[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DK3D80ASZBYZ3R0295P4J":3,"skill-same:01M79DK3D80ASZBYZ3R0295P4J":52},{"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},"01M79DK3D80ASZBYZ3R0295P4J","inspire-lesson",null,"Lessons catalog: capture durable, write-once, version-stamped LESSONS that change how an inspire-* skill behaves in this project — each a single one-line instruction (\"do X this way\"), materialized into the skill so the agent internalizes it. One timestamp-named file per lesson (YYYYMMDD_\u003Cslug>) in inspire_kb\u002F98_lessons\u002F. A lesson is relevant HERE; whether it generalizes is decided upstream. Use to record a lesson after skill friction or a deliberate skill change, list \u002F show them, or purge the archive. Not for product work — that is the tracker (inspire-task), nor for spike\u002Fprototype learnings.","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-lesson\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inspire-lesson\ndescription: \"Lessons catalog: capture durable, write-once, version-stamped LESSONS that change how an inspire-* skill behaves in this project — each a single one-line instruction (\\\"do X this way\\\"), materialized into the skill so the agent internalizes it. One timestamp-named file per lesson (YYYYMMDD_\u003Cslug>) in inspire_kb\u002F98_lessons\u002F. A lesson is relevant HERE; whether it generalizes is decided upstream. Use to record a lesson after skill friction or a deliberate skill change, list \u002F show them, or purge the archive. Not for product work — that is the tracker (inspire-task), nor for spike\u002Fprototype learnings.\"\n---\n\n# \u002Finspire-lesson — Lessons catalog\n\n## Scope\n\nThe **self-teaching layer** —\n`inspire_kb\u002F98_lessons`: **one Markdown file\nper lesson**, **write-once** (created once, never edited). A lesson is a durable,\ntransmissible instruction about how an `inspire-*` **skill itself** should behave —\nnot about the product. It can be *learned* or *taught*; the folder is a **catalog of\nlessons** this project holds.\n\nTwo audiences read the catalog:\n\n1. **This project, across releases** — the catalog is what keeps the agents behaving\n   as you taught them once a release moves the base underneath them. The flow that\n   writes lessons into a skill, and re-derives them against a new base, is **not\n   built**: an update leaves the catalog untouched, so applying a lesson to the\n   skills is the operator's until it exists. Capturing still pays now —\n   a lesson written today is one that flow will find.\n2. **INSPIRE core, via the observer** — an external pull-from-above reads the catalog\n   across many forks and distills the patterns worth folding into the next release.\n   The fork only ever **writes** lessons and is unaware of any central system.\n\nTwo properties keep the org-wide sweep cheap and safe:\n\n- **Timestamp-named** — files are `YYYYMMDD_\u003Cslug>.md`, so a sweep selects a date\n  range by comparing the first 8 characters, without opening a file.\n- **Write-once** — a file below the sweep's date cursor can never have changed, so it\n  is skipped forever; already-processed lessons are never re-worked.\n\nEvery lesson **freezes the INSPIRE version it was captured on** (from the root\n`.inspire.lock`), so the observer can tell whether a newer release already learned it.\n\nThe on-disk contract — naming, the one-line body format, write-once rules, frontmatter\nschema, enums, archive + purge semantics — lives in\n[`references\u002Flessons-format.md`](references\u002Flessons-format.md). **Read it before `note`\nor `purge`.**\n\n## What a lesson is\n\n- **One line, atomic.** The body is a single imperative — *\"When generating a NestJS\n  controller, keep DTOs in a separate file.\"* At most a positive\u002Fnegative pair (*do\n  this* \u002F *not that*), plus an optional **example as support only**. The one-line limit\n  *enforces* atomicity: you cannot pack two intents into one imperative without it\n  obviously being two lessons. This keeps the catalog small and every lesson easy to\n  reason about — and makes update-time reconciliation clean.