[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71QJSXF4HCF99JJ51EZV4J2":3,"skill-same:01M71QJSXF4HCF99JJ51EZV4J2":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":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M71QJSXF4HCF99JJ51EZV4J2","method-genome-build",null,"Pins genome build, annotation release, contig naming, and liftover for genomics data. Use when the user mentions GRCh37\u002F38, hg19\u002Fhg38, T2T, GENCODE\u002FEnsembl versions, or liftover.","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-genome-build\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"method genome build","build","for","use","when","check","naming","genomics","release","FASTA","contig","data","Ensembl","annotation","user","path","2026-11-10 13:02:02",false,"---\nname: method-genome-build\ndescription: \"Pins genome build, annotation release, contig naming, and liftover for genomics data. Use when the user mentions GRCh37\u002F38, hg19\u002Fhg38, T2T, GENCODE\u002FEnsembl versions, or liftover.\"\nargument-hint: \"[--ref-fasta path, --annotation-gtf path, --check]\"\n---\n\n# Genome Build Traceability\n\n\n## Skill Value\n\n- **Problem it solves:** Genomics analyses silently break when build, annotation, or contig conventions drift.\n- **Use when:** The user mentions genome build, GRCh37\u002F38, hg19\u002Fhg38, annotation versions, liftover, or VCF\u002FBAM compatibility.\n- **Output:** Genome-build decision record with reference sources and downstream constraints.\n- **Ask only if:** Only when build, annotation source, or target assay cannot be inferred.\n- **Do not do:** Do not run variant analysis or liftover without explicit workflow scope.\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\nPins the reference genome and annotation versions used in a bioinformatics study, and audits every output for build consistency. Without this, a paper claiming \"we used GRCh38\" can have outputs silently aligned to GRCh37 because a single tool defaulted to its bundled reference.\n\n## When this skill activates\n\n- Start of a new bioinformatics study (declare the build)\n- After a reference update (re-declare and audit)\n- Manual: `method-genome-build --check` to audit; `method-genome-build --ref-fasta refs\u002FGRCh38.fa --annotation-gtf refs\u002Fgencode.v44.gtf` to declare\n\n## Prerequisites\n\n- Reference FASTA file (or path to a reference manifest if using shared references)\n- Annotation file (GTF \u002F GFF \u002F BED)\n- Tools to inspect BAM headers: `samtools view -H`\n- Tools to inspect VCF headers: `bcftools view -h`\n\n## Core workflow\n\n### Step 1: Declare the build (`--ref-fasta` \u002F `--annotation-gtf`)\n\nHash the reference FASTA and establish the assembly from source provenance, diagnostic contig lengths and available sequence checksums. A first contig name or `chr` prefix does not identify a genome build.\n\nThe values below are an illustrative example (GENCODE 44, equivalent to Ensembl release 110); resolve the current release, URLs, md5s, and counts for the build you actually declare rather than copying these.\n\n```yaml\ngenome_build:\n  build: GRCh38\n  patch: GRCh38.p14\n  source: https:\u002F\u002Fftp.ebi.ac.uk\u002Fpub\u002Fdatabases\u002Fgencode\u002FGencode_human\u002Frelease_44\u002FGRCh38.primary_assembly.genome.fa.gz\n  fasta_md5: \u003Cmd5 of unzipped FASTA>\n  contigs:\n    primary: [\"chr1\", \"chr2\", ..., \"chrX\", \"chrY\", \"chrM\"]   # GENCODE\u002FUCSC naming; Ensembl FASTAs use 1..22, X, Y, MT\n    alt_count: 0   # primary_assembly FASTA; the full GRCh38 assembly adds 261 ALT loci\n  annotation:\n    name: GENCODE\n    version: 44\n    source_url: https:\u002F\u002Fftp.ebi.ac.uk\u002Fpub\u002Fdatabases\u002Fgencode\u002FGencode_human\u002Frelease_44\u002Fgencode.v44.annotation.gtf.gz\n    md5: \u003Cmd5>\n    gene_count: 62700\n    transcript_count: 252835   # GENCODE 44 statistics page\ndeclared_at: \u003CISO8601>\ndeclared_by: \u003Cuser>\n```\n\nWrite to `analysis\u002Fgenome-build\u002Fmanifest.yaml`. Commit this; it is the build-truth for the study.\n\n### Step 2: Audit mode (--check)\n\nWalk the project for build artifacts. Compare available provenance, diagnostic contig lengths and checksums with the manifest using `references\u002Fbuild-detection-rules.md`; naming supports consistency checks but cannot identify a build alone.