[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71B5CNJAH2ZPZWMXPKZEDRG":3,"skill-same:01M71B5CNJAH2ZPZWMXPKZEDRG":72},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M71B5CNJAH2ZPZWMXPKZEDRG","bmad-extract-lessons-from-adrs",null,"Mine architecture decision records (ADRs), gotcha files, runbooks, and docs\u002Farchive for cross-project lessons that warrant ai-playbook canonical specs. Use when a project lacks a populated retros\u002F directory but has equivalent material in other forms.","Wizarck\u002Fnexandro","Wizarck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23051550?v=4","01M71B3AAVR67GRWFV5ZXXZP31","arturo6ramirez","01M71B3ABYG1BFNXHX4KZ3PPK6",2,"MIT","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fbmad-extract-lessons-from-adrs\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"bmad","bmad extract lessons from adrs","extract","lessons","directory","architecture decision","architecture","when","access","use","files","material","decision","runbooks","archive","records","project","for","mine","tree","2026-11-10 10:12:30",false,"---\nname: bmad-extract-lessons-from-adrs\ndescription: Mine architecture decision records (ADRs), gotcha files, runbooks, and docs\u002Farchive for cross-project lessons that warrant ai-playbook canonical specs. Use when a project lacks a populated retros\u002F directory but has equivalent material in other forms.\nlicense: MIT\ncompatibility: Requires read access to the consumer's docs tree; emits a structured lessons digest.\nmetadata:\n  author: ai-playbook\n  version: \"1.0\"\n  generatedBy: \"0.11.0\"\n---\n\n# bmad-extract-lessons-from-adrs\n\nMine alternative retro-equivalent surfaces (ADRs, gotchas, runbooks, post-mortems, docs\u002Farchive) for cross-project patterns that warrant inclusion in the next ai-playbook release.\n\n## When to use\n\nUse this skill when:\n\n- A project has **no populated `retros\u002F` directory** but has an extensive ADR set (e.g. `consumer-d` with 28 ADRs).\n- A project has retros but they're **terse \u002F project-specific** and you want a second pass against alternative surfaces.\n- You're authoring an `ai-playbook` release that consolidates cross-project lessons (e.g. v0.11.0) and want to verify coverage across all consumers.\n\nDon't use when:\n\n- The project has comprehensive retros that already capture the lessons (e.g. `consumer-e\u002Fretros\u002F` after Wave 3 — read those directly).\n- You want a quick lookup for a specific topic (just `Grep` the relevant directory).\n\n## Inputs\n\n- **Consumer project root** (cwd or explicit path).\n- **Optional**: a \"filter focus\" — a topic to bias the mining toward (e.g. \"DI patterns\", \"secret rotation\", \"cascade failures\"). If absent, the skill returns broad coverage.\n\n## Mining strategy\n\nThe skill walks the consumer's docs tree in this order, sampling each surface for retro-equivalent content:\n\n### 1. ADRs\n\nPath: `decisions\u002F`, `docs\u002Fadr\u002F`, `architecture\u002Fdecisions\u002F` (whichever exists).\n\nRead each ADR's:\n- \"Context\" \u002F \"Problem\" sections — usually contains the failure mode that motivated the decision.\n- \"Why NOT X\" \u002F \"Rejected alternatives\" sections — the lessons-learned of approaches that failed.\n- \"Consequences\" section — the durable trade-off the team accepted.\n\nSkip ADRs about pure tech selection (e.g. \"ADR-009: PostgreSQL over MySQL\") unless the rationale section lists incident-driven motivations.\n\n### 2. Gotchas\n\nPath: `gotchas.md`, `docs\u002Fgotchas.md`, or per-bounded-context `\u003Cbc>\u002Fgotchas.md`.\n\nEach gotcha is implicitly a one-line postmortem. Read the *why* (often only 1-2 sentences); cross-reference if it recurs in other surfaces.