\n- **Relevant here, not \"upstream-worthy.\"** You capture a lesson because it matters to\n  **you, in this project** — never because you have judged it generalizable. Whether it\n  generalizes is decided **upstream**, by the observer, from the pattern many forks'\n  lessons form. Capture asks only *\"is this worth keeping?\"*\n- **Materialized, not consulted.** The intent is that a lesson is written *into* the\n  skill so the taught behavior **becomes** the behavior — the agent acts on it, it does\n  not check a footnote and apply it if it happens to notice. The model is Terraform's\n  **desired state**: the lessons are the source of truth a run declares, and the skill\n  file is the result it reconciles to them.\n\n## When to capture a lesson\n\nRecord one when a session surfaces something **you want the skill to keep doing (or\nstop doing)**:\n\n- the operator corrects how a skill behaved, in a way that should stick;\n- a deliberate local change to how an `inspire-*` skill works;\n- a recurring friction — an `AskUserQuestion` that should have a default, a step that\n  always needs rework, drift from what the skill anticipated;\n- a house convention or preference the skill should honor;\n- a pattern the skill doesn't cover but should.\n\nIf the signal is **local, actionable work** (\"someone here should fix this\"), file a\nskill-feedback ticket with `inspire-task` instead. A confirmed ticket that should change\nhow a skill behaves graduates into a lesson (see *Relationship to the tracker*).\n\nA lesson is how a project overrides the **runtime** rung — it is the declared channel\nfor \"the skill should behave differently here\"\n([`_references\u002Fauthority.md`](..\u002F_references\u002Fauthority.md)). Where the departure binds\nthe product rather than the skill, it is an ADR or an artifact, not a lesson; and where\nwhat the project wants changed is something mechanical — a frontmatter schema, the\nkeyed-entry vocabulary, a lifecycle state, anything a validator or a parser reads — no\nproject artifact out-specifies it and a lesson is the **only** way in. It is the start\nof the path rather than the whole of it: a lesson teaches the *skills*, and the\nvalidators are not an extension point, so the change lands through the observer and a\nrelease.\n\n## Invocation\n\n- `\u002Finspire-lesson note {title} [--skill X --category preference --supersedes id]`\n- `\u002Finspire-lesson list [--since YYYYMMDD --until YYYYMMDD --skill X --category Z]` (read-only)\n- `\u002Finspire-lesson show {id}` (read-only)\n- `\u002Finspire-lesson purge [--months N | --before YYYYMMDD] [--confirm]`\n\n## Subcommand: note {title} [--flags]\n\n1. Resolve `@handle` from `git config user.email` (cached per session).\n2. Resolve today's date from CLAUDE.md `currentDate` or `date +%Y-%m-%d`.\n3. Read `inspire_version` + `template_sha` from `.inspire.lock` (repo root). If the\n   lock is absent (e.g. inside the template repo itself), fall back to\n   `plugin\u002F.claude-plugin\u002Fplugin.json`; else record `unknown` and warn.\n4. Build the filename `YYYYMMDD_\u003Cslug>.md`, where `\u003Cslug>` is a kebab-case short form\n   of the title (~40 chars). Several lessons may share a date — the slug keeps each\n   name distinct; pick a more specific slug if one would collide. `id` = the filename\n   stem.\n5. Apply flags: `--skill` (required — the skill the lesson teaches, or `runtime` for\n   cross-cutting \u002F methodology), `--category` (default `preference`), `--supersedes`\n   (id of an earlier lesson this revises).\n6. **Draft the one-line instruction with the operator and confirm it.** Keep it to a\n   single imperative; add the optional `Not:` negative and a `> Example:` support line\n   only if they genuinely help. Write the file **once** — frontmatter + the one-line\n   body (see [`references\u002Flessons-format.md`](references\u002Flessons-format.md)).\n7. Print the new id to stdout.\n\n> **Write-once.