[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71QQF4MM2WXB6KP9RQ4QADD":3,"skill-same:01M71QQF4MM2WXB6KP9RQ4QADD":76},{"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":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M71QQF4MM2WXB6KP9RQ4QADD","method-workflow",null,"Shows the methodsmith study lifecycle for the current project and recommends the next safe skill. Use when the user asks what to run next or wants lifecycle status.","sajor2000\u002Fmethodsmith","sajor2000","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F126191042?v=4","01M71QG4M3561SH49E3S7J3GKT","JC Rojas ","01M71QG4N56X2P61YTJSRP95VD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-workflow\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"workflow","method workflow","for","project","study","lifecycle","safe skill","use","when","next","run","safe","status","user","2026-11-10 13:02:02",false,"---\nname: method-workflow\ndescription: \"Shows the methodsmith study lifecycle for the current project and recommends the next safe skill. Use when the user asks what to run next or wants lifecycle status.\"\n---\n\n# Workflow Navigator\n\n\n## Skill Value\n\n- **Problem it solves:** Users do not know which slash skill comes next after setup, QA, SAP, sprint, or analysis work.\n- **Use when:** The user starts or resumes a science project, feels unsure what to run next, or wants lifecycle status.\n- **Output:** Lifecycle card with detected project type, current status, and next recommended skill.\n- **Ask only if:** Only when project type remains ambiguous after scanning repo and stack-profile signals.\n- **Do not do:** Do not run lifecycle skills or modify project state.\n- **Interaction:** Check repo\u002Fconfig\u002Fchat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.\n\nShows the ordered skill sequence for a science project, detects progress, and recommends the next step. Read-only guidance — does not replace any existing skill.\n\n## Stack Profile\n\nThe repository root is pre-resolved at skill load:\n!`git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || true`\n\nUse the resolved absolute path or resolve it at runtime, then read `.methodsmith\u002Fconfig.local.yaml` with the native file-read tool. In a linked worktree, fall back to the main checkout when the machine-local file is absent. Parse these `stack_profile` keys: `language`, `ide`, `reporting`, `data_layer`, `clif.data_dictionary_version`, `clif.mcide_version`, and the optional `inference` map; if no config can be read, infer them from project files.\n\nTreat a saved inference value with its `confidence` and `evidence` as a reusable\nsetup handoff. Do not re-ask a setup question when a high-confidence value is\navailable. If routing must use a fallback, say so and name the missing evidence\nthat would refine it.\n\n## Phase 0: Detect Signals\n\nScan the working directory for project-type signals. Do not ask the user yet.\n\n**CLIF signals** (strong signals → auto-route to CLIF overlay; weak signals need 2+ to route):\n\nStrong (any one sufficient):\n- `CLIF_CLAUDE.md` at repo root\n- Git remote contains `clif-consortium` or `clif-icu`\n- `__CE_CLIF__ active=true` in chat context\n\nWeak (need 2+ together):\n- `mCIDE\u002F` directory exists\n- `clif_*.parquet` files exist\n- `WORKFLOW.md` at repo root\n\nDo NOT route to CLIF for: generic `patient.parquet`, `vitals`, `labs`, `renv.lock` alone, or `WORKFLOW.md` alone — these appear in non-CLIF EHR projects.\n\nWhen CLIF routes, reuse a matching saved `data_dictionary_version` +\n`mcide_version` pair or a matching `__CE_CLIF__` handoff. If the family is\nabsent, incomplete, or mixed, recommend `method-clif` as the next safe skill and\nstate that it will ask the user to choose CLIF 2.1 + mCIDE 2.1 or CLIF 3.0 +\nmCIDE 3.0. Do not infer 3.0 from `mCIDE\u002F` alone or silently apply v2.1.