[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71QJGS1HB23NTP30XP2S5TN":3,"skill-same:01M71QJGS1HB23NTP30XP2S5TN":87},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M71QJGS1HB23NTP30XP2S5TN","method-extract",null,"Extracts methods, cohorts, endpoints, models, and assumptions from retrieved papers for SAP justification. Use when literature results need methods grounding.","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-extract\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],"extract","method extract","results","endpoints","csv","grounding","assumptions","use","methods","for","sap","path","full","max","pubmed","literature","text","when","only","papers","2026-11-10 13:02:02",false,"---\nname: method-extract\ndescription: \"Extracts methods, cohorts, endpoints, models, and assumptions from retrieved papers for SAP justification. Use when literature results need methods grounding.\"\nargument-hint: \"\u003Cpath\u002Fto\u002Fpubmed-results.csv>, optional: --full-text-only --max 25\"\n---\n\n# Method Extraction from Prior Literature\n\n\n## Skill Value\n\n- **Problem it solves:** Plans cite papers but often miss the methods details needed to justify analysis choices.\n- **Use when:** The user has PubMed, Paperclip, or literature-search results and needs methods grounding.\n- **Output:** Structured methods extraction table with cohort, outcome, model, covariate, and effect-size clues.\n- **Ask only if:** Only when source set, extraction fields, or target SAP section is unclear.\n- **Do not do:** Do not treat abstracts as full-text evidence when methods are unavailable.\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\nReads a PubMed result CSV and produces a structured methods-comparison table for the SAP.\n\n## When this skill activates\n\n- After `method-pubmed` has produced `analysis\u002Fpubmed\u002F\u003Cquery>-\u003Cdate>.csv`\n- During `method-plan` SAP drafting when method choice needs justification\n- Before `method-power` when you need literature context for the target difference (published effects are typically inflated by publication bias and small-study effects; `method-power` should justify the target difference as important and\u002For realistic per DELTA2, Cook et al., BMJ 2018, PMID 30560792)\n\n## Prerequisites\n\n- A PubMed result CSV (from `method-pubmed`) exists\n- For `--full-text-only`, the rows must have non-empty `pmcid` (open PMC full text), or Paperclip must be able to `lookup` the paper\n\n## Evidence access\n\nWhen this run needs literature, read `references\u002Fevidence-access.md` first; never invent a citation, effect size, or guideline item.\n\n- **Look up here:** the full text of each included paper (Methods, Results, statistical-analysis sections, and Table 1) for methods extraction; the CSV abstract is the source only when no lawful full text exists.\n\n## Core workflow\n\n### Step 0: Context inputs (scan chat first)\n\nIf no `\u003Cpath\u002Fto\u002Fpubmed-results.csv>` was passed as the first argument, scan the most recent ~50 chat turns for `__CE_PUBMED_RESULTS__ csv=\u003Cpath> n=\u003Cint> ...`. If found, use that CSV path as the input.\n\nAlso scan for `__CE_EVIDENCE_MAP__ path=\u003Cartifact> sources=pubmed[,paperclip] ...`. If present, read the evidence map before extraction and use it to prioritize papers, identify full-text-verified claims, and avoid re-asking literature questions already answered there. The PubMed CSV remains the required tabular input for this skill; the evidence map is context, not a replacement CSV.\n\nPrint: `[pubmed] using results from \u003Cpath> (n=\u003CN>)`. If neither an explicit path nor the signal is present, ask the user to load the `method-pubmed` skill first or pass a CSV path explicitly.\n\n### Step 1: Load and prioritize\n\nRead the input CSV. If `--full-text-only`, drop rows without `pmcid` and report how many were dropped. Sort by year (descending), then by design (RCT > prospective cohort > retrospective cohort > case-control > case series; a project ordering for reading priority, not an evidence grade). Cap at `--max` (default 25).