[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EFCVY2148AZT2G31MP5ZXC":3,"skill-same:01M7EFCVY2148AZT2G31MP5ZXC":66},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7EFCVY2148AZT2G31MP5ZXC","bio-rna-quantification-featurecounts-counting",null,"Count reads per gene from aligned BAM files using Subread featureCounts. Use when turning STAR\u002FHISAT2 BAMs into a gene-level count matrix for DESeq2\u002FedgeR, deciding library strandedness, handling paired-end fragment counting, choosing how to treat multi-mapping and multi-overlapping reads, or diagnosing a low assignment rate from the summary file.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-rna-quantification-featurecounts-counting\ndescription: Count reads per gene from aligned BAM files using Subread featureCounts. Use when turning STAR\u002FHISAT2 BAMs into a gene-level count matrix for DESeq2\u002FedgeR, deciding library strandedness, handling paired-end fragment counting, choosing how to treat multi-mapping and multi-overlapping reads, or diagnosing a low assignment rate from the summary file.\ntool_type: cli\nprimary_tool: featureCounts\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"rna-quantification\u002Ffeaturecounts-counting\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: Subread 2.0+, STAR 2.7.11+, HISAT2 2.2.1+, DESeq2 1.42+, edgeR 4.0+, pandas 2.2+\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- CLI: `\u003Ctool> --version` then `\u003Ctool> --help` to confirm flags\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n\nIf code throws ImportError, AttributeError, or TypeError, introspect the installed\npackage and adapt the example to match the actual API rather than retrying.\n\n# featureCounts Counting\n\n**\"Count reads per gene from my BAM files\"** -> Assign each aligned read to at most one gene by overlap with a GTF, discarding ambiguous reads, to produce an integer gene-by-sample matrix for differential expression.\n- CLI: `featureCounts -a genes.gtf -o counts.txt sample1.bam sample2.bam`\n\nfeatureCounts is bookkeeping, not inference: it tallies reads to genes and discards anything ambiguous. That is correct for gene-level DE, where almost every read's gene of origin is unambiguous even when its isoform is not. The two settings that silently corrupt the matrix if wrong are strandedness (`-s`) and, for paired-end data, fragment counting (`--countReadPairs`).\n\n## Basic Usage\n\n```bash\n# Multiple samples in one run -> a single aligned matrix (recommended)\nfeatureCounts -a annotation.gtf -o counts.txt sample1.bam sample2.bam sample3.bam\n\n# Defaults: -t exon -g gene_id (count reads over exons, aggregate by gene)\n```\n\n## Decision 1: strandedness (`-s`) is the load-bearing setting\n\n| `-s` | Meaning | Read 1 |\n|------|---------|--------|\n| 0 | Unstranded | strand ignored |\n| 1 | Forward stranded | read 1 is sense |\n| 2 | Reverse stranded | read 1 is antisense; read 2 is sense |\n\nThe dominant chemistry, dUTP \u002F Illumina TruSeq Stranded \u002F NEBNext Directional, is reverse, `-s 2`. Setting the wrong strand does not error; it silently destroys the matrix. For a truly stranded library, the correct `-s` assigns ~80-90% of reads while the opposite setting collapses to ~5-20% (counting only antisense background). Do not trust the kit name; determine it empirically:\n\n```bash\n# Method A: RSeQC reports the strand pattern fractions\ninfer_experiment.py -r genes.bed -i sample.bam\n\n# Method B: run all three and pick the one that maximizes Assigned in the .summary\nfor s in 0 1 2; do featureCounts -s $s -a annotation.gtf -o counts_s$s.txt sample.bam; done\n```\n\nIf `-s 1` and `-s 2` give wildly different Assigned fractions, the data are stranded (use the higher); if both are roughly equal and about half of `-s 0`, the data are unstranded. STAR `--quantMode GeneCounts` provides a free cross-check (see below).