[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71MVNP802E7FD6W7WBBFR7G":3,"skill-same:01M71MVNP802E7FD6W7WBBFR7G":89},{"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":15,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M71MVNP802E7FD6W7WBBFR7G","deep-research",null,"Use when a high-stakes question needs an auditable multi-source investigation: falsifiable hypotheses, parallel sub-agent search, triangulation and critique. Produces a sourced research folder with refresh targets; not for quick overviews or market sizing (see market-research).","monoes\u002Fmonomind","monoes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F276744696?v=4","01M71KWF37AJ2NJBP3KWBVSDGT","01M71KWF4CSF8ADH0M6HA09VD2",23,"MIT","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fdeep-research\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fdeep-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"deep research","research","deep","multi","with","market sizing","Market","use","for","planning","parallel","source","sub-agent","critique","when","question","market-research","search","claude-skills","quick","2026-11-10 10:56:23",false,"---\nname: deep-research\ndescription: \"Use when a high-stakes question needs an auditable multi-source investigation: falsifiable hypotheses, parallel sub-agent search, triangulation and critique. Produces a sourced research folder with refresh targets; not for quick overviews or market sizing (see market-research).\"\ntags: [\"research\",\"agents\",\"planning\"]\ntools: []\nlicense: MIT\nsource: https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills\nsource_path: \"research\u002Fdeep-research\u002Fskills\u002Fdeep-research\"\nsource_commit: 19392f7a08264ed00486a251f5b2098321771f94\n---\n# Deep Research — Disciplined Meta-Research\n\nTurn \"research this topic\" into an auditable, reusable investigation instead of a one-shot wall of text. The output is a folder you can return to in a month: every claim traces to a specific source file, the plan documents *why* each choice was made, and a refresh protocol lets you update it later without re-running everything.\n\n**This is the heavy, methodical end of research.** It is not a fast overview — it is the workflow you reach for when getting the answer *wrong* costs more than the tokens spent getting it right.\n\n## How it differs from a quick research router\n\nA router-style research skill (keyword-classify → delegate → short sequential search → markdown brief) is optimal when you need an answer fast and the decision risk is low. `deep-research` is the opposite trade: it pays for rigor. Use it when the answer feeds a strategy, an irreversible decision, a published artifact, or a hypothesis you need to actually test — situations where a shallow fallback would be a liability.\n\nConcretely, `deep-research` adds what a fast overview does not: falsifiable hypotheses up front, parallel sub-agent fan-out across many channels, triangulation with explicit source-type diversity, a mandatory adversarial pass, per-source files with verbatim quotes, and a `refresh_targets.md` for delta-updates later.\n\n## The pipeline (9 phases)\n\nDepth scales with the task — `shallow` runs the core phases inline; `medium`\u002F`deep` add capability discovery, verification, and refresh targets.\n\n| # | Phase | What it does |\n|---|-------|--------------|\n| 1 | **Reframe** | Rewrite the question, fix the underlying decision, state 2–4 *falsifiable* hypotheses |\n| 2 | **Genre & blocks** | Pick the report genre (qa \u002F explainer \u002F decision \u002F landscape \u002F validation \u002F custom) and its building blocks |\n| 3 | **Plan** | Write `plan.md`: scope, structure, sourcing strategy, opposition queries, risk register, stop-criteria |\n| 3.5 | **Capability discovery** | Audit available API keys\u002Fchannels in the environment; map subtopics to sources; fall back to HTML where needed |\n| 4 | **Search** (loop) | Dispatch sources → launch sub-agents in parallel → fetch & dedup → save each to `sources\u002FNN.md`; re-evaluate between rounds |\n| 5 | **Score & triangulate** | Rate every source on Credibility \u002F Recency \u002F Bias; require ≥3 independent, differently-typed sources per thesis |\n| 6 | **Synthesize + adversarial** | Assemble the report from blocks, run 4 self-critique questions, add steel-manned counter-arguments |\n| 6.5 | **Verify** | Lightweight citation check before closing |\n| 7 | **Refresh targets** | Extract entities \u002F numbers \u002F hypotheses into `refresh_targets.md` — the entry point for future updates |\n\n## Core mechanisms\n\nThese are what separate a documented investigation from a confident guess:\n\n- **Triangulation.