\n\n### Step 2: Read the paper, not only the abstract\n\n**MCP egress (every mode):** send PubMed, Paperclip, and other MCP or web tools only search terms, MeSH terms, PMIDs, DOIs, and titles, never data values, identifiers, row text, or data files; an endpoint approval does not cover third-party services.\n\nFull text is the extraction source whenever it is lawfully available; the CSV abstract alone is the last resort. For each paper, in preference order:\n\n1. **PubMed MCP full text.** For rows with a `pmcid`, call `pubmed_fetch_fulltext` (default server), or `get_copyright_status` and then `get_full_text_article` (other connectors), with the PMCID. Read the Methods, Results, and statistical-analysis sections and Table 1. Cite PubMed and include the DOI in the output row.\n2. **Paperclip MCP full text.** `lookup` the paper by `doi`, `pmid`, or `pmc`, then `cat` the Methods\u002FResults sections or `grep`\u002F`scan` for the field cues in Step 3 (for example `Cox|logistic|mixed|propensity|primary outcome`). The authenticated `paperclip` CLI is the fallback for the same reads. Paperclip may cover papers without a PMCID.\n3. **E-utilities fallback** when neither MCP server is connected and the row has a `pmcid`: `efetch.fcgi?db=pmc&id=\u003Cpmcid>&rettype=xml&retmode=xml`, then extract `\u003Csec sec-type=\"methods\">`, `\u003Csec sec-type=\"results\">`, and `\u003Csec sec-type=\"statistics\">`.\n4. **Abstract only** when no lawful full text exists: use the abstract from the input CSV and say so.\n\nRecord what was read in an `evidence_level` column: `full_text` when any of paths 1-3 was read, `abstract` otherwise. Under `--full-text-only`, drop rows that end at `abstract` and report them.\n\n### Step 3: Extract structured fields per paper\n\nFor each paper, populate:\n\n| Field | Source heuristic |\n|-------|------------------|\n| `sample_size` | \"we enrolled N\", \"Final analytic cohort comprised N\", first table-1 N |\n| `primary_outcome` | \"primary outcome was X\", \"primary endpoint\", first sentence after \"Outcomes\" subsection |\n| `outcome_type` | continuous \u002F binary \u002F time-to-event \u002F count \u002F ordinal |\n| `analysis_population` | ITT \u002F per-protocol \u002F mITT \u002F complete-case \u002F multiple-imputation |\n| `statistical_method` | \"Cox proportional hazards\", \"logistic regression\", \"linear mixed model\", etc. |\n| `adjustment_set` | covariates listed in the model |\n| `software` | R + package name, SAS, Stata, Python+statsmodels\u002Fsklearn, etc. |\n| `multiplicity_control` | Bonferroni \u002F FDR \u002F hierarchical \u002F none |\n| `effect_size_reported` | OR, HR, RR, mean diff, with 95% CI |\n| `design` | RCT \u002F prospective cohort \u002F retrospective cohort \u002F case-control \u002F cross-sectional \u002F simulation \u002F methods guidance |\n| `bias_flags` | stated or obvious: selection, confounding, small n, single site, outcome-reporting; `none noted` otherwise (not a formal risk-of-bias assessment) |\n| `checklist_followed` | CONSORT \u002F STROBE \u002F TRIPOD \u002F TRIPOD+AI \u002F PRISMA \u002F none stated |\n| `evidence_level` | `full_text` or `abstract`, from Step 2 |\n\nBe conservative: if the paper does not state a field, write `not reported` rather than infer. Fields such as `adjustment_set`, `software`, and `multiplicity_control` are rarely in an abstract; on an `abstract` row expect `not reported` rather than a guess.\n\n### Step 4: Write the comparison table\n\nSave to `analysis\u002Fpubmed\u002F\u003Cquery-slug>-methods.csv` with one row per paper, keeping the input's `pmid`, `year`, `first_author`, `doi`, and `pmcid` columns (`method-meta-analysis` needs them). Also write `analysis\u002Fpubmed\u002F\u003Cquery-slug>-methods-summary.md`:\n\n- **Modal method** (most common) per outcome type\n- **Method × year** matrix (is the field shifting?)\n- **Software × method** matrix (what to install)\n- **Effect-size range** (min \u002F median \u002F max) for each commonly-reported metric, with a note that published estimates are likely inflated and should not be used unadjusted as the power target\n- **% of papers stating a checklist** (low % is itself informative)\n- **% of rows at `full_text`** versus `abstract`, so the SAP states how much of the justification rests on abstracts\n\n### Step 5: Emit signal for downstream skills\n\n`__CE_METHOD_EXTRACT__ csv=\u003Cpath> n=\u003Ccount> modal_method=\u003Cname>`\n\nCompletion check before emitting: every row has `pmid` or `doi`, `design`, and `evidence_level`; no field is filled by inference (`not reported` instead); the summary's `full_text` percentage matches the CSV.