** After `note`, never edit the file. To revise, write a new lesson with\n> `--supersedes {old-id}`; the old one stays untouched.\n\n## Subcommand: list [--filter]\n\n1. Scan `inspire_kb\u002F98_lessons\u002F*.md` (the live catalog; `--archived` also scans\n   `98_lessons\u002Farchive\u002F`).\n2. `--since` \u002F `--until` filter on the **filename date prefix** (cheap — no frontmatter\n   read). `--skill` \u002F `--category` \u002F `--reporter` filter on frontmatter.\n3. Print a compact table to stdout: `date | category | skill | version | instruction`.\n4. Read-only.\n\n## Subcommand: show {id}\n\nRead the file and print frontmatter + body. Read-only.\n\n## Subcommand: purge [--months N | --before YYYYMMDD] [--confirm]\n\nLocal housekeeping — delete **archived** lessons (those the base has already learned,\nunder `98_lessons\u002Farchive\u002F`) older than a threshold (default `--months 6`), matched on\nthe **filename date prefix**. **Dry-run by default**: list exactly which files would be\nremoved and stop. Delete only when the operator passes `--confirm` (or approves in the\nconversation). Purge is **fully optional** — the archive is durable provenance, and\ndeleted files remain recoverable from git history. Purge only ever removes whole files;\nit never edits one, so the write-once contract holds. (Until the update flow exists,\n`archive\u002F` is empty and purge is a no-op — archiving is populated by an update.)\n\n## Rules\n\n> **Output language — the one exception.** Lessons are authored in **English**,\n> whatever the project's `output_language` is: their reader is the observer \u002F the\n> cross-org INSPIRE core team, not the product team. Everything else in\n> [`_references\u002Foutput-language.md`](..\u002F_references\u002Foutput-language.md) still holds —\n> machine-read tokens stay verbatim.\n\n> **Writing contract.** Lessons follow\n> [`_references\u002Fwriting-style.md`](..\u002F_references\u002Fwriting-style.md) in full. Because\n> lessons are always `en`, R1–R6 apply here whatever the fork's `output_language` is.\n> The mechanical checks follow the *project's* declared language, so in a non-`en` fork\n> this contract lives entirely in your judgment. Atomicity is this layer's own local\n> rule, Rule 3 below.\n\n1. **Write-once.** Never edit a lesson after `note`. Revise by writing a new one with\n   `--supersedes`; retire old ones only in bulk via `purge` on the archive.\n2. **One file per lesson**, named `YYYYMMDD_\u003Cslug>.md`; `id` = the stem.\n3. **One line, atomic.** The body is a single imperative (+ optional `Not:` \u002F example);\n   split anything compound into separate lessons.\n4. **`inspire_version` \u002F `template_sha` are frozen at capture** — the whole point is\n   knowing which release a lesson was based on.\n5. **No `status`, no `updated`.** Processing state lives centrally, keyed by `id` and\n   the date prefix — not inside the fork.\n6. **A lesson is about a skill, not the product.** Product work → `inspire-task`. Spike\n   \u002F prototype **learnings** are a different thing (product insight) — not lessons.\n7. **Concurrent captures are safe** — distinct filenames, no locking, no shared mutation.\n\n## Relationship to the tracker (`inspire-task`)\n\n`99_tracker` skill-feedback tickets and `98_lessons` nodes are two records for two\naudiences, and which signal goes where is the routing stated once in\n[`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md) § Ticket vs. lesson\n— applied above under *When to capture a lesson*.\n\nWhat this section owns is the **graduation**. A friction ticket the team has confirmed,\nand that should durably change how a skill behaves, becomes a lesson: the ticket keeps\ntracking the local fix, while the new lesson carries the instruction and links back\nwith a link to the ticket file (`[TASK-{id}](..\u002F99_tracker\u002Ftickets\u002FTASK-{id}.md)`). Both records stay: the ticket is the local work, and the lesson is\nwhat the skill learns from it — and, via the observer, what INSPIRE core may learn.