** Every thesis must be backed by ≥3 independent sources of *different types* (primary \u002F academic \u002F industry \u002F discussion). A claim with fewer is flagged \"insufficient evidence,\" not stated as fact.\n- **Source-grounding.** Each source becomes its own `sources\u002FNN_slug.md` with metadata, verbatim quotes, and scores. No dangling claim — every assertion links back to a specific file. An empty fetch produces an empty claim, never a fabricated citation.\n- **Adversarial pass.** Phase 6 always runs the strongest available reasoning: 4 self-critique questions plus an active search for counter-arguments and disconfirming evidence.\n- **Falsifiable hypotheses.** Phase 1 commits to 2–4 hypotheses; Phases 5–6 explicitly confirm or refute each against the evidence, or mark it under-determined.\n- **Parallel sub-agents.** Phase 4 launches search sub-agents concurrently (cheap models for broad web sweeps, stronger ones for reasoning-heavy subtopics) — never one-at-a-time.\n- **Refresh protocol.** Phase 7 emits `refresh_targets.md`; an `update \u003Cslug>` run produces a delta (new entrants, entity changes, refreshed numbers, adversarial triggers) instead of replaying the whole investigation.\n- **Atomic findings.** Reusable theses in `findings\u002FFN.md` plus a `sources.csv` index — research compounds across questions instead of starting from zero each time.\n\n## Output structure\n\n```\n\u003Croot>\u002F\u003Cslug>\u002F\n├── plan.md                  # scope, sourcing strategy, risk register, changelog\n├── sources.csv              # index of every source with scores\n├── sources\u002F\n│   ├── 01_\u003Cslug>.md         # one file = one source (metadata + verbatim quotes)\n│   └── ...\n├── findings\u002F                # atomic, reusable theses (larger investigations)\n│   └── F1_\u003Cshort>.md\n├── refresh_targets.md       # what to watch on update (medium\u002Fdeep)\n├── diffs\u002F\n│   └── YYYY-MM-DD_delta.md   # delta from an `update \u003Cslug>` run\n└── YYYY-MM-DD_\u003Cgenre>.md     # final report\n```\n\n## When to use\n\n- A low-quality answer is expensive: strategy, business plan, report, or article groundwork.\n- Comparing N institutions, products, methodologies, or markets and you need defensible reasoning.\n- Validating a hypothesis or a decision against external data.\n- Meta-research: \"understand how X works,\" \"map the landscape of Y,\" answering a connected series of questions.\n\n## Anti-Patterns\n\n- **Don't skip the existing-work check.** Before searching, see whether the answer is already in the project or in a prior research folder — you risk re-researching something you already have.\n- **Don't skip reframing**, even when the request \"seems clear.\" The decision behind the question usually changes the search.\n- **Don't output to chat only.** Always persist sources and the report to files — the reuse value is in the folder, not the transcript.\n- **Don't fabricate citations.** If a fetch returns nothing, the claim is empty — never invent a plausible URL. Bind every claim to a saved verbatim quote.\n- **Don't build conclusions on a thin corpus.** Too few sources, or sources that all share one type, means triangulation hasn't happened — say so rather than overstating confidence.\n- **Don't skip the adversarial pass** on medium\u002Fdeep investigations. Confirmation-only research is the failure mode this skill exists to prevent.\n- **Don't run sub-agents sequentially.** Fan-out in parallel; serial search wastes the wall-clock advantage.\n- **Don't collapse `sources\u002F` into one file.** Per-source files are what make findings searchable and reusable across investigations.\n- **Don't pick the heaviest model for everything.** Match model to subtask — cheap for broad sweeps, strong for synthesis and the adversarial pass.\n\n## Cross-References\n\n- **research router** — for fast topic overviews where decision risk is low; `deep-research` is the heavyweight alternative when rigor matters more than speed.