[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EGMDS1VJND9S9SWBQHT2B9":3,"skill-same:01M7EGMDS1VJND9S9SWBQHT2B9":70},{"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":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":57},"01M7EGMDS1VJND9S9SWBQHT2B9","bio-workflows-imc-pipeline",null,"Orchestrates imaging mass cytometry from raw MCD acquisitions to patient-level spatial analysis, chaining steinbock preprocessing, Mesmer\u002FCellpose segmentation, single-cell quantification, phenotyping, and squidpy spatial statistics. Use when committing the panel + segmentation frame + pixel size (every per-cell number is a mask-bounded pixel average), compensating channel spillover on PIXELS before segmentation but running REDSEA lateral-spillover on the per-cell table AFTER segmentation, using arcsinh cofactor 1 (not the suspension-CyTOF 5), and aggregating to the PATIENT before any cross-condition test (cells and ROIs from one patient are not independent replicates). Hands mechanism to the imaging-mass-cytometry component skills; not a re-teach of any single step.","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-workflows-imc-pipeline\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-workflows-imc-pipeline\ndescription: Orchestrates imaging mass cytometry from raw MCD acquisitions to patient-level spatial analysis, chaining steinbock preprocessing, Mesmer\u002FCellpose segmentation, single-cell quantification, phenotyping, and squidpy spatial statistics. Use when committing the panel + segmentation frame + pixel size (every per-cell number is a mask-bounded pixel average), compensating channel spillover on PIXELS before segmentation but running REDSEA lateral-spillover on the per-cell table AFTER segmentation, using arcsinh cofactor 1 (not the suspension-CyTOF 5), and aggregating to the PATIENT before any cross-condition test (cells and ROIs from one patient are not independent replicates). Hands mechanism to the imaging-mass-cytometry component skills; not a re-teach of any single step.\ntool_type: python\nprimary_tool: steinbock\ngoal_approach_exempt: true\nworkflow: true\ndepends_on:\n  - imaging-mass-cytometry\u002Fdata-preprocessing\n  - imaging-mass-cytometry\u002Fcell-segmentation\n  - imaging-mass-cytometry\u002Fphenotyping\n  - imaging-mass-cytometry\u002Fspatial-analysis\n  - imaging-mass-cytometry\u002Fdifferential-analysis\n  - imaging-mass-cytometry\u002Finteractive-annotation\n  - imaging-mass-cytometry\u002Fquality-metrics\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"workflows\u002Fimc-pipeline\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: Cellpose 4.0+ (cpsam model), anndata 0.10+, matplotlib 3.8+, numpy 1.26+, pandas 2.2+, scanpy 1.10+, scvi-tools 1.1+, squidpy 1.3+, steinbock 0.16+\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n- CLI: `\u003Ctool> --version` then `\u003Ctool> --help` to confirm flags\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# Imaging Mass Cytometry Pipeline\n\n**\"Process my imaging mass cytometry data from images to spatial analysis\"** -> Orchestrate image preprocessing (steinbock), cell segmentation (Cellpose), phenotyping (FlowSOM\u002Fscanpy), spatial neighborhood analysis (squidpy), and tissue community detection.\n\nThis is a workflow skill: it owns the chaining decisions and hand-offs, not the internals of any one step.\n\n## The governing principle\n\nSegmentation is the largest irreversible error source, and it is spatial: every per-cell number is a mask-bounded pixel average, so a wrong boundary fabricates cell types before any expression QC can see them. The seam ORDER — and the patient-level unit — is therefore what decides trustworthiness.\n\n1. **The comparison frame (panel + segmentation frame + pixel size) is committed once and inherited by every per-cell number.** The summed membrane channel encodes a cell-type bias (sum BROADLY-expressed markers, or segmentation under-performs on cell types lacking a strong membrane marker); Mesmer was trained at model_mpp ~0.5 um and rescales the input to it, so passing the wrong pixel size (Mesmer's `image_mpp` defaults to None = NO rescaling, assuming the input is already at model resolution — the true pixel size must be passed explicitly; steinbock's `--pixelsize` flag wraps `image_mpp` and defaults to 1.0) rescales cells to the wrong learned size and degrades every boundary. No downstream step recovers a merged or split cell.