\n\n## Related skills\n\n- The offer protocol the other skills follow lives in\n  [`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md) — they offer\n  `\u002Finspire-lesson note`; the operator decides.\n- `\u002Finspire-task` handles the local, closeable side of the same feedback signal.\n","# \u002Finspire-lesson — Lessons catalog\n\n## Scope\n\nThe **self-teaching layer** —\n`inspire_kb\u002F98_lessons`: **one Markdown file\nper lesson**, **write-once** (created once, never edited). A lesson is a durable,\ntransmissible instruction about how an `inspire-*` **skill itself** should behave —\nnot about the product. It can be *learned* or *taught*; the folder is a **catalog of\nlessons** this project holds.\n\nTwo audiences read the catalog:\n\n1. **This project, across releases** — the catalog is what keeps the agents behaving\n   as you taught them once a release moves the base underneath them. The flow that\n   writes lessons into a skill, and re-derives them against a new base, is **not\n   built**: an update leaves the catalog untouched, so applying a lesson to the\n   skills is the operator's until it exists. Capturing still pays now —\n   a lesson written today is one that flow will find.\n2. **INSPIRE core, via the observer** — an external pull-from-above reads the catalog\n   across many forks and distills the patterns worth folding into the next release.\n   The fork only ever **writes** lessons and is unaware of any central system.\n\nTwo properties keep the org-wide sweep cheap and safe:\n\n- **Timestamp-named** — files are `YYYYMMDD_\u003Cslug>.md`, so a sweep selects a date\n  range by comparing the first 8 characters, without opening a file.\n- **Write-once** — a file below the sweep's date cursor can never have changed, so it\n  is skipped forever; already-processed lessons are never re-worked.\n\nEvery lesson **freezes the INSPIRE version it was captured on** (from the root\n`.inspire.lock`), so the observer can tell whether a newer release already learned it.\n\nThe on-disk contract — naming, the one-line body format, write-once rules, frontmatter\nschema, enums, archive + purge semantics — lives in\n[`references\u002Flessons-format.md`](references\u002Flessons-format.md). **Read it before `note`\nor `purge`.**\n\n## What a lesson is\n\n- **One line, atomic.** The body is a single imperative — *\"When generating a NestJS\n  controller, keep DTOs in a separate file.\"* At most a positive\u002Fnegative pair (*do\n  this* \u002F *not that*), plus an optional **example as support only**. The one-line limit\n  *enforces* atomicity: you cannot pack two intents into one imperative without it\n  obviously being two lessons. This keeps the catalog small and every lesson easy to\n  reason about — and makes update-time reconciliation clean.\n- **Relevant here, not \"upstream-worthy.\"** You capture a lesson because it matters to\n  **you, in this project** — never because you have judged it generalizable. Whether it\n  generalizes is decided **upstream**, by the observer, from the pattern many forks'\n  lessons form. Capture asks only *\"is this worth keeping?\"*\n- **Materialized, not consulted.** The intent is that a lesson is written *into* the\n  skill so the taught behavior **becomes** the behavior — the agent acts on it, it does\n  not check a footnote and apply it if it happens to notice. The model is Terraform's\n  **desired state**: the lessons are the source of truth a run declares, and the skill\n  file is the result it reconciles to them.\n\n## When to capture a lesson\n\nRecord one when a session surfaces something **you want the skill to keep doing (or\nstop doing)**:\n\n- the operator corrects how a skill behaved, in a way that should stick;\n- a deliberate local change to how an `inspire-*` skill works;\n- a recurring friction — an `AskUserQuestion` that should have a default, a step that\n  always needs rework, drift from what the skill anticipated;\n- a house convention or preference the skill should honor;\n- a pattern the skill doesn't cover but should.