\n\n### 3. Runbooks\n\nPath: `runbooks\u002F`, `docs\u002Frunbooks\u002F`.\n\nFilter by name patterns suggesting incident response:\n- `runbook-*-down-*.md`\n- `runbook-*-cascade.md`\n- `runbook-*-recovery.md`\n- `runbook-*-emergency.md`\n\nRead these for cascade graphs + failure-mode taxonomies.\n\n### 4. docs\u002Farchive (or equivalent)\n\nPath: `docs\u002Farchive\u002F`, `docs\u002F_archived\u002F`, `archive\u002F`.\n\nLook for files with audit \u002F TODO \u002F context titles:\n- `*-AUDIT.md` — security audits, often containing concrete incident chains.\n- `TODO-*.md` — abandoned features (the *why* abandoned is the lesson).\n- `CONTEXT.md` — historical decisions written when memory was fresh.\n\n### 5. CHANGELOGs\n\nPath: `CHANGELOG.md`, `.ai-playbook\u002FCHANGELOG.md`.\n\nLook for notes on hotfixes \u002F rollbacks. Pattern: a sequence of small patch releases close in time (`v0.10.0 → v0.10.1 → v0.10.2` within a week) usually means real-world gaps surfaced post-merge — extract the gap.\n\n### 6. Postmortems (if present)\n\nPath: `docs\u002Fpostmortems\u002F`, `postmortems\u002F`.\n\nThese are the canonical retro surface; read each entirely.\n\n## Output structure\n\nEmit a structured digest as a single markdown document:\n\n```markdown\n# Lessons mined from \u003Cproject> — \u003CYYYY-MM-DD>\n\n> Source surfaces walked:\n> - decisions\u002F (N files read)\n> - gotchas.md (M lines read)\n> - runbooks\u002F (P files read)\n> - docs\u002Farchive\u002F (Q files read)\n> - postmortems\u002F (R files read; or \"none present\")\n\n## Cross-project patterns (recurring; warrant ai-playbook canonical spec)\n\n### Pattern: \u003Cname>\n- **Severity**: HIGH \u002F MED \u002F LOW\n- **Sources**: \u003CADR-N>, \u003Cgotcha-line>, \u003Crunbook>\n- **Symptom**: one sentence\n- **Suggested ai-playbook deliverable**: spec \u002F skill \u002F runbook \u002F template\n\n## Project-specific patterns (informational; NOT for ai-playbook)\n\n- \u003Cpattern>: \u003Cone-line summary>; reason it's project-specific.\n\n## Surfaces NOT walked (if any)\n\n- \u003Csurface>: skipped because \u003Creason>.\n```\n\nConstraint: the output is **never written automatically** to `\u003Cproject>\u002Fretros\u002F`. The operator decides which patterns to keep + where they land. The skill emits to stdout \u002F a transient file; the operator copies what they want.\n\n## Steps\n\n1. **Locate the project root** — cwd unless explicitly provided.\n2. **Walk surface 1 (ADRs)** — list ADR files, sample each (read first 50 lines + grep for \"incident\" \u002F \"outage\" \u002F \"broke\" \u002F \"failed\" \u002F \"rolled back\" \u002F \"rejected because\"). Tag findings with the ADR number.\n3. **Walk surface 2 (gotchas)** — read fully (gotcha files are typically \u003C100 lines). Tag findings with line numbers.\n4. **Walk surface 3 (runbooks)** — list runbook files, filter by incident-pattern names, sample each.\n5. **Walk surface 4 (docs\u002Farchive)** — list files, sample those with audit\u002FTODO\u002Fcontext titles.\n6. **Walk surface 5 (CHANGELOGs)** — read; flag patch-release sequences.\n7. **Walk surface 6 (postmortems)** — read all if present.\n8. **Cross-reference** — patterns appearing in ≥2 surfaces become \"recurring\" candidates; one-source patterns become \"project-specific\".\n9. **Write the digest** per the output schema above.\n10. **Show the digest to the operator** + suggest next steps (which patterns to promote, which to defer).\n\n## Fluid workflow integration\n\nThis skill pairs with:\n\n- **`bmad-retrospective`** — when the project has `retros\u002F`, prefer that; this skill is for projects without retros.