\n\n## Decision 2: paired-end fragment counting\n\n```bash\n# Subread >= 2.0.2: -p only declares paired input; --countReadPairs is REQUIRED to count fragments\nfeatureCounts -p --countReadPairs -a annotation.gtf -o counts.txt *.bam\n\n# Stricter: require both ends mapped, exclude chimeric\u002Fdiscordant pairs\nfeatureCounts -p --countReadPairs -B -C -a annotation.gtf -o counts.txt *.bam\n```\n\nOmitting `--countReadPairs` on paired-end data counts each mate separately, roughly doubling counts and breaking the count model. `-B` requires both ends aligned; `-C` excludes pairs mapping across chromosomes or in the wrong orientation.\n\n## Decision 3: multi-mapping and multi-overlap reads\n\n```bash\n# Default (recommended for gene-level DE): discard both -> uniquely, unambiguously assigned reads only\nfeatureCounts -a annotation.gtf -o counts.txt *.bam\n\n# Count multimappers fractionally (1\u002FN) or fully (1 each) -- NOT recommended for DE\nfeatureCounts -M --fraction -a annotation.gtf -o counts.txt *.bam\nfeatureCounts -M -a annotation.gtf -o counts.txt *.bam\n\n# Count reads overlapping >1 gene in all of them\nfeatureCounts -O -a annotation.gtf -o counts.txt *.bam\n```\n\nDiscarding multimappers is the right default for gene-level DE. `-M --fraction` looks principled but biases exactly the genes where resolution matters: a read truly from gene A that also maps to paralog A' is split 0.5\u002F0.5, diluting both. This is the regime where alignment-free EM quantifiers (rna-quantification\u002Falignment-free-quant) outperform featureCounts, because they reassign by full likelihood rather than a flat split.\n\n## Quality and feature options\n\n```bash\nfeatureCounts -Q 10 -a annotation.gtf -o counts.txt *.bam      # min MAPQ (aligner-specific scale)\nfeatureCounts --primary -a annotation.gtf -o counts.txt *.bam  # primary alignments only\nfeatureCounts -t CDS -g gene_id -a annotation.gtf -o counts.txt *.bam  # count CDS instead of exon\n```\n\n`-Q` thresholds mapping quality, but MAPQ conventions are aligner-specific (STAR assigns 255 to unique reads, low values to multimappers), so confirm the scheme before choosing a cutoff. Do NOT add `--ignoreDup` for standard RNA-seq: high duplication is expected from highly expressed genes, and position-based deduplication discards real signal. Deduplicate only with UMIs. For exon-level usage testing (DEXSeq), use a flattened annotation rather than gene-level counting (alternative-splicing\u002Fisoform-switching).\n\n## Output\n\n```\ncounts.txt:           Geneid Chr Start End Strand Length sample1.bam sample2.bam ...\ncounts.txt.summary:   Status              sample1.bam  sample2.bam\n                      Assigned            1523456      1678234\n                      Unassigned_NoFeatures 234567     245678\n```\n\nReading the `.summary` is the primary QC step. A good poly-A library assigns ~70-90% of mapped reads (rRNA-depletion libraries run lower).\n\n| Dominant unassigned category | Likely cause | Action |\n|------------------------------|--------------|--------|\n| Unassigned_NoFeatures high | GTF\u002Fgenome mismatch (chr naming `1` vs `chr1`, wrong release), DNA contamination | Match GTF release and chromosome naming to the BAM |\n| Unassigned_MultiMapping high | rRNA carryover or repetitive content | Check rRNA depletion; inspect with FastQ Screen |\n| Unassigned_Ambiguity high | Overlapping\u002Fnested gene models or wrong feature level | Expected in gene-dense regions; reconsider `-O`\u002Ffeature type |\n| Assigned low, others spread thin | Wrong strandedness | Re-test `-s` (see Decision 1) |\n\n## STAR cross-check\n\nIf aligned with STAR `--quantMode GeneCounts`, `ReadsPerGene.out.tab` gives a free independent count: column 2 = unstranded (≈ `-s 0`), column 3 = forward (≈ `-s 1`), column 4 = reverse (≈ `-s 2`). The larger of columns 3 vs 4 reveals the strand directly, and the per-gene counts should track featureCounts at the matching `-s`.