\n- **competitive-teardown** — for comparing N competitors on a structured 12-dimension matrix.\n- **litreview \u002F dossier \u002F patent** — domain specialists when the investigation is narrowly academic, person\u002Fcompany-focused, or patent-focused.\n","# Deep Research — Disciplined Meta-Research\n\nTurn \"research this topic\" into an auditable, reusable investigation instead of a one-shot wall of text. The output is a folder you can return to in a month: every claim traces to a specific source file, the plan documents *why* each choice was made, and a refresh protocol lets you update it later without re-running everything.\n\n**This is the heavy, methodical end of research.** It is not a fast overview — it is the workflow you reach for when getting the answer *wrong* costs more than the tokens spent getting it right.\n\n## How it differs from a quick research router\n\nA router-style research skill (keyword-classify → delegate → short sequential search → markdown brief) is optimal when you need an answer fast and the decision risk is low. `deep-research` is the opposite trade: it pays for rigor. Use it when the answer feeds a strategy, an irreversible decision, a published artifact, or a hypothesis you need to actually test — situations where a shallow fallback would be a liability.\n\nConcretely, `deep-research` adds what a fast overview does not: falsifiable hypotheses up front, parallel sub-agent fan-out across many channels, triangulation with explicit source-type diversity, a mandatory adversarial pass, per-source files with verbatim quotes, and a `refresh_targets.md` for delta-updates later.\n\n## The pipeline (9 phases)\n\nDepth scales with the task — `shallow` runs the core phases inline; `medium`\u002F`deep` add capability discovery, verification, and refresh targets.\n\n| # | Phase | What it does |\n|---|-------|--------------|\n| 1 | **Reframe** | Rewrite the question, fix the underlying decision, state 2–4 *falsifiable* hypotheses |\n| 2 | **Genre & blocks** | Pick the report genre (qa \u002F explainer \u002F decision \u002F landscape \u002F validation \u002F custom) and its building blocks |\n| 3 | **Plan** | Write `plan.md`: scope, structure, sourcing strategy, opposition queries, risk register, stop-criteria |\n| 3.5 | **Capability discovery** | Audit available API keys\u002Fchannels in the environment; map subtopics to sources; fall back to HTML where needed |\n| 4 | **Search** (loop) | Dispatch sources → launch sub-agents in parallel → fetch & dedup → save each to `sources\u002FNN.md`; re-evaluate between rounds |\n| 5 | **Score & triangulate** | Rate every source on Credibility \u002F Recency \u002F Bias; require ≥3 independent, differently-typed sources per thesis |\n| 6 | **Synthesize + adversarial** | Assemble the report from blocks, run 4 self-critique questions, add steel-manned counter-arguments |\n| 6.5 | **Verify** | Lightweight citation check before closing |\n| 7 | **Refresh targets** | Extract entities \u002F numbers \u002F hypotheses into `refresh_targets.md` — the entry point for future updates |\n\n## Core mechanisms\n\nThese are what separate a documented investigation from a confident guess:\n\n- **Triangulation.** Every thesis must be backed by ≥3 independent sources of *different types* (primary \u002F academic \u002F industry \u002F discussion). A claim with fewer is flagged \"insufficient evidence,\" not stated as fact.\n- **Source-grounding.** Each source becomes its own `sources\u002FNN_slug.md` with metadata, verbatim quotes, and scores. No dangling claim — every assertion links back to a specific file. An empty fetch produces an empty claim, never a fabricated citation.\n- **Adversarial pass.** Phase 6 always runs the strongest available reasoning: 4 self-critique questions plus an active search for counter-arguments and disconfirming evidence.\n- **Falsifiable hypotheses.** Phase 1 commits to 2–4 hypotheses; Phases 5–6 explicitly confirm or refute each against the evidence, or mark it under-determined.\n- **Parallel sub-agents.** Phase 4 launches search sub-agents concurrently (cheap models for broad web sweeps, stronger ones for reasoning-heavy subtopics) — never one-at-a-time.\n- **Refresh protocol.