\n2. **Channel spillover is compensated on PIXELS before segmentation; lateral spillover (REDSEA) runs on the per-cell table AFTER segmentation — they are DIFFERENT problems.** Metal-isotope crosstalk is a pixel-level NNLS correction whose compensated value must be what gets averaged into the per-cell mean (post-aggregation is wrong). REDSEA corrects real signal leaking across shared cell boundaries at ~1 um even with perfect segmentation and zero channel spillover — it is defined on segmented neighbors, so it must run after segmentation. Running REDSEA pre-segmentation, or channel comp post-aggregation, is a category error.\n3. **The experimental unit is the PATIENT, not the cell or the ROI.** Cells and ROIs from one patient are not independent replicates; a cell-level or per-image test over correlated cells is pseudoreplication (reports p~0 for trivial effects). Aggregate to per-patient proportions\u002Fsummaries, then a mixed model \u002F scCODA. Arcsinh cofactor is 1 for IMC integer ion counts, NOT the suspension-CyTOF 5 (which over-compresses them). Impossible lineage-exclusive co-expression is a segmentation\u002Fspillover ALARM, not a hybrid cell type.\n\n## Made-once commitments\n\n| Commitment | Consequence inherited downstream |\n|------------|----------------------------------|\n| Panel (metal->antibody; membrane-sum channels) | Which channels extract and phenotype; a narrow membrane sum biases segmentation against some cell types |\n| Segmentation frame (nuclear + membrane channels) | Every per-cell number (all are mask-bounded pixel averages); the largest irreversible error source |\n| Pixel size (steinbock `--pixelsize` \u002F Mesmer `image_mpp`, ~1.0 um for IMC) | Boundary quality + all spatial distances; the wrong value rescales cells to the wrong learned size |\n| Arcsinh cofactor = 1 (IMC), not 5 (CyTOF) | Clustering\u002Fphenotyping distances; cofactor 5 over-compresses integer ion counts |\n\n## Pipeline Overview\n\n```\nRaw MCD\u002FTIFF Files ──> Image Processing ──> Cell Masks\n                                                 │\n                                                 ▼\n                ┌─────────────────────────────────────────────┐\n                │              imc-pipeline                   │\n                ├─────────────────────────────────────────────┤\n                │  1. Data Preprocessing (spillover, hot px)  │\n                │  2. Cell Segmentation (Cellpose\u002FMesmer)     │\n                │  3. Single-cell Quantification              │\n                │  4. Clustering & Phenotyping                │\n                │  5. Spatial Analysis                        │\n                │  6. Visualization                           │\n                └─────────────────────────────────────────────┘\n                                                 │\n                                                 ▼\n                    Cell Types + Spatial Neighborhoods\n```\n\n## Decisions Threaded Through This Pipeline\n\nFour reframes govern every stage and are detailed in the depended-on skills: IMC pixels are integer ion COUNTS (arcsinh cofactor 1, not the suspension-CyTOF 5), and spillover is spatial so it must be NNLS-compensated before segmentation; segmentation is the largest irreversible error source, so impossible double-positives are a QC alarm, not biology; a spatial interaction is a hypothesis test whose null silently decides whether the result is real or a density artifact; and the experimental unit is the patient, not the cell, so cross-condition tests aggregate to patients before testing.