\n\n**OMOP signals** (any one → observational study + OMOP overlay):\n- SQL files referencing `cdm_source`, `concept`, `person`, or `observation_period`\n- `analysis\u002Fcohort\u002F` contains `.sql` with OMOP table names\n\n**Bioinformatics signals** (any one → bioinformatics path):\n- `.fastq`, `.fastq.gz`, `.bam`, `.vcf` files in project tree\n- `Snakefile`, `nextflow.config`, or `workflow\u002FSnakefile` exists\n- `Bioconductor` in `renv.lock` or `DESCRIPTION`\n\n**Claims signals** (any one → observational-study + claims overlay):\n- Medicare, Medicaid, MarketScan, NDC, enrollment-gap, or payer-claim logic in active analysis files\n\n**Generic EHR signals** (two or more → observational-study + generic-EHR overlay):\n- cohort, encounter, diagnosis, medication, laboratory, or vital-sign fields in active analysis files\n\n**No biomedical signals** → default to Technical \u002F software path without asking and label the route `fallback: no biomedical project evidence`.\n\n## Phase 1: Detect or Ask Project Type\n\nIf signals clearly indicate a project type, auto-route and print a one-line banner with its evidence:\n\n```\n[method-workflow] Auto-detected: Observational study (CLIF data layer, R; evidence: CLIF_CLAUDE.md, clif_*.parquet)\n```\n\nIf project type remains unclear after scanning available files, ask this routing question using the Skill Value interaction rule above.\n\n**Question:** \"What type of project is this?\"\n\n**Options:**\n1. Observational study (cohort, case-control, cross-sectional)\n2. Clinical trial analysis (RCT, trial emulation)\n3. Prediction \u002F ML model (development, validation, impact)\n4. Bioinformatics \u002F omics (genomics, transcriptomics, proteomics)\n\n## Phase 2: Detect Progress and Emit Card\n\nRead `references\u002Flifecycle-paths.md` for the skill sequence matching the project type. Then read `references\u002Fstate-detection.md` and check each signal to determine step status:\n\n- Done: file artifact exists and appears complete\n- In progress: artifact exists but is partial or ambiguous\n- Not started: no artifact found\n\nResolve language from the highest-confidence compatible source in this order:\nexplicit current request, saved profile, saved inference, `__CE_LANG__`, then\nproject files. Resolve data domain from Phase 0 signals or saved inference\n(OMOP, CLIF, admin claims, bioinformatics, generic EHR, or generic data). Never\nconvert an unknown language to `both`; show `unknown` and recommend setup only\nwhen the selected lifecycle needs a language-specific artifact.\n\nEmit the lifecycle card (an example rendering for Path 1; take the steps from `references\u002Flifecycle-paths.md`):\n\n```\n## Workflow: Observational Study (OMOP)\nLanguage: Python (Jupyter) | Data layer: OMOP\n\n 1. [done] `method-question`    analysis\u002Fresearch-question.yaml\n 2. [done] `method-pubmed`                analysis\u002Fpubmed\u002F\n 3. [    ] `method-extract`\n 4. [    ] `method-checklist`       STROBE + RECORD\n 5. [    ] `method-meta-analysis`\n 6. [    ] `method-power`\n 7. [    ] `method-cohort`          OMOP SQL + concept sets\n 8. [    ] `method-data-qa`\n 9. [    ] `method-phenotype`\n10. [    ] `method-model-choice`\n11. [    ] `method-plan` (SAP mode)\n12. [    ] `method-sap-workbook`\n13. [    ] `method-sprint`\n14. [    ] `method-work`                  Jupyter .ipynb\n15. [    ] `method-review`\n\nNext step: `method-extract`\n  Extract statistical methods from your PubMed results for SAP justification.\n```\n\nRender each status as `[done]`, `[wip ]` (in progress), or `[    ]` (not\nstarted), and after each done or in-progress step name the artifact that set it.\n\nWhen `analysis\u002Fnumbers\u002Fregistry.json` exists, add a `Numbers:` line under the card with the `method-numbers` gate status from `references\u002Fstate-detection.md` (`PASS`, `FAIL` with its problem count, or `not run`); a `FAIL` makes fixing it the next step before any manuscript or submission step.\n\nInline language-specific and data-layer notes at the steps where they matter (e.g., step 7 shows \"OMOP SQL + concept sets\" or \"CAPR + SQL\" depending on language; step 14 shows \"Jupyter .ipynb\" or \"Marimo .py\" or \"Quarto .qmd\").