \u002F update \u002F close \u002F list \u002F show tickets in inspire_kb\u002F99_tracker\u002F. A plain-file kanban (one Markdown file per ticket, no external tool) for tracking work, drift, and skill-feedback. Use to open, advance, close, or query tickets.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-task\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M79DKTXQWFBW2P6VMQW3DYWX","inspire-spike","Vertical spikes: register and harvest external functional-prototype repos. A spike is a narrow, deep, throwaway build in its OWN repo that answers 'can we build it as we think?'. Use to register such a repo (name\u002Freference it, set up its learnings hygiene) and to capture its learnings into the vault as a gap analysis against the current project.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-spike\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M79DKQDXVS3TJ6GG6KXYTMXF","inspire-screens","Create and validate screens (a screen is the UI spec for one view). A screen declares its own bindings — data sources, dispatches, navigation, states — and names a shared layout and shared components as dependencies. Use when designing or reviewing an application's screens.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-screens\u002FSKILL.md",[],[]]