\n- **`openspec-propose`** for an ai-playbook release — after mining, the recurring patterns become draft `proposal.md` content.\n- **`bmad-distillator`** — sister skill that consolidates BMAD planning artefacts; this skill consolidates post-implementation lessons.\n\n## Anti-patterns\n\n- **Auto-writing to `\u003Cproject>\u002Fretros\u002F`**: forbidden. The operator's project doesn't necessarily want a synthesised retro; let them decide.\n- **Skipping CHANGELOG on the assumption it's purely descriptive**: forbidden. Patch-release cadence is a strong signal.\n- **Treating every \"Rejected alternative\" in an ADR as a lesson**: avoid. Some are simple \"didn't fit\" with no incident behind them; keep the lesson list to incident-driven rejections.\n- **Promoting a pattern based on one surface**: forbidden. Cross-project canonical specs need ≥2 surfaces (within or across projects).\n\n## Reference invocation\n\n```\n\u002Fbmad-extract-lessons-from-adrs\n\n# With filter focus:\n\u002Fbmad-extract-lessons-from-adrs --focus=\"cascade failures\"\n\n# Against a specific project (when cwd is elsewhere):\n\u002Fbmad-extract-lessons-from-adrs --project=\u002Fpath\u002Fto\u002Fconsumer-d\n```\n\n## Validation\n\nThe skill is validated by reproducing the v0.11.0 mining session:\n\n1. Ran against `consumer-d` (28 ADRs + gotchas.md + 19 runbooks).\n2. Ran against `consumer-b` (no ADRs; docs\u002Farchive only).\n3. Output: 3 NEW patterns + 2 reinforced patterns vs the prior consumer-e+consumer-c baseline. Direct input to v0.11.0 specs `multi-layer-defense-single-operator.md`, `cascade-failure-template.md`, and the HITL section in `hitl-approval-pattern.md`.\n\nEach subsequent ai-playbook release SHOULD invoke this skill against every consumer in [`consumers.yaml`](..\u002F..\u002Fconsumers.yaml) where `retros\u002F` is empty.\n","# bmad-extract-lessons-from-adrs\n\nMine alternative retro-equivalent surfaces (ADRs, gotchas, runbooks, post-mortems, docs\u002Farchive) for cross-project patterns that warrant inclusion in the next ai-playbook release.\n\n## When to use\n\nUse this skill when:\n\n- A project has **no populated `retros\u002F` directory** but has an extensive ADR set (e.g. `consumer-d` with 28 ADRs).\n- A project has retros but they're **terse \u002F project-specific** and you want a second pass against alternative surfaces.\n- You're authoring an `ai-playbook` release that consolidates cross-project lessons (e.g. v0.11.0) and want to verify coverage across all consumers.\n\nDon't use when:\n\n- The project has comprehensive retros that already capture the lessons (e.g. `consumer-e\u002Fretros\u002F` after Wave 3 — read those directly).\n- You want a quick lookup for a specific topic (just `Grep` the relevant directory).\n\n## Inputs\n\n- **Consumer project root** (cwd or explicit path).\n- **Optional**: a \"filter focus\" — a topic to bias the mining toward (e.g. \"DI patterns\", \"secret rotation\", \"cascade failures\"). If absent, the skill returns broad coverage.\n\n## Mining strategy\n\nThe skill walks the consumer's docs tree in this order, sampling each surface for retro-equivalent content:\n\n### 1. ADRs\n\nPath: `decisions\u002F`, `docs\u002Fadr\u002F`, `architecture\u002Fdecisions\u002F` (whichever exists).\n\nRead each ADR's:\n- \"Context\" \u002F \"Problem\" sections — usually contains the failure mode that motivated the decision.\n- \"Why NOT X\" \u002F \"Rejected alternatives\" sections — the lessons-learned of approaches that failed.\n- \"Consequences\" section — the durable trade-off the team accepted.\n\nSkip ADRs about pure tech selection (e.g. \"ADR-009: PostgreSQL over MySQL\") unless the rationale section lists incident-driven motivations.