[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ED89JDDRNWX4KR6PJTS2GP":3,"skill-same:01M7ED89JDDRNWX4KR6PJTS2GP":62},{"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},"01M7ED89JDDRNWX4KR6PJTS2GP","bio-flow-cytometry-clustering-phenotyping",null,"Unsupervised clustering and cell-type identification for high-dimensional flow, spectral, and mass cytometry - FlowSOM, PhenoGraph, FlowSOM-via-CATALYST, with UMAP\u002FtSNE for visualization. Covers the type-vs-state marker distinction (cluster on lineage, test state within clusters), over-provision-then-metacluster, the Weber-Robinson benchmark, seed dependence and metacluster stability, why embeddings are for looking not measuring, and median-heatmap annotation\u002Fmerging. Use when discovering populations without predefined gates, choosing a clustering algorithm, selecting the number of metaclusters, or annotating clusters into cell types.","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-flow-cytometry-clustering-phenotyping\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-flow-cytometry-clustering-phenotyping\ndescription: Unsupervised clustering and cell-type identification for high-dimensional flow, spectral, and mass cytometry - FlowSOM, PhenoGraph, FlowSOM-via-CATALYST, with UMAP\u002FtSNE for visualization. Covers the type-vs-state marker distinction (cluster on lineage, test state within clusters), over-provision-then-metacluster, the Weber-Robinson benchmark, seed dependence and metacluster stability, why embeddings are for looking not measuring, and median-heatmap annotation\u002Fmerging. Use when discovering populations without predefined gates, choosing a clustering algorithm, selecting the number of metaclusters, or annotating clusters into cell types.\ntool_type: r\nprimary_tool: CATALYST\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"flow-cytometry\u002Fclustering-phenotyping\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: CATALYST 1.26+, FlowSOM 2.10+, flowCore 2.14+; Rphenograph (GitHub: JinmiaoChenLab\u002FRphenograph).\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n\n`Rphenograph` is GitHub-only (`remotes::install_github('JinmiaoChenLab\u002FRphenograph')`) and returns a list - membership is `igraph::membership(out[[2]])`, not a vector. Adapt rather than retrying.\n\n# Clustering and Phenotyping\n\n**\"Cluster my cytometry data to find cell types\"** -> Discover populations in high-dimensional data without gates, then annotate them by marker expression.\n- R: `CATALYST::cluster()` (wraps FlowSOM + ConsensusClusterPlus) - the field default\n- R: `FlowSOM::FlowSOM()` directly, or `Rphenograph()` for graph-based clustering\n\n## The Single Most Important Modern Insight -- Cluster on Type Markers; the Embedding Is for Looking, Not Measuring\n\nTwo rules carry most of the correctness here. First, the type-vs-state distinction: LINEAGE\u002Ftype markers (CD3, CD4, CD8, CD19) DEFINE clusters; functional\u002FSTATE markers (phospho-epitopes, cytokines, Ki-67, activation markers) must be WITHHELD from clustering and tested within clusters instead (the DA\u002FDS framework, Nowicka 2017 *F1000Res* 6:748). Clustering on state markers splits \"activated CD4\" from \"resting CD4\" and confounds abundance with activation - a classic, silent design error. Second, t-SNE\u002FUMAP embeddings do NOT preserve inter-cluster distances, cluster sizes, or densities (the apparent \"UMAP preserves global structure\" edge over tSNE is largely an initialization artifact - Kobak & Linderman 2021 *Nat Biotechnol* 39:156). Define populations by clustering in the HIGH-DIMENSIONAL space and COLOR the embedding by cluster; never gate on the embedding or read biology off blob distances.