\n\n| Artifact | Inspect | Expect |\n|----------|---------|--------|\n| BAM \u002F CRAM | `@SQ` lines (reference contig names + LN lengths) | Match manifest contigs and lengths |\n| BAM \u002F CRAM | `@PG` lines | Tool used to align, version |\n| VCF | `##contig=\u003CID=...,length=...,assembly=...>` | Match manifest |\n| VCF | `##reference=` | URL or path matches manifest source |\n| BED \u002F Interval list | First contig name format (chr1 vs 1) | Consistent with manifest contig style |\n| Counts matrix (RNA-seq) | rownames or `gene_id` column format | Match annotation gene_ids (e.g., ENSG00000... if Ensembl) |\n| Variant call output | `INFO\u002FCSQ` annotation source if VEP | VEP cache version matches manifest |\n\nFor each file, record whether its build evidence is compatible, incompatible, unknown or uninspected. Flag mismatches:\n\n- **P0:** Different build between BAM and VCF (alignment in GRCh38, called against GRCh37 reference)\n- **P0:** Annotation version drift (Counts matrix uses GENCODE 36 but manifest says GENCODE 44)\n- **P1:** Contig naming inconsistency (chr1 vs 1) -- usually fixable but breaks tools\n- **P1:** Tool version not recorded in `@PG` lines\n\n### Step 3: Per-output traceability table\n\nProduce `analysis\u002Fgenome-build\u002Ftraceability.csv`:\n\n| output_file | build | annotation | tool | tool_version | match_manifest |\n|-------------|-------|------------|------|--------------|----------------|\n| variants\u002Fcohort.vcf.gz | GRCh38 | -- | GATK | 4.5.0 | yes |\n| counts\u002Fgene-counts.tsv | -- | GENCODE 44 | featureCounts | 2.0.6 | yes |\n| methylation\u002Fbeta.csv | -- | EPIC v1 | sesame | 1.20 | yes |\n\nThis table goes into the manuscript as a supplementary file -- it answers \"what build did you use?\" verifiably.\n\n### Step 4: Surface mismatches\n\nIf `--check` found any issue, exit non-zero and print a clear report. Resolve every issue before declaring the audit complete.\n\n## What this skill does NOT do\n\n- Does not re-align or re-call (that's a pipeline run)\n- Does not download references (user supplies paths)\n- Does not validate reference correctness against external truth -- only internal consistency\n\n## References\n\n`scripts\u002Faudit_build.py` supports Step 2 with build declarations, diagnostic chromosome-1\u002F8 lengths, available chromosome-1 MD5s, and naming consistency. `--declared` accepts `GRCh37`, `GRCh38` and `T2T` (requires an explicit CHM13\u002FT2T v2.0 declaration; diagnostic lengths support that version only). Each file is `verified` for compatible header evidence, `incompatible`, `unknown`, or `uninspected`; this does not establish complete sequence identity or annotation-release parity. Missing tools, absent evidence, unsupported T2T versions, or no inspected files block a clean result. It writes YAML (JSON for a `.json` destination), a Markdown report, and `__CE_GENOME_BUILD__ declared=\u003Cbuild> files=\u003Cn> issues=\u003Cn> manifest=\u003Cpath> report=\u003Cpath>`. Exit 2 requires resolution, including P1 naming issues; a prefix difference alone is not a build mismatch. Complete the other Step 2 manual checks before declaring the audit complete. `--manifest` is overwritten, so never point it at `analysis\u002Fgenome-build\u002Fmanifest.yaml`:\n\n```bash\nSKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";\npython3 \"$SKILL_DIR\u002Fscripts\u002Faudit_build.py\" \u003Cproject-dir> --declared GRCh38 --manifest analysis\u002Fgenome-build\u002Faudit-findings.yaml --report analysis\u002Fgenome-build\u002Faudit-report.md\n```\n\n`references\u002Fbuild-detection-rules.md` — build inference rules used in Step 2.\n","# Genome Build Traceability\n\n\n## Skill Value\n\n- **Problem it solves:** Genomics analyses silently break when build, annotation, or contig conventions drift.\n- **Use when:** The user mentions genome build, GRCh37\u002F38, hg19\u002Fhg38, annotation versions, liftover, or VCF\u002FBAM compatibility.\n- **Output:** Genome-build decision record with reference sources and downstream constraints.\n- **Ask only if:** Only when build, annotation source, or target assay cannot be inferred.\n- **Do not do:** Do not run variant analysis or liftover without explicit workflow scope.\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\nPins the reference genome and annotation versions used in a bioinformatics study, and audits every output for build consistency. Without this, a paper claiming \"we used GRCh38\" can have outputs silently aligned to GRCh37 because a single tool defaulted to its bundled reference.