\n\n### 2. Gotchas\n\nPath: `gotchas.md`, `docs\u002Fgotchas.md`, or per-bounded-context `\u003Cbc>\u002Fgotchas.md`.\n\nEach gotcha is implicitly a one-line postmortem. Read the *why* (often only 1-2 sentences); cross-reference if it recurs in other surfaces.\n\n### 3. Runbooks\n\nPath: `runbooks\u002F`, `docs\u002Frunbooks\u002F`.\n\nFilter by name patterns suggesting incident response:\n- `runbook-*-down-*.md`\n- `runbook-*-cascade.md`\n- `runbook-*-recovery.md`\n- `runbook-*-emergency.md`\n\nRead these for cascade graphs + failure-mode taxonomies.\n\n### 4. docs\u002Farchive (or equivalent)\n\nPath: `docs\u002Farchive\u002F`, `docs\u002F_archived\u002F`, `archive\u002F`.\n\nLook for files with audit \u002F TODO \u002F context titles:\n- `*-AUDIT.md` — security audits, often containing concrete incident chains.\n- `TODO-*.md` — abandoned features (the *why* abandoned is the lesson).\n- `CONTEXT.md` — historical decisions written when memory was fresh.\n\n### 5. CHANGELOGs\n\nPath: `CHANGELOG.md`, `.ai-playbook\u002FCHANGELOG.md`.\n\nLook for notes on hotfixes \u002F rollbacks. Pattern: a sequence of small patch releases close in time (`v0.10.0 → v0.10.1 → v0.10.2` within a week) usually means real-world gaps surfaced post-merge — extract the gap.\n\n### 6. Postmortems (if present)\n\nPath: `docs\u002Fpostmortems\u002F`, `postmortems\u002F`.\n\nThese are the canonical retro surface; read each entirely.\n\n## Output structure\n\nEmit a structured digest as a single markdown document:\n\n```markdown\n# Lessons mined from \u003Cproject> — \u003CYYYY-MM-DD>\n\n> Source surfaces walked:\n> - decisions\u002F (N files read)\n> - gotchas.md (M lines read)\n> - runbooks\u002F (P files read)\n> - docs\u002Farchive\u002F (Q files read)\n> - postmortems\u002F (R files read; or \"none present\")\n\n## Cross-project patterns (recurring; warrant ai-playbook canonical spec)\n\n### Pattern: \u003Cname>\n- **Severity**: HIGH \u002F MED \u002F LOW\n- **Sources**: \u003CADR-N>, \u003Cgotcha-line>, \u003Crunbook>\n- **Symptom**: one sentence\n- **Suggested ai-playbook deliverable**: spec \u002F skill \u002F runbook \u002F template\n\n## Project-specific patterns (informational; NOT for ai-playbook)\n\n- \u003Cpattern>: \u003Cone-line summary>; reason it's project-specific.\n\n## Surfaces NOT walked (if any)\n\n- \u003Csurface>: skipped because \u003Creason>.\n```\n\nConstraint: the output is **never written automatically** to `\u003Cproject>\u002Fretros\u002F`. The operator decides which patterns to keep + where they land. The skill emits to stdout \u002F a transient file; the operator copies what they want.\n\n## Steps\n\n1. **Locate the project root** — cwd unless explicitly provided.\n2. **Walk surface 1 (ADRs)** — list ADR files, sample each (read first 50 lines + grep for \"incident\" \u002F \"outage\" \u002F \"broke\" \u002F \"failed\" \u002F \"rolled back\" \u002F \"rejected because\"). Tag findings with the ADR number.\n3. **Walk surface 2 (gotchas)** — read fully (gotcha files are typically \u003C100 lines). Tag findings with line numbers.\n4. **Walk surface 3 (runbooks)** — list runbook files, filter by incident-pattern names, sample each.\n5. **Walk surface 4 (docs\u002Farchive)** — list files, sample those with audit\u002FTODO\u002Fcontext titles.\n6. **Walk surface 5 (CHANGELOGs)** — read; flag patch-release sequences.\n7. **Walk surface 6 (postmortems)** — read all if present.\n8. **Cross-reference** — patterns appearing in ≥2 surfaces become \"recurring\" candidates; one-source patterns become \"project-specific\".\n9. **Write the digest** per the output schema above.