\n\n## Algorithm Taxonomy\n\n| Algorithm | Citation | Mechanism | Speed | Rare-pop | Determinism |\n|-----------|----------|-----------|-------|----------|-------------|\n| FlowSOM | Van Gassen 2015 *Cytometry A* 87:636 | SOM grid -> MST (viz) -> consensus metaclustering | fastest | good if grid over-provisioned | stochastic; seed-controllable |\n| PhenoGraph | Levine 2015 *Cell* 162:184 | kNN graph (Jaccard) + Louvain | moderate | strong (no preset k) | seed-fragile (>40% reassignment reported) |\n| X-shift | Samusik 2016 *Nat Methods* 13:493 | weighted kNN density + auto cluster # | slow | excellent | more deterministic |\n| flowMeans | Aghaeepour 2011 *Cytometry A* 79:6 | k-means multi-cluster + change-point k | fast | moderate | stochastic |\n\nBenchmark: Weber & Robinson 2016 *Cytometry A* 89:1084 tested 18 methods - FlowSOM (with metaclustering) was a top performer AND by far fastest, hence the field default; but its accuracy depends on supplying the right number of metaclusters.\n\n## Why Over-Provision the Grid, Then Metacluster\n\nSet the SOM grid (e.g. 10x10 = 100 nodes) MUCH larger than the number of populations expected, then metacluster down. The asymmetry: metaclustering can MERGE over-fine nodes into a real population, but can NEVER SPLIT a node that erroneously fused two cell types. Too coarse commits the unrecoverable error; too fine commits only the recoverable one. So over-cluster, then merge by hand off the median heatmap.\n\n## CATALYST Clustering Pipeline\n\n**Goal:** Cluster on type markers and prepare for annotation.\n\n**Approach:** `prepData` builds the SCE (panel `marker_class` flags type vs state); `cluster()` wraps FlowSOM+ConsensusClusterPlus. Defaults `xdim=ydim=10`, `maxK=20` (the metacluster cap people forget); set `seed` on the function.\n\n```r\nlibrary(CATALYST)\n\nsce \u003C- prepData(fs, panel, md, transform = TRUE, cofactor = 5)   # cofactor 5 = CyTOF; ~150 for fluorescence\nsce \u003C- cluster(sce, features = 'type',                            # type markers only\n               xdim = 10, ydim = 10, maxK = 20, seed = 42)        # maxK caps metaclusters at 20 by default\nplotExprHeatmap(sce, features = 'type', by = 'cluster_id', k = 'meta20', scale = 'last')\n```\n\n## PhenoGraph (graph-based alternative)\n\n**Goal:** Cluster with a kNN graph when a data-driven cluster count is wanted.\n\n**Approach:** `Rphenograph` on the type-marker matrix (cells x markers); extract membership from the list.\n\n```r\nlibrary(Rphenograph)\ntype_expr \u003C- t(assay(sce, 'exprs')[rowData(sce)$marker_class == 'type', ])\nout \u003C- Rphenograph(type_expr, k = 30)                  # only knob: k (neighbors)\nsce$phenograph \u003C- factor(igraph::membership(out[[2]]))  # list -> membership, not a vector\n```\n\n## Dimensionality Reduction (visualization only) and Annotation\n\n**Goal:** Visualize structure and assign cell-type labels.\n\n**Approach:** `runDR` subsamples per sample (`cells=`); color by cluster, never gate on it. Annotate from the median heatmap, then `mergeClusters` with a curated table.\n\n```r\nsce \u003C- runDR(sce, dr = 'UMAP', features = 'type', cells = 2000)   # subsampled embedding\nplotDR(sce, 'UMAP', color_by = 'meta20')\n\nmerging \u003C- data.frame(old_cluster = 1:20,\n                      new_cluster = c('CD4 T','CD4 T','CD8 T', '...'))   # curated from the heatmap\nsce \u003C- mergeClusters(sce, k = 'meta20', table = merging, id = 'annotated')\n```\n\n## Per-Method Failure Modes\n\n### Clustering on state markers\n**Trigger:** activation\u002Fphospho markers in the clustering feature set. **Mechanism:** state contaminates lineage identity. **Symptom:** \"activated\" and \"resting\" versions of a type split as separate clusters. **Fix:** cluster on `type` only; test state markers within clusters (differential-analysis).\n\n### Seed-dependent \"novel populations\"\n**Trigger:** a population that appears at one seed and vanishes at another. **Mechanism:** FlowSOM init \u002F Louvain are stochastic. **Symptom:** non-reproducible clusters. **Fix:** set + report the seed; check multi-seed stability; treat unstable clusters as hypotheses.\n\n### Reading biology off the embedding\n**Trigger:** \"cluster A is closer to B than C.\" **Mechanism:** UMAP\u002FtSNE distances are non-metric. **Symptom:** false developmental\u002Frelatedness claims. **Fix:** quantify in marker space; embedding for display only.