** Phase 7 emits `refresh_targets.md`; an `update \u003Cslug>` run produces a delta (new entrants, entity changes, refreshed numbers, adversarial triggers) instead of replaying the whole investigation.\n- **Atomic findings.** Reusable theses in `findings\u002FFN.md` plus a `sources.csv` index — research compounds across questions instead of starting from zero each time.\n\n## Output structure\n\n```\n\u003Croot>\u002F\u003Cslug>\u002F\n├── plan.md                  # scope, sourcing strategy, risk register, changelog\n├── sources.csv              # index of every source with scores\n├── sources\u002F\n│   ├── 01_\u003Cslug>.md         # one file = one source (metadata + verbatim quotes)\n│   └── ...\n├── findings\u002F                # atomic, reusable theses (larger investigations)\n│   └── F1_\u003Cshort>.md\n├── refresh_targets.md       # what to watch on update (medium\u002Fdeep)\n├── diffs\u002F\n│   └── YYYY-MM-DD_delta.md   # delta from an `update \u003Cslug>` run\n└── YYYY-MM-DD_\u003Cgenre>.md     # final report\n```\n\n## When to use\n\n- A low-quality answer is expensive: strategy, business plan, report, or article groundwork.\n- Comparing N institutions, products, methodologies, or markets and you need defensible reasoning.\n- Validating a hypothesis or a decision against external data.\n- Meta-research: \"understand how X works,\" \"map the landscape of Y,\" answering a connected series of questions.\n\n## Anti-Patterns\n\n- **Don't skip the existing-work check.** Before searching, see whether the answer is already in the project or in a prior research folder — you risk re-researching something you already have.\n- **Don't skip reframing**, even when the request \"seems clear.\" The decision behind the question usually changes the search.\n- **Don't output to chat only.** Always persist sources and the report to files — the reuse value is in the folder, not the transcript.\n- **Don't fabricate citations.** If a fetch returns nothing, the claim is empty — never invent a plausible URL. Bind every claim to a saved verbatim quote.\n- **Don't build conclusions on a thin corpus.** Too few sources, or sources that all share one type, means triangulation hasn't happened — say so rather than overstating confidence.\n- **Don't skip the adversarial pass** on medium\u002Fdeep investigations. Confirmation-only research is the failure mode this skill exists to prevent.\n- **Don't run sub-agents sequentially.** Fan-out in parallel; serial search wastes the wall-clock advantage.\n- **Don't collapse `sources\u002F` into one file.** Per-source files are what make findings searchable and reusable across investigations.\n- **Don't pick the heaviest model for everything.** Match model to subtask — cheap for broad sweeps, strong for synthesis and the adversarial pass.\n\n## Cross-References\n\n- **research router** — for fast topic overviews where decision risk is low; `deep-research` is the heavyweight alternative when rigor matters more than speed.\n- **competitive-teardown** — for comparing N competitors on a structured 12-dimension matrix.\n- **litreview \u002F dossier \u002F patent** — domain specialists when the investigation is narrowly academic, person\u002Fcompany-focused, or patent-focused.\n",{"name":5,"tags":49,"tools":51,"source":52,"license":14,"description":7,"source_path":53,"source_commit":54},[25,50,33],"agents",[],"https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills","research\u002Fdeep-research\u002Fskills\u002Fdeep-research","19392f7a08264ed00486a251f5b2098321771f94","main","f7cd4595d0f8959822163e14f9787117765c931a","packages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fdeep-research",2,"https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind","https:\u002F\u002Fmonoes.github.io\u002Fmonomind\u002F","https:\u002F\u002Fgithub.com\u002Fmonoes","https:\u002F\u002Fmonoes.me","2026-11-14 03:30:52",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add monoes\u002Fmonomind --skill deep-research",{"tool":70,"command":71},"bunx","bunx skills add monoes\u002Fmonomind --skill deep-research",{"tool":73,"command":74},"pnpm","pnpm dlx skills add monoes\u002Fmonomind --skill deep-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fdeep-research\u002FSKILL.md",true,[78,83],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":15},"LICENSE.txt","LICENSE","许可证",1072,{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ffull-catalog.md","REFERENCE","参考文档",980,"https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fdeep-research\u002Freferences\u002Ffull-catalog.md",[90,119,152,178,200,226],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":118},"01M71PB3SHWKMNJM6MD65VX8D6","zk-steward","Org role guidance for a ZK steward: engineer zero-knowledge proof systems with circuit design, SNARK vs STARK choice and security review. This is zero-knowledge cryptography, not Zettelkasten note-taking.