\n\n## Extract the matrix\n\n```bash\ncut -f1,7- counts.txt | tail -n +2 > count_matrix.txt   # drop the 6 annotation columns\n```\n\n```python\nimport pandas as pd\ncounts = pd.read_csv('counts.txt', sep='\\t', comment='#')\nmat = counts.set_index('Geneid').iloc[:, 5:]\nmat.columns = [c.replace('.bam', '') for c in mat.columns]\nmat.to_csv('count_matrix.csv')\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| Assigned ~half of expected, no error | Wrong `-s`, or paired-end without `--countReadPairs` (double-counting) | Determine strand empirically; add `--countReadPairs` for paired-end |\n| Near-zero counts for known genes | `gene_id` attribute or feature type mismatch with the GTF | Confirm `-t`\u002F`-g` match the annotation; check the GTF attribute names |\n| Counts much higher than read count | Paired-end mates counted separately | Add `-p --countReadPairs` |\n| Inflated correlated paralog counts | `-M`\u002F`-O` fractional counting enabled | Drop `-M`\u002F`-O` for DE; use alignment-free EM for paralog-heavy genes |\n| Low Assigned across all `-s` values | GTF does not match the aligned genome | Use the GTF release and contig names matching the alignment reference |\n\n## Related Skills\n\n- alignment-files\u002Fsam-bam-basics - Input BAM handling and filtering\n- read-alignment\u002Fstar-alignment - Producing BAMs and ReadsPerGene.out.tab strand cross-check\n- genome-intervals\u002Fgtf-gff-handling - GTF\u002FGFF annotation files\n- rna-quantification\u002Falignment-free-quant - EM-based alternative; better for multimappers\u002Fparalogs\n- rna-quantification\u002Fcount-matrix-qc - QC the resulting matrix before DE\n- differential-expression\u002Fdeseq2-basics - Gene-level DE from these counts\n\n## References\n\n- Liao Y, Smyth GK, Shi W. 2014. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Bioinformatics 30(7):923-930. doi:10.1093\u002Fbioinformatics\u002Fbtt656\n- Liao Y, Smyth GK, Shi W. 2013. The Subread aligner: fast, accurate and scalable read mapping by seed-and-vote. Nucleic Acids Res 41(10):e108. doi:10.1093\u002Fnar\u002Fgkt214\n","## Version Compatibility\n\nReference examples tested with: Subread 2.0+, STAR 2.7.11+, HISAT2 2.2.1+, DESeq2 1.42+, edgeR 4.0+, pandas 2.2+\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- CLI: `\u003Ctool> --version` then `\u003Ctool> --help` to confirm flags\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n\nIf code throws ImportError, AttributeError, or TypeError, introspect the installed\npackage and adapt the example to match the actual API rather than retrying.\n\n# featureCounts Counting\n\n**\"Count reads per gene from my BAM files\"** -> Assign each aligned read to at most one gene by overlap with a GTF, discarding ambiguous reads, to produce an integer gene-by-sample matrix for differential expression.\n- CLI: `featureCounts -a genes.gtf -o counts.txt sample1.bam sample2.bam`\n\nfeatureCounts is bookkeeping, not inference: it tallies reads to genes and discards anything ambiguous. That is correct for gene-level DE, where almost every read's gene of origin is unambiguous even when its isoform is not. The two settings that silently corrupt the matrix if wrong are strandedness (`-s`) and, for paired-end data, fragment counting (`--countReadPairs`).\n\n## Basic Usage\n\n```bash\n# Multiple samples in one run -> a single aligned matrix (recommended)\nfeatureCounts -a annotation.gtf -o counts.txt sample1.bam sample2.bam sample3.bam\n\n# Defaults: -t exon -g gene_id (count reads over exons, aggregate by gene)\n```\n\n## Decision 1: strandedness (`-s`) is the load-bearing setting\n\n| `-s` | Meaning | Read 1 |\n|------|---------|--------|\n| 0 | Unstranded | strand ignored |\n| 1 | Forward stranded | read 1 is sense |\n| 2 | Reverse stranded | read 1 is antisense; read 2 is sense |\n\nThe dominant chemistry, dUTP \u002F Illumina TruSeq Stranded \u002F NEBNext Directional, is reverse, `-s 2`. Setting the wrong strand does not error; it silently destroys the matrix. For a truly stranded library, the correct `-s` assigns ~80-90% of reads while the opposite setting collapses to ~5-20% (counting only antisense background). Do not trust the kit name; determine it empirically:\n\n```bash\n# Method A: RSeQC reports the strand pattern fractions\ninfer_experiment.py -r genes.bed -i sample.bam\n\n# Method B: run all three and pick the one that maximizes Assigned in the .summary\nfor s in 0 1 2; do featureCounts -s $s -a annotation.gtf -o counts_s$s.txt sample.bam; done\n```\n\nIf `-s 1` and `-s 2` give wildly different Assigned fractions, the data are stranded (use the higher); if both are roughly equal and about half of `-s 0`, the data are unstranded. STAR `--quantMode GeneCounts` provides a free cross-check (see below).