\n\nThe modal method is reported as context for `method-model-choice`, which selects the analytic method from the estimand, outcome, and data structure; method frequency is never the selection criterion. The comparison table (PMIDs, DOIs, per-row `design` and `evidence_level`) is the citation for that context.\n\n## What this skill does NOT do\n\n- Does not download PDFs or use unauthorized mirrors (full text via open PMC or a connected Paperclip service only)\n- Does not perform formal risk-of-bias or quality appraisal (it records design and obvious bias flags only)\n- Does not pool effect sizes (use the `method-meta-analysis` skill)\n- Does not match the study to a checklist (use the `method-checklist` skill)\n\n## References\n\n@.\u002Freferences\u002Fextraction-prompts.md\n\n@.\u002Freferences\u002Fmethod-taxonomy.md\n","# Method Extraction from Prior Literature\n\n\n## Skill Value\n\n- **Problem it solves:** Plans cite papers but often miss the methods details needed to justify analysis choices.\n- **Use when:** The user has PubMed, Paperclip, or literature-search results and needs methods grounding.\n- **Output:** Structured methods extraction table with cohort, outcome, model, covariate, and effect-size clues.\n- **Ask only if:** Only when source set, extraction fields, or target SAP section is unclear.\n- **Do not do:** Do not treat abstracts as full-text evidence when methods are unavailable.\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\nReads a PubMed result CSV and produces a structured methods-comparison table for the SAP.\n\n## When this skill activates\n\n- After `method-pubmed` has produced `analysis\u002Fpubmed\u002F\u003Cquery>-\u003Cdate>.csv`\n- During `method-plan` SAP drafting when method choice needs justification\n- Before `method-power` when you need literature context for the target difference (published effects are typically inflated by publication bias and small-study effects; `method-power` should justify the target difference as important and\u002For realistic per DELTA2, Cook et al., BMJ 2018, PMID 30560792)\n\n## Prerequisites\n\n- A PubMed result CSV (from `method-pubmed`) exists\n- For `--full-text-only`, the rows must have non-empty `pmcid` (open PMC full text), or Paperclip must be able to `lookup` the paper\n\n## Evidence access\n\nWhen this run needs literature, read `references\u002Fevidence-access.md` first; never invent a citation, effect size, or guideline item.\n\n- **Look up here:** the full text of each included paper (Methods, Results, statistical-analysis sections, and Table 1) for methods extraction; the CSV abstract is the source only when no lawful full text exists.\n\n## Core workflow\n\n### Step 0: Context inputs (scan chat first)\n\nIf no `\u003Cpath\u002Fto\u002Fpubmed-results.csv>` was passed as the first argument, scan the most recent ~50 chat turns for `__CE_PUBMED_RESULTS__ csv=\u003Cpath> n=\u003Cint> ...`. If found, use that CSV path as the input.\n\nAlso scan for `__CE_EVIDENCE_MAP__ path=\u003Cartifact> sources=pubmed[,paperclip] ...`. If present, read the evidence map before extraction and use it to prioritize papers, identify full-text-verified claims, and avoid re-asking literature questions already answered there. The PubMed CSV remains the required tabular input for this skill; the evidence map is context, not a replacement CSV.\n\nPrint: `[pubmed] using results from \u003Cpath> (n=\u003CN>)`. If neither an explicit path nor the signal is present, ask the user to load the `method-pubmed` skill first or pass a CSV path explicitly.\n\n### Step 1: Load and prioritize\n\nRead the input CSV. If `--full-text-only`, drop rows without `pmcid` and report how many were dropped. Sort by year (descending), then by design (RCT > prospective cohort > retrospective cohort > case-control > case series; a project ordering for reading priority, not an evidence grade). Cap at `--max` (default 25).