\n\n## When this skill activates\n\n- Start of a new bioinformatics study (declare the build)\n- After a reference update (re-declare and audit)\n- Manual: `method-genome-build --check` to audit; `method-genome-build --ref-fasta refs\u002FGRCh38.fa --annotation-gtf refs\u002Fgencode.v44.gtf` to declare\n\n## Prerequisites\n\n- Reference FASTA file (or path to a reference manifest if using shared references)\n- Annotation file (GTF \u002F GFF \u002F BED)\n- Tools to inspect BAM headers: `samtools view -H`\n- Tools to inspect VCF headers: `bcftools view -h`\n\n## Core workflow\n\n### Step 1: Declare the build (`--ref-fasta` \u002F `--annotation-gtf`)\n\nHash the reference FASTA and establish the assembly from source provenance, diagnostic contig lengths and available sequence checksums. A first contig name or `chr` prefix does not identify a genome build.\n\nThe values below are an illustrative example (GENCODE 44, equivalent to Ensembl release 110); resolve the current release, URLs, md5s, and counts for the build you actually declare rather than copying these.\n\n```yaml\ngenome_build:\n  build: GRCh38\n  patch: GRCh38.p14\n  source: https:\u002F\u002Fftp.ebi.ac.uk\u002Fpub\u002Fdatabases\u002Fgencode\u002FGencode_human\u002Frelease_44\u002FGRCh38.primary_assembly.genome.fa.gz\n  fasta_md5: \u003Cmd5 of unzipped FASTA>\n  contigs:\n    primary: [\"chr1\", \"chr2\", ..., \"chrX\", \"chrY\", \"chrM\"]   # GENCODE\u002FUCSC naming; Ensembl FASTAs use 1..22, X, Y, MT\n    alt_count: 0   # primary_assembly FASTA; the full GRCh38 assembly adds 261 ALT loci\n  annotation:\n    name: GENCODE\n    version: 44\n    source_url: https:\u002F\u002Fftp.ebi.ac.uk\u002Fpub\u002Fdatabases\u002Fgencode\u002FGencode_human\u002Frelease_44\u002Fgencode.v44.annotation.gtf.gz\n    md5: \u003Cmd5>\n    gene_count: 62700\n    transcript_count: 252835   # GENCODE 44 statistics page\ndeclared_at: \u003CISO8601>\ndeclared_by: \u003Cuser>\n```\n\nWrite to `analysis\u002Fgenome-build\u002Fmanifest.yaml`. Commit this; it is the build-truth for the study.\n\n### Step 2: Audit mode (--check)\n\nWalk the project for build artifacts. Compare available provenance, diagnostic contig lengths and checksums with the manifest using `references\u002Fbuild-detection-rules.md`; naming supports consistency checks but cannot identify a build alone.\n\n| Artifact | Inspect | Expect |\n|----------|---------|--------|\n| BAM \u002F CRAM | `@SQ` lines (reference contig names + LN lengths) | Match manifest contigs and lengths |\n| BAM \u002F CRAM | `@PG` lines | Tool used to align, version |\n| VCF | `##contig=\u003CID=...,length=...,assembly=...>` | Match manifest |\n| VCF | `##reference=` | URL or path matches manifest source |\n| BED \u002F Interval list | First contig name format (chr1 vs 1) | Consistent with manifest contig style |\n| Counts matrix (RNA-seq) | rownames or `gene_id` column format | Match annotation gene_ids (e.g., ENSG00000... if Ensembl) |\n| Variant call output | `INFO\u002FCSQ` annotation source if VEP | VEP cache version matches manifest |\n\nFor each file, record whether its build evidence is compatible, incompatible, unknown or uninspected. Flag mismatches:\n\n- **P0:** Different build between BAM and VCF (alignment in GRCh38, called against GRCh37 reference)\n- **P0:** Annotation version drift (Counts matrix uses GENCODE 36 but manifest says GENCODE 44)\n- **P1:** Contig naming inconsistency (chr1 vs 1) -- usually fixable but breaks tools\n- **P1:** Tool version not recorded in `@PG` lines\n\n### Step 3: Per-output traceability table\n\nProduce `analysis\u002Fgenome-build\u002Ftraceability.csv`:\n\n| output_file | build | annotation | tool | tool_version | match_manifest |\n|-------------|-------|------------|------|--------------|----------------|\n| variants\u002Fcohort.vcf.gz | GRCh38 | -- | GATK | 4.5.0 | yes |\n| counts\u002Fgene-counts.tsv | -- | GENCODE 44 | featureCounts | 2.0.6 | yes |\n| methylation\u002Fbeta.csv | -- | EPIC v1 | sesame | 1.20 | yes |\n\nThis table goes into the manuscript as a supplementary file -- it answers \"what build did you use?\" verifiably.\n\n### Step 4: Surface mismatches\n\nIf `--check` found any issue, exit non-zero and print a clear report. Resolve every issue before declaring the audit complete.