\n\n## Complete steinbock Workflow\n\n### Step 1: Setup and Preprocessing\n\n```bash\n# generate the panel template; edit the keep column before extracting\nsteinbock preprocess imc panel\n\n# extract per-channel TIFFs (keep-filtered, panel-ordered) with hot-pixel removal\n# (--hpf is a signed 8-neighbor difference; 50 is a count, tune to dynamic range)\nsteinbock preprocess imc images --hpf 50\n\n# channel spillover is compensated with NNLS (CATALYST\u002Fcytomapper, R) on the pixel images\n# BEFORE segmentation when spatial analysis is the endpoint -- see data-preprocessing\n```\n\n### Step 2: Cell Segmentation\n\n```bash\n# Mesmer\u002FDeepCell whole-cell (nuclear-first); membrane channels aggregated via the panel column.\n# --pixelsize is steinbock's CLI flag for the acquisition resolution (it wraps Mesmer's image_mpp);\n# steinbock defaults it to 1.0 um for IMC, so pass the true value explicitly rather than relying on it.\nsteinbock segment deepcell --pixelsize 1.0 --minmax -o masks\n\n# Alternative: Cellpose container (Cellpose 4+ default model cpsam; channel order reversed vs native)\nsteinbock segment cellpose --minmax -o masks\n```\n\n### Step 3: Single-cell Quantification\n\n```bash\n# Extract per-cell MEAN intensities (mean is the default and the right phenotyping aggregator;\n# sum confounds cell size with expression)\nsteinbock measure intensities -o intensities\n\n# Measure cell properties (area, centroid, eccentricity)\nsteinbock measure regionprops -o regionprops\n\n# Build the spatial neighbor graph (expansion within a max distance; match the graph to the\n# biological claim -- contact vs proximity -- in spatial-analysis)\nsteinbock measure neighbors --type expansion --dmax 15 -o neighbors\n```\n\n## Complete Python Workflow\n\n```python\nimport pandas as pd\nimport numpy as np\nimport anndata as ad\nimport scanpy as sc\nimport squidpy as sq\nfrom pathlib import Path\n\n# === 1. LOAD DATA ===\ndata_dir = Path('steinbock_output')\n\nintensities = pd.read_csv(data_dir \u002F 'intensities.csv', index_col=0)\nregionprops = pd.read_csv(data_dir \u002F 'regionprops.csv', index_col=0)\nneighbors = pd.read_csv(data_dir \u002F 'neighbors.csv')\n\nprint(f'Loaded {len(intensities)} cells')\n\n# === 2. CREATE ANNDATA ===\nadata = ad.AnnData(X=intensities.values, obs=regionprops, var=pd.DataFrame(index=intensities.columns))\nadata.obs['image_id'] = pd.Categorical([idx.rsplit('_', 1)[0] for idx in intensities.index])   # strip only the trailing cell index: rsplit keeps Patient1_ROI002 distinct from Patient1_ROI001. squidpy library_key requires a categorical, not object\u002Fstring\nadata.obs['cell_id'] = intensities.index\n\n# Add spatial coordinates (skimage regionprops_table names them centroid-0 (y) \u002F centroid-1 (x))\nadata.obsm['spatial'] = regionprops[['centroid-0', 'centroid-1']].values\n\n# === 3. PREPROCESSING ===\n# Arcsinh transform: cofactor 1 for IMC single-cell means (Hunter 2024), NOT the\n# suspension-CyTOF cofactor 5, which over-compresses IMC's lower-count means\nadata.layers['counts'] = adata.X.copy()\nadata.X = np.arcsinh(adata.X \u002F 1)\n\n# Scale for clustering\nsc.pp.scale(adata, max_value=10)\nadata.raw = adata.copy()\n\n# === 4. DIMENSIONALITY REDUCTION ===\nsc.pp.pca(adata, n_comps=20)\nsc.pp.neighbors(adata, n_neighbors=15)\nsc.tl.umap(adata)\n\n# === 5. CLUSTERING ===\nsc.tl.leiden(adata, resolution=0.8)\nprint(f'Found {adata.obs[\"leiden\"].nunique()} clusters')\n\n# === 6. PHENOTYPING ===\n# Marker expression per cluster\nsc.tl.rank_genes_groups(adata, 'leiden', method='wilcoxon')\nmarker_genes = sc.get.rank_genes_groups_df(adata, group=None)\n\n# Annotate clusters based on markers\ncluster_annotations = {\n    '0': 'T cells',\n    '1': 'Macrophages',\n    '2': 'Tumor',\n    '3': 'B cells',\n    '4': 'Stromal'\n}\nadata.obs['cell_type'] = adata.obs['leiden'].map(cluster_annotations)\n\n# === 7. SPATIAL ANALYSIS ===\n# Build spatial graph PER IMAGE (library_key), else Delaunay fabricates edges across ROIs\nsq.gr.spatial_neighbors(adata, coord_type='generic', delaunay=True, library_key='image_id')\n\n# Neighborhood enrichment\nsq.gr.nhood_enrichment(adata, cluster_key='cell_type')\n\n# Co-occurrence analysis\nsq.gr.co_occurrence(adata, cluster_key='cell_type')\n\n# Ripley's statistics\nsq.gr.ripley(adata, cluster_key='cell_type', mode='L')\n\n# === 8. VISUALIZATION ===\nimport matplotlib.pyplot as plt\n\n# UMAP by cell type\nfig, axes = plt.subplots(1, 2, figsize=(14, 5))\nsc.pl.umap(adata, color='cell_type', ax=axes[0], show=False)\nsc.pl.umap(adata, color='leiden', ax=axes[1], show=False)\nplt.savefig('umap_celltypes.png', dpi=150, bbox_inches='tight')\n\n# Spatial plot. Pick the image dynamically: image_id is derived from the cell index, so a hardcoded\n# literal selects zero cells and spatial_scatter errors on the empty subset.