\n\n### Clustering uncompensated\u002Funtransformed data\n**Trigger:** raw linear input to FlowSOM. **Mechanism:** spillover + scale dominate Euclidean distance. **Symptom:** clusters track intensity, not biology. **Fix:** compensate + transform first.\n\n## Quantitative Thresholds\n\n| Threshold | Source | Rationale |\n|-----------|--------|-----------|\n| over-provision grid (10x10) >> expected pops | Van Gassen 2015 | metacluster can merge, never split |\n| maxK = 20 default | CATALYST | metacluster cap; raise if expecting more |\n| FlowSOM needs correct K | Weber & Robinson 2016 | accuracy depends on metacluster number |\n| use median (not mean) per cluster | Bendall 2011 *Science* 332:687 | robust to doublet\u002Fspillover contamination |\n\n## Common Errors\n\n| Error \u002F symptom | Cause | Solution |\n|-----------------|-------|----------|\n| clustering uses scatter\u002FTime\u002Fstate | `features` not restricted | `features='type'` \u002F `colsToUse=` lineage markers |\n| Rphenograph result unusable | it returns a list | `igraph::membership(out[[2]])` |\n| `set.seed` doesn't make FlowSOM reproducible | internal reseeding | pass `seed=` to `cluster()` |\n| only 20 clusters no matter what | `maxK` default | raise `maxK` |\n\n## References\n\n- Van Gassen 2015 *Cytometry A* 87(7):636-645 — FlowSOM.\n- Levine 2015 *Cell* 162(1):184-197 — PhenoGraph.\n- Samusik 2016 *Nat Methods* 13(6):493-496 — X-shift.\n- Weber & Robinson 2016 *Cytometry A* 89(12):1084-1096 — clustering benchmark (FlowSOM top + fastest).\n- Nowicka 2017 *F1000Research* 6:748 — CyTOF workflow; type-vs-state markers.\n- Kobak & Linderman 2021 *Nat Biotechnol* 39:156-157 — embedding initialization artifact.\n- Bendall 2011 *Science* 332(6030):687-696 — arcsinh-median analysis of CyTOF data.\n\n## Related Skills\n\n- compensation-transformation - Compensate\u002Ftransform before clustering\n- gating-analysis - Supervised alternative; needed for rare populations\n- differential-analysis - Test abundance\u002Fstate of clusters between conditions\n- cytometry-qc - Cluster only QC-passed events\n- single-cell\u002Fclustering - Leiden\u002FLouvain on scRNA-seq (shared graph-clustering ideas)\n- imaging-mass-cytometry\u002Fphenotyping - Same CATALYST\u002FFlowSOM conventions for imaging\n","## Version Compatibility\n\nReference examples tested with: CATALYST 1.26+, FlowSOM 2.10+, flowCore 2.14+; Rphenograph (GitHub: JinmiaoChenLab\u002FRphenograph).\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n\n`Rphenograph` is GitHub-only (`remotes::install_github('JinmiaoChenLab\u002FRphenograph')`) and returns a list - membership is `igraph::membership(out[[2]])`, not a vector. Adapt rather than retrying.\n\n# Clustering and Phenotyping\n\n**\"Cluster my cytometry data to find cell types\"** -> Discover populations in high-dimensional data without gates, then annotate them by marker expression.\n- R: `CATALYST::cluster()` (wraps FlowSOM + ConsensusClusterPlus) - the field default\n- R: `FlowSOM::FlowSOM()` directly, or `Rphenograph()` for graph-based clustering\n\n## The Single Most Important Modern Insight -- Cluster on Type Markers; the Embedding Is for Looking, Not Measuring\n\nTwo rules carry most of the correctness here. First, the type-vs-state distinction: LINEAGE\u002Ftype markers (CD3, CD4, CD8, CD19) DEFINE clusters; functional\u002FSTATE markers (phospho-epitopes, cytokines, Ki-67, activation markers) must be WITHHELD from clustering and tested within clusters instead (the DA\u002FDS framework, Nowicka 2017 *F1000Res* 6:748). Clustering on state markers splits \"activated CD4\" from \"resting CD4\" and confounds abundance with activation - a classic, silent design error. Second, t-SNE\u002FUMAP embeddings do NOT preserve inter-cluster distances, cluster sizes, or densities (the apparent \"UMAP preserves global structure\" edge over tSNE is largely an initialization artifact - Kobak & Linderman 2021 *Nat Biotechnol* 39:156). Define populations by clustering in the HIGH-DIMENSIONAL space and COLOR the embedding by cluster; never gate on the embedding or read biology off blob distances.