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fzk-steward\u002FSKILL.md",[],[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"zk","zk steward","steward","zero-knowledge","engineer","choice","design","knowledge","impact","query","snark","review","monomind","security review","stark","zettelkasten","cryptography","security","org","blockchain","2026-11-10 13:02:02",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":134,"publishedAt":118},"01M71PB18SDG28WBKPKJNB814K","writing-plans","Use when you have a spec or requirements for a multi-step coding task and must write an implementation plan before touching code. Produces bite-sized TDD tasks with exact file paths, code and commands for an engineer with zero context.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FSKILL.md",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[135,136,137,102,138,139,38,140,107,141,142,143,144,145,146,147,148,149,150,151],"writing","writing plans","plans","superpowers","implementation plan","you","code","tasks","plan","product","write","commands","paths","suggest","coding","context","ZeRO",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":156,"sourceHtmlUrl":157,"categories":158,"keywords":162,"publishedAt":118},"01M71PAXFM488X9ARXK0T04TF5","write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FSKILL.md",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000031","产品经理",[145,163,164,165,166,105,167,38,168,169,170,144,171,172,173,174,175,176,31,177],"write spec","spec","user request","problem","acceptance","ask","vague","work","request","scoping","idea","metrics","feature","problem statement","document",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":182,"sourceHtmlUrl":183,"categories":184,"keywords":188,"publishedAt":118},"01M71PASSZY800C0RPEARBS918","write-query","Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FSKILL.md",[185],{"categoryNo":186,"categoryName":187,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000033","数据分析师",[107,145,189,190,32,191,105,31,38,192,193,28,27,170,194,195,196,197,198,199],"write query","postgres","snowflake","best practices","natural-language","github","sql","https","syntax","plugins","data",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":212,"publishedAt":118},"01M71PAPTX0T3PF6ETFVR96SJJ","workflow-automation","Org role guidance for workflow automation: build and maintain CI\u002FCD definitions in GitHub Actions or equivalent: triggers, jobs, matrices, caching. Covers path filters, dependency caching, parallel jobs, timeouts and fail-fast ordering.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-automation\u002FSKILL.md",[206,209],{"categoryNo":207,"categoryName":208,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[213,214,215,34,32,216,217,218,219,106,220,221,222,107,110,194,223,224,225,196],"Workflow Automation","automation","workflow","actions","ci","triggers","github actions","maintain","filters","caching","build","dependency","devops",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":233,"publishedAt":118},"01M71PAM19Z1XTV9NPCFSE2MY8","workflow-architect","Org role guidance for a workflow architect: map full workflow trees for systems, user journeys and agents, covering every branch and failure. Covers discovering workflows from code, handoff contracts, timeouts, recovery paths and observable state.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-architect\u002FSKILL.md",[232],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},[215,234,235,236,237,238,33,32,239,240,141,241,242,243,110,194,244,245,196,246],"workflow architect","architect","trees","user journeys","branch","map","workflows","architecture","state","leadership","recovery","operations","systems"]