\n\nIf the signal is **local, actionable work** (\"someone here should fix this\"), file a\nskill-feedback ticket with `inspire-task` instead. A confirmed ticket that should change\nhow a skill behaves graduates into a lesson (see *Relationship to the tracker*).\n\nA lesson is how a project overrides the **runtime** rung — it is the declared channel\nfor \"the skill should behave differently here\"\n([`_references\u002Fauthority.md`](..\u002F_references\u002Fauthority.md)). Where the departure binds\nthe product rather than the skill, it is an ADR or an artifact, not a lesson; and where\nwhat the project wants changed is something mechanical — a frontmatter schema, the\nkeyed-entry vocabulary, a lifecycle state, anything a validator or a parser reads — no\nproject artifact out-specifies it and a lesson is the **only** way in. It is the start\nof the path rather than the whole of it: a lesson teaches the *skills*, and the\nvalidators are not an extension point, so the change lands through the observer and a\nrelease.\n\n## Invocation\n\n- `\u002Finspire-lesson note {title} [--skill X --category preference --supersedes id]`\n- `\u002Finspire-lesson list [--since YYYYMMDD --until YYYYMMDD --skill X --category Z]` (read-only)\n- `\u002Finspire-lesson show {id}` (read-only)\n- `\u002Finspire-lesson purge [--months N | --before YYYYMMDD] [--confirm]`\n\n## Subcommand: note {title} [--flags]\n\n1. Resolve `@handle` from `git config user.email` (cached per session).\n2. Resolve today's date from CLAUDE.md `currentDate` or `date +%Y-%m-%d`.\n3. Read `inspire_version` + `template_sha` from `.inspire.lock` (repo root). If the\n   lock is absent (e.g. inside the template repo itself), fall back to\n   `plugin\u002F.claude-plugin\u002Fplugin.json`; else record `unknown` and warn.\n4. Build the filename `YYYYMMDD_\u003Cslug>.md`, where `\u003Cslug>` is a kebab-case short form\n   of the title (~40 chars). Several lessons may share a date — the slug keeps each\n   name distinct; pick a more specific slug if one would collide. `id` = the filename\n   stem.\n5. Apply flags: `--skill` (required — the skill the lesson teaches, or `runtime` for\n   cross-cutting \u002F methodology), `--category` (default `preference`), `--supersedes`\n   (id of an earlier lesson this revises).\n6. **Draft the one-line instruction with the operator and confirm it.** Keep it to a\n   single imperative; add the optional `Not:` negative and a `> Example:` support line\n   only if they genuinely help. Write the file **once** — frontmatter + the one-line\n   body (see [`references\u002Flessons-format.md`](references\u002Flessons-format.md)).\n7. Print the new id to stdout.\n\n> **Write-once.** After `note`, never edit the file. To revise, write a new lesson with\n> `--supersedes {old-id}`; the old one stays untouched.\n\n## Subcommand: list [--filter]\n\n1. Scan `inspire_kb\u002F98_lessons\u002F*.md` (the live catalog; `--archived` also scans\n   `98_lessons\u002Farchive\u002F`).\n2. `--since` \u002F `--until` filter on the **filename date prefix** (cheap — no frontmatter\n   read). `--skill` \u002F `--category` \u002F `--reporter` filter on frontmatter.\n3. Print a compact table to stdout: `date | category | skill | version | instruction`.\n4. Read-only.\n\n## Subcommand: show {id}\n\nRead the file and print frontmatter + body. Read-only.\n\n## Subcommand: purge [--months N | --before YYYYMMDD] [--confirm]\n\nLocal housekeeping — delete **archived** lessons (those the base has already learned,\nunder `98_lessons\u002Farchive\u002F`) older than a threshold (default `--months 6`), matched on\nthe **filename date prefix**. **Dry-run by default**: list exactly which files would be\nremoved and stop. Delete only when the operator passes `--confirm` (or approves in the\nconversation). Purge is **fully optional** — the archive is durable provenance, and\ndeleted files remain recoverable from git history. Purge only ever removes whole files;\nit never edits one, so the write-once contract holds. (Until the update flow exists,\n`archive\u002F` is empty and purge is a no-op — archiving is populated by an update.)