\n\n## Algorithm Taxonomy\n\n| Algorithm | Citation | Mechanism | Speed | Rare-pop | Determinism |\n|-----------|----------|-----------|-------|----------|-------------|\n| FlowSOM | Van Gassen 2015 *Cytometry A* 87:636 | SOM grid -> MST (viz) -> consensus metaclustering | fastest | good if grid over-provisioned | stochastic; seed-controllable |\n| PhenoGraph | Levine 2015 *Cell* 162:184 | kNN graph (Jaccard) + Louvain | moderate | strong (no preset k) | seed-fragile (>40% reassignment reported) |\n| X-shift | Samusik 2016 *Nat Methods* 13:493 | weighted kNN density + auto cluster # | slow | excellent | more deterministic |\n| flowMeans | Aghaeepour 2011 *Cytometry A* 79:6 | k-means multi-cluster + change-point k | fast | moderate | stochastic |\n\nBenchmark: Weber & Robinson 2016 *Cytometry A* 89:1084 tested 18 methods - FlowSOM (with metaclustering) was a top performer AND by far fastest, hence the field default; but its accuracy depends on supplying the right number of metaclusters.\n\n## Why Over-Provision the Grid, Then Metacluster\n\nSet the SOM grid (e.g. 10x10 = 100 nodes) MUCH larger than the number of populations expected, then metacluster down. The asymmetry: metaclustering can MERGE over-fine nodes into a real population, but can NEVER SPLIT a node that erroneously fused two cell types. Too coarse commits the unrecoverable error; too fine commits only the recoverable one. So over-cluster, then merge by hand off the median heatmap.\n\n## CATALYST Clustering Pipeline\n\n**Goal:** Cluster on type markers and prepare for annotation.\n\n**Approach:** `prepData` builds the SCE (panel `marker_class` flags type vs state); `cluster()` wraps FlowSOM+ConsensusClusterPlus. Defaults `xdim=ydim=10`, `maxK=20` (the metacluster cap people forget); set `seed` on the function.\n\n```r\nlibrary(CATALYST)\n\nsce \u003C- prepData(fs, panel, md, transform = TRUE, cofactor = 5)   # cofactor 5 = CyTOF; ~150 for fluorescence\nsce \u003C- cluster(sce, features = 'type',                            # type markers only\n               xdim = 10, ydim = 10, maxK = 20, seed = 42)        # maxK caps metaclusters at 20 by default\nplotExprHeatmap(sce, features = 'type', by = 'cluster_id', k = 'meta20', scale = 'last')\n```\n\n## PhenoGraph (graph-based alternative)\n\n**Goal:** Cluster with a kNN graph when a data-driven cluster count is wanted.\n\n**Approach:** `Rphenograph` on the type-marker matrix (cells x markers); extract membership from the list.\n\n```r\nlibrary(Rphenograph)\ntype_expr \u003C- t(assay(sce, 'exprs')[rowData(sce)$marker_class == 'type', ])\nout \u003C- Rphenograph(type_expr, k = 30)                  # only knob: k (neighbors)\nsce$phenograph \u003C- factor(igraph::membership(out[[2]]))  # list -> membership, not a vector\n```\n\n## Dimensionality Reduction (visualization only) and Annotation\n\n**Goal:** Visualize structure and assign cell-type labels.\n\n**Approach:** `runDR` subsamples per sample (`cells=`); color by cluster, never gate on it. Annotate from the median heatmap, then `mergeClusters` with a curated table.\n\n```r\nsce \u003C- runDR(sce, dr = 'UMAP', features = 'type', cells = 2000)   # subsampled embedding\nplotDR(sce, 'UMAP', color_by = 'meta20')\n\nmerging \u003C- data.frame(old_cluster = 1:20,\n                      new_cluster = c('CD4 T','CD4 T','CD8 T', '...'))   # curated from the heatmap\nsce \u003C- mergeClusters(sce, k = 'meta20', table = merging, id = 'annotated')\n```\n\n## Per-Method Failure Modes\n\n### Clustering on state markers\n**Trigger:** activation\u002Fphospho markers in the clustering feature set. **Mechanism:** state contaminates lineage identity. **Symptom:** \"activated\" and \"resting\" versions of a type split as separate clusters. **Fix:** cluster on `type` only; test state markers within clusters (differential-analysis).\n\n### Seed-dependent \"novel populations\"\n**Trigger:** a population that appears at one seed and vanishes at another. **Mechanism:** FlowSOM init \u002F Louvain are stochastic. **Symptom:** non-reproducible clusters. **Fix:** set + report the seed; check multi-seed stability; treat unstable clusters as hypotheses.