[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71QM9BHRXZEW7582K1JXPES":3,"skill-same:01M71QM9BHRXZEW7582K1JXPES":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},"01M71QM9BHRXZEW7582K1JXPES","method-omics-qc",null,"Runs sequencing and omics QA: FASTQ, BAM\u002FCRAM, VCF, count matrices, methylation arrays, sample swaps, batch confounding. Use when omics data needs QC before analysis.","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-omics-qc\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"method omics qc","qc","omics","bam","atac","use","methylation","FASTQ","count","rnaseq","data","swaps","sample","batch","analysis","vcf","when","sequencing","qa","arrays","2026-11-10 13:02:02",false,"---\nname: method-omics-qc\ndescription: \"Runs sequencing and omics QA: FASTQ, BAM\u002FCRAM, VCF, count matrices, methylation arrays, sample swaps, batch confounding. Use when omics data needs QC before analysis.\"\nargument-hint: \"\u003Cdata dir or sample sheet>, optional: --modality wgs|wes|rnaseq|chipseq|methyl|atac\"\n---\n\n# Bioinformatics Data QA Gate\n\n\n## Skill Value\n\n- **Problem it solves:** Sequencing and omics projects can move into analysis before raw data quality, sample identity, and batch confounding are checked.\n- **Use when:** The user mentions FASTQ, BAM\u002FCRAM, VCF, RNA-seq, WGS\u002FWES, ATAC-seq, methylation arrays, FastQC, MultiQC, sample swaps, or omics batch effects.\n- **Output:** A GO\u002FNO-GO omics QA summary with modality-specific checks and blockers for downstream analysis.\n- **Ask only if:** Only when modality, sample sheet, batch variable, or case\u002Fcontrol grouping cannot be inferred.\n- **Do not do:** Do not run differential expression, association testing, or clinical interpretation.\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\nThe omics counterpart to `method-data-qa`. Sequencing and array data fail in domain-specific ways (low base quality, adapter contamination, sample swaps, batch confounds with condition); this skill runs the right QC for the modality.\n\n## When this skill activates\n\n- A new sequencing run \u002F array batch was just registered as a data wave\n- Before differential expression \u002F variant calling \u002F methylation analysis\n- After a re-sequence following a sample-quality-fail\n- Before sharing data to a collaborator (sanity check)\n- Manual: `method-omics-qc \u002Fdata\u002Fruns\u002Frun_2025_04 --modality rnaseq`\n\n## Prerequisites\n\n- A sample sheet (CSV\u002FTSV) listing samples, files, and at minimum a `condition` and `batch` column\n- Tools available locally OR via Conda: `fastqc`, `multiqc`, `samtools`, `picard`, `mosdepth`, `somalier` (sample swap), `picard CrosscheckFingerprints`\n- For methylation: `minfi` \u002F `sesame` (R)\n- For RNA-seq: `salmon` or `STAR` outputs (or raw FASTQ)\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:** modality-specific QC benchmarks (depth, mapping and duplicate rates, contamination, rRNA and intergenic fractions, detection p-values, FRiP\u002FTSS enrichment, mitochondrial fraction, Ti\u002FTv) and batch-effect test conventions; every threshold the report applies is either cited by PMID (tool manuals count as `documentation`) or marked `project default`.\n\n## Core workflow\n\n### Step 1: Modality detection\n\nIf `--modality` not passed, sniff the file extensions and tool outputs:\n- `*.fastq.gz` only → fastq stage\n- `*.bam` \u002F `*.cram` → alignment stage\n- counts matrix (`counts.tsv`, `salmon.sf`) → quantification stage\n- `.idat` \u002F `_Methylation_*.csv` → methylation array\n- VCF → variant calling stage\n\nDifferent modality → different checks. Refuse to proceed if conflicting signals (mixed FASTQ + count matrix without explicit modality).