\n\n## Decision 2: paired-end fragment counting\n\n```bash\n# Subread >= 2.0.2: -p only declares paired input; --countReadPairs is REQUIRED to count fragments\nfeatureCounts -p --countReadPairs -a annotation.gtf -o counts.txt *.bam\n\n# Stricter: require both ends mapped, exclude chimeric\u002Fdiscordant pairs\nfeatureCounts -p --countReadPairs -B -C -a annotation.gtf -o counts.txt *.bam\n```\n\nOmitting `--countReadPairs` on paired-end data counts each mate separately, roughly doubling counts and breaking the count model. `-B` requires both ends aligned; `-C` excludes pairs mapping across chromosomes or in the wrong orientation.\n\n## Decision 3: multi-mapping and multi-overlap reads\n\n```bash\n# Default (recommended for gene-level DE): discard both -> uniquely, unambiguously assigned reads only\nfeatureCounts -a annotation.gtf -o counts.txt *.bam\n\n# Count multimappers fractionally (1\u002FN) or fully (1 each) -- NOT recommended for DE\nfeatureCounts -M --fraction -a annotation.gtf -o counts.txt *.bam\nfeatureCounts -M -a annotation.gtf -o counts.txt *.bam\n\n# Count reads overlapping >1 gene in all of them\nfeatureCounts -O -a annotation.gtf -o counts.txt *.bam\n```\n\nDiscarding multimappers is the right default for gene-level DE. `-M --fraction` looks principled but biases exactly the genes where resolution matters: a read truly from gene A that also maps to paralog A' is split 0.5\u002F0.5, diluting both. This is the regime where alignment-free EM quantifiers (rna-quantification\u002Falignment-free-quant) outperform featureCounts, because they reassign by full likelihood rather than a flat split.\n\n## Quality and feature options\n\n```bash\nfeatureCounts -Q 10 -a annotation.gtf -o counts.txt *.bam      # min MAPQ (aligner-specific scale)\nfeatureCounts --primary -a annotation.gtf -o counts.txt *.bam  # primary alignments only\nfeatureCounts -t CDS -g gene_id -a annotation.gtf -o counts.txt *.bam  # count CDS instead of exon\n```\n\n`-Q` thresholds mapping quality, but MAPQ conventions are aligner-specific (STAR assigns 255 to unique reads, low values to multimappers), so confirm the scheme before choosing a cutoff. Do NOT add `--ignoreDup` for standard RNA-seq: high duplication is expected from highly expressed genes, and position-based deduplication discards real signal. Deduplicate only with UMIs. For exon-level usage testing (DEXSeq), use a flattened annotation rather than gene-level counting (alternative-splicing\u002Fisoform-switching).\n\n## Output\n\n```\ncounts.txt:           Geneid Chr Start End Strand Length sample1.bam sample2.bam ...\ncounts.txt.summary:   Status              sample1.bam  sample2.bam\n                      Assigned            1523456      1678234\n                      Unassigned_NoFeatures 234567     245678\n```\n\nReading the `.summary` is the primary QC step. A good poly-A library assigns ~70-90% of mapped reads (rRNA-depletion libraries run lower).\n\n| Dominant unassigned category | Likely cause | Action |\n|------------------------------|--------------|--------|\n| Unassigned_NoFeatures high | GTF\u002Fgenome mismatch (chr naming `1` vs `chr1`, wrong release), DNA contamination | Match GTF release and chromosome naming to the BAM |\n| Unassigned_MultiMapping high | rRNA carryover or repetitive content | Check rRNA depletion; inspect with FastQ Screen |\n| Unassigned_Ambiguity high | Overlapping\u002Fnested gene models or wrong feature level | Expected in gene-dense regions; reconsider `-O`\u002Ffeature type |\n| Assigned low, others spread thin | Wrong strandedness | Re-test `-s` (see Decision 1) |\n\n## STAR cross-check\n\nIf aligned with STAR `--quantMode GeneCounts`, `ReadsPerGene.out.tab` gives a free independent count: column 2 = unstranded (≈ `-s 0`), column 3 = forward (≈ `-s 1`), column 4 = reverse (≈ `-s 2`). The larger of columns 3 vs 4 reveals the strand directly, and the per-gene counts should track featureCounts at the matching `-s`.