\n\nIf all steps are complete, emit: \"All lifecycle steps complete. Load the `method-compound` skill to document learnings.\"\n\nIf no stack profile exists, append: \"Run the `method-setup` command first to review the detected profile.\"\n\n## What this skill does NOT do\n\n- Does not run any lifecycle skill — it only recommends the next one\n- Does not replace setup -- the user must run the `method-setup` command first for a full stack profile (it is manual-invocation-only)\n- Does not create files or modify project state\n- Does not replace `method-clif` — CLIF activation happens automatically via `method-clif`\n\n## References\n\n`references\u002Flifecycle-paths.md` — Ordered skill sequences for all 5 project types with language branches and data-layer overlays\n\n`references\u002Fstate-detection.md` — File-system signals used to infer which steps are complete\n","# Workflow Navigator\n\n\n## Skill Value\n\n- **Problem it solves:** Users do not know which slash skill comes next after setup, QA, SAP, sprint, or analysis work.\n- **Use when:** The user starts or resumes a science project, feels unsure what to run next, or wants lifecycle status.\n- **Output:** Lifecycle card with detected project type, current status, and next recommended skill.\n- **Ask only if:** Only when project type remains ambiguous after scanning repo and stack-profile signals.\n- **Do not do:** Do not run lifecycle skills or modify project state.\n- **Interaction:** Check repo\u002Fconfig\u002Fchat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.\n\nShows the ordered skill sequence for a science project, detects progress, and recommends the next step. Read-only guidance — does not replace any existing skill.\n\n## Stack Profile\n\nThe repository root is pre-resolved at skill load:\n!`git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || true`\n\nUse the resolved absolute path or resolve it at runtime, then read `.methodsmith\u002Fconfig.local.yaml` with the native file-read tool. In a linked worktree, fall back to the main checkout when the machine-local file is absent. Parse these `stack_profile` keys: `language`, `ide`, `reporting`, `data_layer`, `clif.data_dictionary_version`, `clif.mcide_version`, and the optional `inference` map; if no config can be read, infer them from project files.\n\nTreat a saved inference value with its `confidence` and `evidence` as a reusable\nsetup handoff. Do not re-ask a setup question when a high-confidence value is\navailable. If routing must use a fallback, say so and name the missing evidence\nthat would refine it.\n\n## Phase 0: Detect Signals\n\nScan the working directory for project-type signals. Do not ask the user yet.\n\n**CLIF signals** (strong signals → auto-route to CLIF overlay; weak signals need 2+ to route):\n\nStrong (any one sufficient):\n- `CLIF_CLAUDE.md` at repo root\n- Git remote contains `clif-consortium` or `clif-icu`\n- `__CE_CLIF__ active=true` in chat context\n\nWeak (need 2+ together):\n- `mCIDE\u002F` directory exists\n- `clif_*.parquet` files exist\n- `WORKFLOW.md` at repo root\n\nDo NOT route to CLIF for: generic `patient.parquet`, `vitals`, `labs`, `renv.lock` alone, or `WORKFLOW.md` alone — these appear in non-CLIF EHR projects.\n\nWhen CLIF routes, reuse a matching saved `data_dictionary_version` +\n`mcide_version` pair or a matching `__CE_CLIF__` handoff. If the family is\nabsent, incomplete, or mixed, recommend `method-clif` as the next safe skill and\nstate that it will ask the user to choose CLIF 2.1 + mCIDE 2.1 or CLIF 3.0 +\nmCIDE 3.0. Do not infer 3.0 from `mCIDE\u002F` alone or silently apply v2.1.