\n10. **Show the digest to the operator** + suggest next steps (which patterns to promote, which to defer).\n\n## Fluid workflow integration\n\nThis skill pairs with:\n\n- **`bmad-retrospective`** — when the project has `retros\u002F`, prefer that; this skill is for projects without retros.\n- **`openspec-propose`** for an ai-playbook release — after mining, the recurring patterns become draft `proposal.md` content.\n- **`bmad-distillator`** — sister skill that consolidates BMAD planning artefacts; this skill consolidates post-implementation lessons.\n\n## Anti-patterns\n\n- **Auto-writing to `\u003Cproject>\u002Fretros\u002F`**: forbidden. The operator's project doesn't necessarily want a synthesised retro; let them decide.\n- **Skipping CHANGELOG on the assumption it's purely descriptive**: forbidden. Patch-release cadence is a strong signal.\n- **Treating every \"Rejected alternative\" in an ADR as a lesson**: avoid. Some are simple \"didn't fit\" with no incident behind them; keep the lesson list to incident-driven rejections.\n- **Promoting a pattern based on one surface**: forbidden. Cross-project canonical specs need ≥2 surfaces (within or across projects).\n\n## Reference invocation\n\n```\n\u002Fbmad-extract-lessons-from-adrs\n\n# With filter focus:\n\u002Fbmad-extract-lessons-from-adrs --focus=\"cascade failures\"\n\n# Against a specific project (when cwd is elsewhere):\n\u002Fbmad-extract-lessons-from-adrs --project=\u002Fpath\u002Fto\u002Fconsumer-d\n```\n\n## Validation\n\nThe skill is validated by reproducing the v0.11.0 mining session:\n\n1. Ran against `consumer-d` (28 ADRs + gotchas.md + 19 runbooks).\n2. Ran against `consumer-b` (no ADRs; docs\u002Farchive only).\n3. Output: 3 NEW patterns + 2 reinforced patterns vs the prior consumer-e+consumer-c baseline. Direct input to v0.11.0 specs `multi-layer-defense-single-operator.md`, `cascade-failure-template.md`, and the HITL section in `hitl-approval-pattern.md`.\n\nEach subsequent ai-playbook release SHOULD invoke this skill against every consumer in [`consumers.yaml`](..\u002F..\u002Fconsumers.yaml) where `retros\u002F` is empty.\n",{"name":5,"license":15,"metadata":44,"description":7,"compatibility":48},{"author":45,"version":46,"generatedBy":47},"ai-playbook","1.0","0.11.0","Requires read access to the consumer's docs tree; emits a structured lessons digest.","master","f57cddf3a79f076c1bb1ba9c187850fba797c0c9","skills\u002Fbmad-extract-lessons-from-adrs",1,"https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro","https:\u002F\u002Fgithub.com\u002FWizarck","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Framirezarturo\u002F","Geek by birth, with not much to say but plenty to talk about.","2026-09-25 20:04:26",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Wizarck\u002Fnexandro --skill bmad-extract-lessons-from-adrs",{"tool":64,"command":65},"bunx","bunx skills add Wizarck\u002Fnexandro --skill bmad-extract-lessons-from-adrs",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Wizarck\u002Fnexandro --skill bmad-extract-lessons-from-adrs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fbmad-extract-lessons-from-adrs\u002FSKILL.md",true,[],[73,106,135,158,172,198],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":90,"publishedAt":39},"01M71BBM78XJY2YXFXJ2YNCEGY","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files into proper spreadsheets.","AGPL-3.0","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fxlsx\u002FSKILL.md",[80,85],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[75,91,92,93,36,94,95,96,97,98,99,100,29,28,101,26,102,103,104,105],"sources","tsv","by name","spreadsheet","time","trigger","fix","scratch","open","new","Existing","done","convert","file","tabular",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":118,"publishedAt":39},"01M71BBGZJG2FKCPJZWR32SCZ5","use-case-research","Creates JTBD-aligned Use Cases CSVs through structured user interviews, parallel vendor\u002Findustry research, and Jobs-to-be-Done synthesis. Generates 17-column CSV (OFFER-001 format) and validates with \u002Fqa-use-cases. Use when creating or updating use case research for an offering.