\n\n## Extract the matrix\n\n```bash\ncut -f1,7- counts.txt | tail -n +2 > count_matrix.txt   # drop the 6 annotation columns\n```\n\n```python\nimport pandas as pd\ncounts = pd.read_csv('counts.txt', sep='\\t', comment='#')\nmat = counts.set_index('Geneid').iloc[:, 5:]\nmat.columns = [c.replace('.bam', '') for c in mat.columns]\nmat.to_csv('count_matrix.csv')\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| Assigned ~half of expected, no error | Wrong `-s`, or paired-end without `--countReadPairs` (double-counting) | Determine strand empirically; add `--countReadPairs` for paired-end |\n| Near-zero counts for known genes | `gene_id` attribute or feature type mismatch with the GTF | Confirm `-t`\u002F`-g` match the annotation; check the GTF attribute names |\n| Counts much higher than read count | Paired-end mates counted separately | Add `-p --countReadPairs` |\n| Inflated correlated paralog counts | `-M`\u002F`-O` fractional counting enabled | Drop `-M`\u002F`-O` for DE; use alignment-free EM for paralog-heavy genes |\n| Low Assigned across all `-s` values | GTF does not match the aligned genome | Use the GTF release and contig names matching the alignment reference |\n\n## Related Skills\n\n- alignment-files\u002Fsam-bam-basics - Input BAM handling and filtering\n- read-alignment\u002Fstar-alignment - Producing BAMs and ReadsPerGene.out.tab strand cross-check\n- genome-intervals\u002Fgtf-gff-handling - GTF\u002FGFF annotation files\n- rna-quantification\u002Falignment-free-quant - EM-based alternative; better for multimappers\u002Fparalogs\n- rna-quantification\u002Fcount-matrix-qc - QC the resulting matrix before DE\n- differential-expression\u002Fdeseq2-basics - Gene-level DE from these counts\n\n## References\n\n- Liao Y, Smyth GK, Shi W. 2014. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Bioinformatics 30(7):923-930. doi:10.1093\u002Fbioinformatics\u002Fbtt656\n- Liao Y, Smyth GK, Shi W. 2013. The Subread aligner: fast, accurate and scalable read mapping by seed-and-vote. Nucleic Acids Res 41(10):e108. doi:10.1093\u002Fnar\u002Fgkt214\n",{"name":5,"source":24,"license":15,"tool_type":25,"description":7,"imported_at":26,"source_path":27,"primary_tool":28,"source_repository":29},"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills","cli","2026-09-20","rna-quantification\u002Ffeaturecounts-counting\u002FSKILL.md","featureCounts","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-rna-quantification-featurecounts-counting",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-rna-quantification-featurecounts-counting",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-rna-quantification-featurecounts-counting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting\u002FSKILL.md",true,[50,56,60],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002Fcount_genes.sh","SCRIPT","脚本",643,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting\u002Fexamples\u002Fcount_genes.sh",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"examples\u002Fprocess_counts.py",719,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting\u002Fexamples\u002Fprocess_counts.py",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"usage-guide.md","REFERENCE","参考文档",4676,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-rna-quantification-featurecounts-counting\u002Fusage-guide.md",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":74},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":74},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"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":95,"publishedAt":74},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":74},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"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":109,"publishedAt":74},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]