\n\n**OMOP signals** (any one → observational study + OMOP overlay):\n- SQL files referencing `cdm_source`, `concept`, `person`, or `observation_period`\n- `analysis\u002Fcohort\u002F` contains `.sql` with OMOP table names\n\n**Bioinformatics signals** (any one → bioinformatics path):\n- `.fastq`, `.fastq.gz`, `.bam`, `.vcf` files in project tree\n- `Snakefile`, `nextflow.config`, or `workflow\u002FSnakefile` exists\n- `Bioconductor` in `renv.lock` or `DESCRIPTION`\n\n**Claims signals** (any one → observational-study + claims overlay):\n- Medicare, Medicaid, MarketScan, NDC, enrollment-gap, or payer-claim logic in active analysis files\n\n**Generic EHR signals** (two or more → observational-study + generic-EHR overlay):\n- cohort, encounter, diagnosis, medication, laboratory, or vital-sign fields in active analysis files\n\n**No biomedical signals** → default to Technical \u002F software path without asking and label the route `fallback: no biomedical project evidence`.\n\n## Phase 1: Detect or Ask Project Type\n\nIf signals clearly indicate a project type, auto-route and print a one-line banner with its evidence:\n\n```\n[method-workflow] Auto-detected: Observational study (CLIF data layer, R; evidence: CLIF_CLAUDE.md, clif_*.parquet)\n```\n\nIf project type remains unclear after scanning available files, ask this routing question using the Skill Value interaction rule above.\n\n**Question:** \"What type of project is this?\"\n\n**Options:**\n1. Observational study (cohort, case-control, cross-sectional)\n2. Clinical trial analysis (RCT, trial emulation)\n3. Prediction \u002F ML model (development, validation, impact)\n4. Bioinformatics \u002F omics (genomics, transcriptomics, proteomics)\n\n## Phase 2: Detect Progress and Emit Card\n\nRead `references\u002Flifecycle-paths.md` for the skill sequence matching the project type. Then read `references\u002Fstate-detection.md` and check each signal to determine step status:\n\n- Done: file artifact exists and appears complete\n- In progress: artifact exists but is partial or ambiguous\n- Not started: no artifact found\n\nResolve language from the highest-confidence compatible source in this order:\nexplicit current request, saved profile, saved inference, `__CE_LANG__`, then\nproject files. Resolve data domain from Phase 0 signals or saved inference\n(OMOP, CLIF, admin claims, bioinformatics, generic EHR, or generic data). Never\nconvert an unknown language to `both`; show `unknown` and recommend setup only\nwhen the selected lifecycle needs a language-specific artifact.\n\nEmit the lifecycle card (an example rendering for Path 1; take the steps from `references\u002Flifecycle-paths.md`):\n\n```\n## Workflow: Observational Study (OMOP)\nLanguage: Python (Jupyter) | Data layer: OMOP\n\n 1. [done] `method-question`    analysis\u002Fresearch-question.yaml\n 2. [done] `method-pubmed`                analysis\u002Fpubmed\u002F\n 3. [    ] `method-extract`\n 4. [    ] `method-checklist`       STROBE + RECORD\n 5. [    ] `method-meta-analysis`\n 6. [    ] `method-power`\n 7. [    ] `method-cohort`          OMOP SQL + concept sets\n 8. [    ] `method-data-qa`\n 9. [    ] `method-phenotype`\n10. [    ] `method-model-choice`\n11. [    ] `method-plan` (SAP mode)\n12. [    ] `method-sap-workbook`\n13. [    ] `method-sprint`\n14. [    ] `method-work`                  Jupyter .ipynb\n15. [    ] `method-review`\n\nNext step: `method-extract`\n  Extract statistical methods from your PubMed results for SAP justification.\n```\n\nRender each status as `[done]`, `[wip ]` (in progress), or `[    ]` (not\nstarted), and after each done or in-progress step name the artifact that set it.\n\nWhen `analysis\u002Fnumbers\u002Fregistry.json` exists, add a `Numbers:` line under the card with the `method-numbers` gate status from `references\u002Fstate-detection.md` (`PASS`, `FAIL` with its problem count, or `not run`); a `FAIL` makes fixing it the next step before any manuscript or submission step.\n\nInline language-specific and data-layer notes at the steps where they matter (e.g., step 7 shows \"OMOP SQL + concept sets\" or \"CAPR + SQL\" depending on language; step 14 shows \"Jupyter .ipynb\" or \"Marimo .py\" or \"Quarto .qmd\").\n\nIf all steps are complete, emit: \"All lifecycle steps complete. Load the `method-compound` skill to document learnings.\"\n\nIf no stack profile exists, append: \"Run the `method-setup` command first to review the detected profile.