\n\n### Step 2: Run modality-specific checks\n\n| Modality | Tool | Check |\n|----------|------|-------|\n| FASTQ (any) | FastQC | per-base quality, adapter content, GC distribution, kmer content |\n| FASTQ (any) | MultiQC | aggregate report; sample-to-sample outliers |\n| BAM (WGS\u002FWES) | samtools flagstat | mapping rate, duplicate rate, paired-properly rate |\n| BAM (WGS\u002FWES) | mosdepth | coverage uniformity, mean depth, % on-target |\n| BAM (RNA-seq) | RSeQC \u002F Picard CollectRnaSeqMetrics | strand specificity, intronic\u002Fintergenic % |\n| BAM (any) | somalier extract + relate | sample swap detection (genotype concordance to expected sex \u002F pedigree) |\n| BAM (any) | Picard CrosscheckFingerprints | sample swap via fingerprint VCF if available |\n| Counts matrix | DESeq2 `vst()`\u002F`rlog()` or edgeR `cpm(log = TRUE)`, then PCA (not raw counts) | sample clustering vs declared condition \u002F batch |\n| Counts matrix | `sva::num.sv` \u002F `svaseq`, `RUVSeq::RUVg` diagnostics | surrogate-variable \u002F unwanted-variation detection (report only; correction is a downstream choice) |\n| Methylation IDAT | minfi qcReport | bisulfite conversion efficiency, detection p-value |\n| Methylation array | sesame | sex-prediction discordance |\n| VCF | bcftools stats | Ti\u002FTv ratio, het\u002Fhom ratio, novel variant fraction |\n\n### Step 3: Batch-effect screening (no removal)\n\nAlways inspect the sample-design cross-tabulation, rank of `~ batch + condition`, and estimability of the intended contrast before expression PCA. Complete aliasing is a P0 blocker even when PC1\u002FPC2 show no batch separation; larger unrelated variation can hide it in later PCs. Then run PCA on variance-stabilized\u002Flog-CPM counts or the appropriate transformed assay matrix, colored by batch and condition. Grade partial association with Cramér's V (equivalent to |phi| for two-level factors), using the project-default thresholds in `references\u002Fbatch-confound-rules.md`: V above 0.5 is a P0 review flag; 0.3-0.5 is a P1 warning. V and PCA cannot establish identifiability; distinguish a full-rank but unbalanced design from a non-estimable contrast. For full aliasing, report:\n\n> Batch is confounded with condition. No correction, matching, or stable result after deleting a batch identifies this contrast under full aliasing. Re-block\u002Frecollect, or restrict to a different contrast that actually has within-batch support. For an identifiable partially confounded design, model batch in the differential-analysis design (`~ batch + condition`) rather than testing a batch-corrected matrix.\n\n### Step 4: Sample swap screening\n\nFor BAM data, run somalier `relate` against the expected pedigree (or against declared sample sex). For each sample where the predicted sex \u002F kinship doesn't match the sample sheet → P0 finding `sample-swap-suspected`.\n\n### Step 5: Report\n\nWrite `reports\u002Fbioinfo-qa\u002F\u003Cwave_id>.html` (MultiQC-rendered) and `reports\u002Fbioinfo-qa\u002F\u003Cwave_id>.md` summary:\n\n1. Modality and N samples\n2. Per-sample pass\u002Fwarn\u002Ffail table, naming each threshold's source (PMID or `project default`)\n3. Batch confound assessment\n4. Sample swap assessment\n5. Aggregate metrics (mean coverage, mean Q score, % aligned, etc.)\n6. Sign-off block\n\n### Step 6: Emit GO\u002FNO-GO\n\n`__CE_BIOINFO_QC_PASS__` or `__CE_BIOINFO_QC_FAIL__ wave=\u003Cid> blockers=\u003Ccount>`\n\nCompletion check: every fail row names its threshold source (PMID or `project default`); a missing tool is reported as \"check not run\", never as pass.\n\n## What this skill does NOT do\n\n- Does not modify the data (read-only)\n- Does not remove batch effects (only flags; removal is a downstream choice)\n- Does not call variants or quantify expression (use a pipeline reviewed by `method-bioinfo-pipeline-reviewer`)\n- Does not de-identify (genomic data has its own re-identification rules; consult IRB)\n\n## References\n\n@.\u002Freferences\u002Fmodality-checks.md\n\n@.\u002Freferences\u002Fbatch-confound-rules.md\n","# Bioinformatics Data QA Gate\n\n\n## Skill Value\n\n- **Problem it solves:** Sequencing and omics projects can move into analysis before raw data quality, sample identity, and batch confounding are checked.\n- **Use when:** The user mentions FASTQ, BAM\u002FCRAM, VCF, RNA-seq, WGS\u002FWES, ATAC-seq, methylation arrays, FastQC, MultiQC, sample swaps, or omics batch effects.\n- **Output:** A GO\u002FNO-GO omics QA summary with modality-specific checks and blockers for downstream analysis.\n- **Ask only if:** Only when modality, sample sheet, batch variable, or case\u002Fcontrol grouping cannot be inferred.\n- **Do not do:** Do not run differential expression, association testing, or clinical interpretation.\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\nThe omics counterpart to `method-data-qa`. Sequencing and array data fail in domain-specific ways (low base quality, adapter contamination, sample swaps, batch confounds with condition); this skill runs the right QC for the modality.