\n\n## What this skill does NOT do\n\n- Does not re-align or re-call (that's a pipeline run)\n- Does not download references (user supplies paths)\n- Does not validate reference correctness against external truth -- only internal consistency\n\n## References\n\n`scripts\u002Faudit_build.py` supports Step 2 with build declarations, diagnostic chromosome-1\u002F8 lengths, available chromosome-1 MD5s, and naming consistency. `--declared` accepts `GRCh37`, `GRCh38` and `T2T` (requires an explicit CHM13\u002FT2T v2.0 declaration; diagnostic lengths support that version only). Each file is `verified` for compatible header evidence, `incompatible`, `unknown`, or `uninspected`; this does not establish complete sequence identity or annotation-release parity. Missing tools, absent evidence, unsupported T2T versions, or no inspected files block a clean result. It writes YAML (JSON for a `.json` destination), a Markdown report, and `__CE_GENOME_BUILD__ declared=\u003Cbuild> files=\u003Cn> issues=\u003Cn> manifest=\u003Cpath> report=\u003Cpath>`. Exit 2 requires resolution, including P1 naming issues; a prefix difference alone is not a build mismatch. Complete the other Step 2 manual checks before declaring the audit complete. `--manifest` is overwritten, so never point it at `analysis\u002Fgenome-build\u002Fmanifest.yaml`:\n\n```bash\nSKILL_DIR=\"\u003Cabsolute path of the directory containing this SKILL.md>\";\npython3 \"$SKILL_DIR\u002Fscripts\u002Faudit_build.py\" \u003Cproject-dir> --declared GRCh38 --manifest analysis\u002Fgenome-build\u002Faudit-findings.yaml --report analysis\u002Fgenome-build\u002Faudit-report.md\n```\n\n`references\u002Fbuild-detection-rules.md` — build inference rules used in Step 2.\n",{"name":5,"description":7,"argument-hint":40},"[--ref-fasta path, --annotation-gtf path, --check]","main","893bccb980e4dce1345919e9f675f5a9dcbed364","plugins\u002Fmethodsmith\u002Fskills\u002Fmethod-genome-build",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add sajor2000\u002Fmethodsmith --skill method-genome-build",{"tool":56,"command":57},"bunx","bunx skills add sajor2000\u002Fmethodsmith --skill method-genome-build",{"tool":59,"command":60},"pnpm","pnpm dlx skills add sajor2000\u002Fmethodsmith --skill method-genome-build","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-genome-build\u002FSKILL.md",true,[64,70],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fbuild-detection-rules.md","REFERENCE","参考文档",2856,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-genome-build\u002Freferences\u002Fbuild-detection-rules.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Faudit_build.py","SCRIPT","脚本",11984,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-genome-build\u002Fscripts\u002Faudit_build.py",[77,93,107,119,128,137],{"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":88,"publishedAt":35},"01M71QQY0KE1184AF58EC1J5C1","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[89,90,91,92],"one","skill one","sample","sample skill",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":100,"publishedAt":35},"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",[99],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[101,102,103,104,105,106],"disabled skill","a skill","with model","with","true","model",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":35},"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",[113],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[115,116,117,102,118],"claude only","claude only skill","only","code",{"skillNo":120,"name":121,"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":122,"categories":123,"keywords":125,"publishedAt":35},"01M71QQRPZ76X623V5P7T1E3DD","default-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[124],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[126,127],"default","default skill",{"skillNo":129,"name":130,"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":131,"categories":132,"keywords":134,"publishedAt":35},"01M71QQQG3FF2HFQHVH8VHA08R","custom-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[133],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[135,136],"custom skill","custom",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":35},"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",[],[144,145,146,147,148,149,22,23,150,151,104,152,153,154],"write","method write","point","evidence","entry","claim","provenance","reviewer","scientific","prose","drafts"]