\"\n\n## What this skill does NOT do\n\n- Does not run any lifecycle skill — it only recommends the next one\n- Does not replace setup -- the user must run the `method-setup` command first for a full stack profile (it is manual-invocation-only)\n- Does not create files or modify project state\n- Does not replace `method-clif` — CLIF activation happens automatically via `method-clif`\n\n## References\n\n`references\u002Flifecycle-paths.md` — Ordered skill sequences for all 5 project types with language branches and data-layer overlays\n\n`references\u002Fstate-detection.md` — File-system signals used to infer which steps are complete\n",{"name":5,"description":7},"main","893bccb980e4dce1345919e9f675f5a9dcbed364","plugins\u002Fmethodsmith\u002Fskills\u002Fmethod-workflow",0,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith","https:\u002F\u002Fsajor2000.github.io\u002Fmethodsmith\u002F","https:\u002F\u002Fgithub.com\u002Fsajor2000","Critical care physician-scientist at Rush University. @Common-Longitudinal-ICU-data-Format contributor building open ICU data tools & clinical AI","2026-11-01 01:56:01",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add sajor2000\u002Fmethodsmith --skill method-workflow",{"tool":58,"command":59},"bunx","bunx skills add sajor2000\u002Fmethodsmith --skill method-workflow",{"tool":61,"command":62},"pnpm","pnpm dlx skills add sajor2000\u002Fmethodsmith --skill method-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-workflow\u002FSKILL.md",true,[66,72],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Flifecycle-paths.md","REFERENCE","参考文档",11432,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-workflow\u002Freferences\u002Flifecycle-paths.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fstate-detection.md",4521,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-workflow\u002Freferences\u002Fstate-detection.md",[77,89,103,115,124,133],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":84,"publishedAt":38},"01M71QQY0KE1184AF58EC1J5C1","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[83],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[85,86,87,88],"one","skill one","sample","sample skill",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":96,"publishedAt":38},"01M71QQW3PNK9AYB5HBMAPM72J","disabled-skill","A skill with model invocation disabled","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fdisabled-skill\u002FSKILL.md",[95],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[97,98,99,100,101,102],"disabled skill","a skill","with model","with","true","model",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":38},"01M71QQSY02X7DNZQRAGJ6YFGY","claude-only-skill","A skill restricted to Claude Code only","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fclaude-only-skill\u002FSKILL.md",[109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[111,112,113,98,114],"claude only","claude only skill","only","code",{"skillNo":116,"name":117,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":38},"01M71QQRPZ76X623V5P7T1E3DD","default-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123],"default","default skill",{"skillNo":125,"name":126,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":130,"publishedAt":38},"01M71QQQG3FF2HFQHVH8VHA08R","custom-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[129],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,132],"custom skill","custom",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":38},"01M71QQMBNC76141GHXBSMENSH","method-write","Drafts, revises, and audits evidence-bound manuscripts, sections, abstracts, and reviewer responses with claim provenance. Use when scientific prose must be written or revised (entry point).","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-write\u002FSKILL.md",[],[140,141,142,143,144,145,31,32,146,147,100,148,149,150],"write","method write","point","evidence","entry","claim","provenance","reviewer","scientific","prose","drafts"]