\n\n## Rules\n\n> **Output language — the one exception.** Lessons are authored in **English**,\n> whatever the project's `output_language` is: their reader is the observer \u002F the\n> cross-org INSPIRE core team, not the product team. Everything else in\n> [`_references\u002Foutput-language.md`](..\u002F_references\u002Foutput-language.md) still holds —\n> machine-read tokens stay verbatim.\n\n> **Writing contract.** Lessons follow\n> [`_references\u002Fwriting-style.md`](..\u002F_references\u002Fwriting-style.md) in full. Because\n> lessons are always `en`, R1–R6 apply here whatever the fork's `output_language` is.\n> The mechanical checks follow the *project's* declared language, so in a non-`en` fork\n> this contract lives entirely in your judgment. Atomicity is this layer's own local\n> rule, Rule 3 below.\n\n1. **Write-once.** Never edit a lesson after `note`. Revise by writing a new one with\n   `--supersedes`; retire old ones only in bulk via `purge` on the archive.\n2. **One file per lesson**, named `YYYYMMDD_\u003Cslug>.md`; `id` = the stem.\n3. **One line, atomic.** The body is a single imperative (+ optional `Not:` \u002F example);\n   split anything compound into separate lessons.\n4. **`inspire_version` \u002F `template_sha` are frozen at capture** — the whole point is\n   knowing which release a lesson was based on.\n5. **No `status`, no `updated`.** Processing state lives centrally, keyed by `id` and\n   the date prefix — not inside the fork.\n6. **A lesson is about a skill, not the product.** Product work → `inspire-task`. Spike\n   \u002F prototype **learnings** are a different thing (product insight) — not lessons.\n7. **Concurrent captures are safe** — distinct filenames, no locking, no shared mutation.\n\n## Relationship to the tracker (`inspire-task`)\n\n`99_tracker` skill-feedback tickets and `98_lessons` nodes are two records for two\naudiences, and which signal goes where is the routing stated once in\n[`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md) § Ticket vs. lesson\n— applied above under *When to capture a lesson*.\n\nWhat this section owns is the **graduation**. A friction ticket the team has confirmed,\nand that should durably change how a skill behaves, becomes a lesson: the ticket keeps\ntracking the local fix, while the new lesson carries the instruction and links back\nwith a link to the ticket file (`[TASK-{id}](..\u002F99_tracker\u002Ftickets\u002FTASK-{id}.md)`). Both records stay: the ticket is the local work, and the lesson is\nwhat the skill learns from it — and, via the observer, what INSPIRE core may learn.\n\n## Related skills\n\n- The offer protocol the other skills follow lives in\n  [`_references\u002Flesson-capture.md`](..\u002F_references\u002Flesson-capture.md) — they offer\n  `\u002Finspire-lesson note`; the operator decides.\n- `\u002Finspire-task` handles the local, closeable side of the same feedback signal.\n",{"name":5,"description":7},"main","bf5124558fc1203b1fe5aea2d2ae38cfba34939b","plugin\u002Fbase\u002Fskills\u002Finspire-lesson",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-lesson",{"tool":38,"command":39},"bunx","bunx skills add Genomcore\u002Finspire --skill inspire-lesson",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Genomcore\u002Finspire --skill inspire-lesson","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-lesson\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Flessons-format.md","REFERENCE","参考文档",7405,"https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-lesson\u002Freferences\u002Flessons-format.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M79DM28JSC3GWEJ82346VGW6","inspire-workspace","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.","https:\u002F\u002Fgithub.com\u002FGenomcore\u002Finspire\u002Fblob\u002Fmain\u002Fplugin\u002Fbase\u002Fskills\u002Finspire-workspace\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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",[],[]]