\n\n## When this skill activates\n\n- A new sequencing run \u002F array batch was just registered as a data wave\n- Before differential expression \u002F variant calling \u002F methylation analysis\n- After a re-sequence following a sample-quality-fail\n- Before sharing data to a collaborator (sanity check)\n- Manual: `method-omics-qc \u002Fdata\u002Fruns\u002Frun_2025_04 --modality rnaseq`\n\n## Prerequisites\n\n- A sample sheet (CSV\u002FTSV) listing samples, files, and at minimum a `condition` and `batch` column\n- Tools available locally OR via Conda: `fastqc`, `multiqc`, `samtools`, `picard`, `mosdepth`, `somalier` (sample swap), `picard CrosscheckFingerprints`\n- For methylation: `minfi` \u002F `sesame` (R)\n- For RNA-seq: `salmon` or `STAR` outputs (or raw FASTQ)\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:** modality-specific QC benchmarks (depth, mapping and duplicate rates, contamination, rRNA and intergenic fractions, detection p-values, FRiP\u002FTSS enrichment, mitochondrial fraction, Ti\u002FTv) and batch-effect test conventions; every threshold the report applies is either cited by PMID (tool manuals count as `documentation`) or marked `project default`.\n\n## Core workflow\n\n### Step 1: Modality detection\n\nIf `--modality` not passed, sniff the file extensions and tool outputs:\n- `*.fastq.gz` only → fastq stage\n- `*.bam` \u002F `*.cram` → alignment stage\n- counts matrix (`counts.tsv`, `salmon.sf`) → quantification stage\n- `.idat` \u002F `_Methylation_*.csv` → methylation array\n- VCF → variant calling stage\n\nDifferent modality → different checks. Refuse to proceed if conflicting signals (mixed FASTQ + count matrix without explicit modality).\n\n### Step 2: Run modality-specific checks\n\n| Modality | Tool | Check |\n|----------|------|-------|\n| FASTQ (any) | FastQC | per-base quality, adapter content, GC distribution, kmer content |\n| FASTQ (any) | MultiQC | aggregate report; sample-to-sample outliers |\n| BAM (WGS\u002FWES) | samtools flagstat | mapping rate, duplicate rate, paired-properly rate |\n| BAM (WGS\u002FWES) | mosdepth | coverage uniformity, mean depth, % on-target |\n| BAM (RNA-seq) | RSeQC \u002F Picard CollectRnaSeqMetrics | strand specificity, intronic\u002Fintergenic % |\n| BAM (any) | somalier extract + relate | sample swap detection (genotype concordance to expected sex \u002F pedigree) |\n| BAM (any) | Picard CrosscheckFingerprints | sample swap via fingerprint VCF if available |\n| Counts matrix | DESeq2 `vst()`\u002F`rlog()` or edgeR `cpm(log = TRUE)`, then PCA (not raw counts) | sample clustering vs declared condition \u002F batch |\n| Counts matrix | `sva::num.sv` \u002F `svaseq`, `RUVSeq::RUVg` diagnostics | surrogate-variable \u002F unwanted-variation detection (report only; correction is a downstream choice) |\n| Methylation IDAT | minfi qcReport | bisulfite conversion efficiency, detection p-value |\n| Methylation array | sesame | sex-prediction discordance |\n| VCF | bcftools stats | Ti\u002FTv ratio, het\u002Fhom ratio, novel variant fraction |\n\n### Step 3: Batch-effect screening (no removal)\n\nAlways inspect the sample-design cross-tabulation, rank of `~ batch + condition`, and estimability of the intended contrast before expression PCA. Complete aliasing is a P0 blocker even when PC1\u002FPC2 show no batch separation; larger unrelated variation can hide it in later PCs. Then run PCA on variance-stabilized\u002Flog-CPM counts or the appropriate transformed assay matrix, colored by batch and condition. Grade partial association with Cramér's V (equivalent to |phi| for two-level factors), using the project-default thresholds in `references\u002Fbatch-confound-rules.md`: V above 0.5 is a P0 review flag; 0.3-0.5 is a P1 warning. V and PCA cannot establish identifiability; distinguish a full-rank but unbalanced design from a non-estimable contrast. For full aliasing, report:\n\n> Batch is confounded with condition. No correction, matching, or stable result after deleting a batch identifies this contrast under full aliasing. Re-block\u002Frecollect, or restrict to a different contrast that actually has within-batch support. For an identifiable partially confounded design, model batch in the differential-analysis design (`~ batch + condition`) rather than testing a batch-corrected matrix.