\n\n### Reading biology off the embedding\n**Trigger:** \"cluster A is closer to B than C.\" **Mechanism:** UMAP\u002FtSNE distances are non-metric. **Symptom:** false developmental\u002Frelatedness claims. **Fix:** quantify in marker space; embedding for display only.\n\n### Clustering uncompensated\u002Funtransformed data\n**Trigger:** raw linear input to FlowSOM. **Mechanism:** spillover + scale dominate Euclidean distance. **Symptom:** clusters track intensity, not biology. **Fix:** compensate + transform first.\n\n## Quantitative Thresholds\n\n| Threshold | Source | Rationale |\n|-----------|--------|-----------|\n| over-provision grid (10x10) >> expected pops | Van Gassen 2015 | metacluster can merge, never split |\n| maxK = 20 default | CATALYST | metacluster cap; raise if expecting more |\n| FlowSOM needs correct K | Weber & Robinson 2016 | accuracy depends on metacluster number |\n| use median (not mean) per cluster | Bendall 2011 *Science* 332:687 | robust to doublet\u002Fspillover contamination |\n\n## Common Errors\n\n| Error \u002F symptom | Cause | Solution |\n|-----------------|-------|----------|\n| clustering uses scatter\u002FTime\u002Fstate | `features` not restricted | `features='type'` \u002F `colsToUse=` lineage markers |\n| Rphenograph result unusable | it returns a list | `igraph::membership(out[[2]])` |\n| `set.seed` doesn't make FlowSOM reproducible | internal reseeding | pass `seed=` to `cluster()` |\n| only 20 clusters no matter what | `maxK` default | raise `maxK` |\n\n## References\n\n- Van Gassen 2015 *Cytometry A* 87(7):636-645 — FlowSOM.\n- Levine 2015 *Cell* 162(1):184-197 — PhenoGraph.\n- Samusik 2016 *Nat Methods* 13(6):493-496 — X-shift.\n- Weber & Robinson 2016 *Cytometry A* 89(12):1084-1096 — clustering benchmark (FlowSOM top + fastest).\n- Nowicka 2017 *F1000Research* 6:748 — CyTOF workflow; type-vs-state markers.\n- Kobak & Linderman 2021 *Nat Biotechnol* 39:156-157 — embedding initialization artifact.\n- Bendall 2011 *Science* 332(6030):687-696 — arcsinh-median analysis of CyTOF data.\n\n## Related Skills\n\n- compensation-transformation - Compensate\u002Ftransform before clustering\n- gating-analysis - Supervised alternative; needed for rare populations\n- differential-analysis - Test abundance\u002Fstate of clusters between conditions\n- cytometry-qc - Cluster only QC-passed events\n- single-cell\u002Fclustering - Leiden\u002FLouvain on scRNA-seq (shared graph-clustering ideas)\n- imaging-mass-cytometry\u002Fphenotyping - Same CATALYST\u002FFlowSOM conventions for imaging\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","r","2026-09-20","flow-cytometry\u002Fclustering-phenotyping\u002FSKILL.md","CATALYST","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-flow-cytometry-clustering-phenotyping","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-flow-cytometry-clustering-phenotyping",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-flow-cytometry-clustering-phenotyping",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-flow-cytometry-clustering-phenotyping","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-flow-cytometry-clustering-phenotyping\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002Fcluster_cytof.R","OTHER","其他",1200,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-flow-cytometry-clustering-phenotyping\u002Fexamples\u002Fcluster_cytof.R",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"usage-guide.md","REFERENCE","参考文档",3656,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-flow-cytometry-clustering-phenotyping\u002Fusage-guide.md",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":70},"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":70},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":70},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":70},"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":70},"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",[],[]]