\n\n### Step 2: Read the paper, not only the abstract\n\n**MCP egress (every mode):** send PubMed, Paperclip, and other MCP or web tools only search terms, MeSH terms, PMIDs, DOIs, and titles, never data values, identifiers, row text, or data files; an endpoint approval does not cover third-party services.\n\nFull text is the extraction source whenever it is lawfully available; the CSV abstract alone is the last resort. For each paper, in preference order:\n\n1. **PubMed MCP full text.** For rows with a `pmcid`, call `pubmed_fetch_fulltext` (default server), or `get_copyright_status` and then `get_full_text_article` (other connectors), with the PMCID. Read the Methods, Results, and statistical-analysis sections and Table 1. Cite PubMed and include the DOI in the output row.\n2. **Paperclip MCP full text.** `lookup` the paper by `doi`, `pmid`, or `pmc`, then `cat` the Methods\u002FResults sections or `grep`\u002F`scan` for the field cues in Step 3 (for example `Cox|logistic|mixed|propensity|primary outcome`). The authenticated `paperclip` CLI is the fallback for the same reads. Paperclip may cover papers without a PMCID.\n3. **E-utilities fallback** when neither MCP server is connected and the row has a `pmcid`: `efetch.fcgi?db=pmc&id=\u003Cpmcid>&rettype=xml&retmode=xml`, then extract `\u003Csec sec-type=\"methods\">`, `\u003Csec sec-type=\"results\">`, and `\u003Csec sec-type=\"statistics\">`.\n4. **Abstract only** when no lawful full text exists: use the abstract from the input CSV and say so.\n\nRecord what was read in an `evidence_level` column: `full_text` when any of paths 1-3 was read, `abstract` otherwise. Under `--full-text-only`, drop rows that end at `abstract` and report them.\n\n### Step 3: Extract structured fields per paper\n\nFor each paper, populate:\n\n| Field | Source heuristic |\n|-------|------------------|\n| `sample_size` | \"we enrolled N\", \"Final analytic cohort comprised N\", first table-1 N |\n| `primary_outcome` | \"primary outcome was X\", \"primary endpoint\", first sentence after \"Outcomes\" subsection |\n| `outcome_type` | continuous \u002F binary \u002F time-to-event \u002F count \u002F ordinal |\n| `analysis_population` | ITT \u002F per-protocol \u002F mITT \u002F complete-case \u002F multiple-imputation |\n| `statistical_method` | \"Cox proportional hazards\", \"logistic regression\", \"linear mixed model\", etc. |\n| `adjustment_set` | covariates listed in the model |\n| `software` | R + package name, SAS, Stata, Python+statsmodels\u002Fsklearn, etc. |\n| `multiplicity_control` | Bonferroni \u002F FDR \u002F hierarchical \u002F none |\n| `effect_size_reported` | OR, HR, RR, mean diff, with 95% CI |\n| `design` | RCT \u002F prospective cohort \u002F retrospective cohort \u002F case-control \u002F cross-sectional \u002F simulation \u002F methods guidance |\n| `bias_flags` | stated or obvious: selection, confounding, small n, single site, outcome-reporting; `none noted` otherwise (not a formal risk-of-bias assessment) |\n| `checklist_followed` | CONSORT \u002F STROBE \u002F TRIPOD \u002F TRIPOD+AI \u002F PRISMA \u002F none stated |\n| `evidence_level` | `full_text` or `abstract`, from Step 2 |\n\nBe conservative: if the paper does not state a field, write `not reported` rather than infer. Fields such as `adjustment_set`, `software`, and `multiplicity_control` are rarely in an abstract; on an `abstract` row expect `not reported` rather than a guess.\n\n### Step 4: Write the comparison table\n\nSave to `analysis\u002Fpubmed\u002F\u003Cquery-slug>-methods.csv` with one row per paper, keeping the input's `pmid`, `year`, `first_author`, `doi`, and `pmcid` columns (`method-meta-analysis` needs them). Also write `analysis\u002Fpubmed\u002F\u003Cquery-slug>-methods-summary.md`:\n\n- **Modal method** (most common) per outcome type\n- **Method × year** matrix (is the field shifting?)