\n\n### Step 4: Sample swap screening\n\nFor BAM data, run somalier `relate` against the expected pedigree (or against declared sample sex). For each sample where the predicted sex \u002F kinship doesn't match the sample sheet → P0 finding `sample-swap-suspected`.\n\n### Step 5: Report\n\nWrite `reports\u002Fbioinfo-qa\u002F\u003Cwave_id>.html` (MultiQC-rendered) and `reports\u002Fbioinfo-qa\u002F\u003Cwave_id>.md` summary:\n\n1. Modality and N samples\n2. Per-sample pass\u002Fwarn\u002Ffail table, naming each threshold's source (PMID or `project default`)\n3. Batch confound assessment\n4. Sample swap assessment\n5. Aggregate metrics (mean coverage, mean Q score, % aligned, etc.)\n6. Sign-off block\n\n### Step 6: Emit GO\u002FNO-GO\n\n`__CE_BIOINFO_QC_PASS__` or `__CE_BIOINFO_QC_FAIL__ wave=\u003Cid> blockers=\u003Ccount>`\n\nCompletion check: every fail row names its threshold source (PMID or `project default`); a missing tool is reported as \"check not run\", never as pass.\n\n## What this skill does NOT do\n\n- Does not modify the data (read-only)\n- Does not remove batch effects (only flags; removal is a downstream choice)\n- Does not call variants or quantify expression (use a pipeline reviewed by `method-bioinfo-pipeline-reviewer`)\n- Does not de-identify (genomic data has its own re-identification rules; consult IRB)\n\n## References\n\n@.\u002Freferences\u002Fmodality-checks.md\n\n@.\u002Freferences\u002Fbatch-confound-rules.md\n",{"name":5,"description":7,"argument-hint":49},"\u003Cdata dir or sample sheet>, optional: --modality wgs|wes|rnaseq|chipseq|methyl|atac","main","893bccb980e4dce1345919e9f675f5a9dcbed364","plugins\u002Fmethodsmith\u002Fskills\u002Fmethod-omics-qc",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-omics-qc",{"tool":65,"command":66},"bunx","bunx skills add sajor2000\u002Fmethodsmith --skill method-omics-qc",{"tool":68,"command":69},"pnpm","pnpm dlx skills add sajor2000\u002Fmethodsmith --skill method-omics-qc","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-omics-qc\u002FSKILL.md",true,[73,79,83],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fbatch-confound-rules.md","REFERENCE","参考文档",3576,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-omics-qc\u002Freferences\u002Fbatch-confound-rules.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fevidence-access.md",2208,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-omics-qc\u002Freferences\u002Fevidence-access.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fmodality-checks.md",3105,"https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Fplugins\u002Fmethodsmith\u002Fskills\u002Fmethod-omics-qc\u002Freferences\u002Fmodality-checks.md",[88,103,117,129,138,147],{"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":99,"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":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[100,101,36,102],"one","skill one","sample skill",{"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":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",[109],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[111,112,113,114,115,116],"disabled skill","a skill","with model","with","true","model",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":124,"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",[123],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[125,126,127,112,128],"claude only","claude only skill","only","code",{"skillNo":130,"name":131,"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":132,"categories":133,"keywords":135,"publishedAt":44},"01M71QQRPZ76X623V5P7T1E3DD","default-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[134],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[136,137],"default","default skill",{"skillNo":139,"name":140,"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":141,"categories":142,"keywords":144,"publishedAt":44},"01M71QQQG3FF2HFQHVH8VHA08R","custom-skill","https:\u002F\u002Fgithub.com\u002Fsajor2000\u002Fmethodsmith\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[143],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[145,146],"custom skill","custom",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"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",[],[154,155,156,157,158,159,29,40,160,161,114,162,163,164],"write","method write","point","evidence","entry","claim","provenance","reviewer","scientific","prose","drafts"]