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fuse-case-research\u002FSKILL.md",[112,115],{"categoryNo":113,"categoryName":114,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":116,"categoryName":117,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发",[119,28,120,121,122,123,124,125,26,102,126,127,128,129,130,131,132,133,36,134],"use case research","case","research","industry research","user interviews","qa","jtbd","Bash","websearch","read","write","edit","interviews","opus","parallel","true",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":39},"01M71BBCCGXCBJZSYK72CT7MJW","sync-jira","Two-way sync between PROGRESS.md pipeline status and JIRA CIT tasks. Use when syncing offering progress with JIRA, checking JIRA status, bootstrapping JIRA tasks for new offerings, or pushing\u002Fpulling status updates. Also use when the user mentions JIRA, CIT tasks, or pipeline sync.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fsync-jira\u002FSKILL.md",[141],{"categoryNo":116,"categoryName":117,"taxonomyType":83,"taxonomyTypeDesc":84},[143,144,145,146,147,36,148,149,100,150,28,26,151,126,152,153,154,155,156,157],"sync jira","jira","sync","pull","push","pipeline","status updates","MCP","updates","tasks","bootstrap","dry","two","with","id",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":39},"01M71BBAV2F4ABBVAM9FMZ692C","strategy","Tunes business strategy and aligns with corporate ABC Goals. Use when working on 01_BS\u002F business strategy files.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstrategy\u002FSKILL.md",[164],{"categoryNo":116,"categoryName":117,"taxonomyType":83,"taxonomyTypeDesc":84},[160,134,29,28,166,26,156,157,167,168,128,129,130,169,170,171],"business","goals","business strategy","corporate","grep","sonnet",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":182,"publishedAt":39},"01M71BB6N1EJDAMAWAF0FSGFRR","start","Starts the full MCP stack: LiteLLM proxy + Docker services (Hindsight, Atlassian, Google Workspace) + skills-manager + notebooklm. All services connect directly — no proxy. Use \u002Fstart at the beginning of any session where MCP tools are needed, or when any service is stopped. LiteLLM must start before Docker — Hindsight depends on it at startup.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstart\u002FSKILL.md",[178,181],{"categoryNo":179,"categoryName":180,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":116,"categoryName":117,"taxonomyType":83,"taxonomyTypeDesc":84},[174,183,184,185,186,187,188,150,28,189,26,126,190,191,192,193,194,195,196,197],"hindsight","google workspace","proxy","docker","session","litellm","connect","stack","haiku","services","workspace","at","notebooklm","google","startup",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":39},"01M71BB50307CW202PCTECJ3BB","start-palafito","Úsalo cuando el usuario quiere arrancar el stack palafito-prod (Paperclip) y, si hace falta, levantar Docker Desktop antes.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstart-palafito\u002FSKILL.md",[204],{"categoryNo":179,"categoryName":180,"taxonomyType":83,"taxonomyTypeDesc":84},[174,206,190,207,208,209,126,186,171],"start palafito","desktop","fork","paperclip"]