\n- **Software × method** matrix (what to install)\n- **Effect-size range** (min \u002F median \u002F max) for each commonly-reported metric, with a note that published estimates are likely inflated and should not be used unadjusted as the power target\n- **% of papers stating a checklist** (low % is itself informative)\n- **% of rows at `full_text`** versus `abstract`, so the SAP states how much of the justification rests on abstracts\n\n### Step 5: Emit signal for downstream skills\n\n`__CE_METHOD_EXTRACT__ csv=\u003Cpath> n=\u003Ccount> modal_method=\u003Cname>`\n\nCompletion check before emitting: every row has `pmid` or `doi`, `design`, and `evidence_level`; no field is filled by inference (`not reported` instead); the summary's `full_text` percentage matches the CSV.\n\nThe modal method is reported as context for `method-model-choice`, which selects the analytic method from the estimand, outcome, and data structure; method frequency is never the selection criterion. The comparison table (PMIDs, DOIs, per-row `design` and `evidence_level`) is the citation for that context.\n\n## What this skill does NOT do\n\n- Does not download PDFs or use unauthorized mirrors (full text via open PMC or a connected Paperclip service only)\n- Does not perform formal risk-of-bias or quality appraisal (it records design and obvious bias flags only)\n- Does not pool effect sizes (use the `method-meta-analysis` skill)\n- Does not match the study to a checklist (use the `method-checklist` skill)\n\n## References\n\n@.\u002Freferences\u002Fextraction-prompts.md\n\n@.\u002Freferences\u002Fmethod-taxonomy.md\n",{"name":5,"description":7,"argument-hint":49},"\u003Cpath\u002Fto\u002Fpubmed-results.csv>, optional: --full-text-only --max 25","main","893bccb980e4dce1345919e9f675f5a9dcbed364","plugins\u002Fmethodsmith\u002Fskills\u002Fmethod-extract",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":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add sajor2000\u002Fmethodsmith --skill method-extract",{"tool":65,"command":66},"bunx","bunx skills add sajor2000\u002Fmethodsmith --skill method-extract",{"tool":68,"command":69},"pnpm","pnpm dlx skills add sajor2000\u002Fmethodsmith --skill method-extract","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-extract\u002FSKILL.md",true,[73,79,83],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fevidence-access.md","REFERENCE","参考文档",2208,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-extract\u002Freferences\u002Fevidence-access.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fextraction-prompts.md",2059,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-extract\u002Freferences\u002Fextraction-prompts.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fmethod-taxonomy.md",1596,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-extract\u002Freferences\u002Fmethod-taxonomy.md",[88,102,116,127,136,145],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":97,"publishedAt":44},"01M71QQY0KE1184AF58EC1J5C1","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[98,99,100,101],"one","skill one","sample","sample skill",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":109,"publishedAt":44},"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",[108],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[110,111,112,113,114,115],"disabled skill","a skill","with model","with","true","model",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":123,"publishedAt":44},"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",[122],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[124,125,42,111,126],"claude only","claude only skill","code",{"skillNo":128,"name":129,"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":130,"categories":131,"keywords":133,"publishedAt":44},"01M71QQRPZ76X623V5P7T1E3DD","default-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[132],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[134,135],"default","default skill",{"skillNo":137,"name":138,"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":139,"categories":140,"keywords":142,"publishedAt":44},"01M71QQQG3FF2HFQHVH8VHA08R","custom-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[141],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[143,144],"custom skill","custom",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":44},"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",[],[152,153,154,155,156,157,31,41,158,159,113,160,161,162],"write","method write","point","evidence","entry","claim","provenance","reviewer","scientific","prose","drafts"]