\nfig, ax = plt.subplots(figsize=(10, 10))\nfirst_image = adata.obs['image_id'].iloc[0]\nsq.pl.spatial_scatter(adata[adata.obs['image_id'] == first_image],\n                      color='cell_type', shape=None, size=10, ax=ax)\nplt.savefig('spatial_celltypes.png', dpi=150, bbox_inches='tight')\n\n# Neighborhood enrichment heatmap\nsq.pl.nhood_enrichment(adata, cluster_key='cell_type')\nplt.savefig('neighborhood_enrichment.png', dpi=150, bbox_inches='tight')\n\n# === 9. DIFFERENTIAL ANALYSIS (patient is the unit, NOT the cell) ===\nimport statsmodels.formula.api as smf\n\n# aggregate to per-image proportions, then test across PATIENTS -- a cell-level or per-image\n# test over correlated cells is pseudoreplication and reports p~0 for trivial effects.\n# obs must carry patient and condition columns; see differential-analysis for scCODA\n# (compositional) and the spatial differential path.\ncounts = adata.obs.groupby(['patient', 'condition', 'image_id', 'cell_type'], observed=True).size().unstack(fill_value=0)   # observed=True: image_id is categorical; the default expands the full cartesian product into all-zero phantom rows -> NaN proportions\nimage_prop = counts.div(counts.sum(axis=1), axis=0).reset_index()\ntarget = 'Tumor'   # an actual cell_type column from cluster_annotations above (single-word for the formula)\nres = smf.mixedlm(f'{target} ~ condition', image_prop, groups=image_prop['patient']).fit()  # patient random effect\nprint(res.summary())\n\nadata.write('imc_analysis.h5ad')\nprint('Analysis complete!')\n```\n\n## R Alternative (imcRtools)\n\n```r\nlibrary(imcRtools)\nlibrary(cytomapper)\nlibrary(CATALYST)\n\n# Read steinbock output\nspe \u003C- read_steinbock('steinbock_output\u002F')\n\n# Transform (cofactor 1 for IMC single-cell means, not 5)\nassay(spe, 'exprs') \u003C- asinh(counts(spe) \u002F 1)\n\n# Cluster (CATALYST runDR takes assay=; cluster() always uses the 'exprs' assay, no assay arg)\nspe \u003C- runDR(spe, features = rownames(spe), assay = 'exprs', dr = 'UMAP')\nspe \u003C- cluster(spe, features = rownames(spe), xdim = 10, ydim = 10, maxK = 20)\n\n# Spatial analysis. buildSpatialGraph names the colPair '\u003Ctype>_interaction_graph';\n# aggregateNeighbors counts a label via aggregate_by='metadata' + count_by=.\nspe \u003C- buildSpatialGraph(spe, img_id = 'sample_id', type = 'expansion', threshold = 20)\nspe \u003C- aggregateNeighbors(spe, colPairName = 'expansion_interaction_graph',\n                          aggregate_by = 'metadata', count_by = 'cluster_id')\n\n# Spatial context\nspe \u003C- detectCommunity(spe, colPairName = 'expansion_interaction_graph',\n                       size_threshold = 10, group_by = 'sample_id')\n\n# Plot (img_id is the colData COLUMN used to facet; read_steinbock names it 'sample_id', not 'image_id')\nplotSpatial(spe, img_id = 'sample_id', node_color_by = 'cluster_id')\n```\n\n## QC Checkpoints\n\n| Stage | Check | Action if Failed |\n|-------|-------|------------------|\n| Preprocessing | No hot pixel streaks | Lower threshold |\n| Segmentation | >80% cells detected | Adjust diameter |\n| Quantification | All markers extracted | Check panel.csv |\n| Clustering | 5-20 clusters | Adjust resolution |\n| Spatial | Neighbors detected | Check distance |\n\n## Workflow Variants\n\n### High-plex Panels (40+ markers)\n```python\n# Use batch-aware clustering\nimport scvi\n\nscvi.model.SCVI.setup_anndata(adata, batch_key='image_id')\nmodel = scvi.model.SCVI(adata)\nmodel.train()\nadata.obsm['X_scvi'] = model.get_latent_representation()\nsc.pp.neighbors(adata, use_rep='X_scvi')\n```\n\n### Tumor Microenvironment Analysis\n```python\n# Spatial cell-cell co-location around tumor (per-image, then aggregate to patient).\n# Note: sq.gr.ligrec keys ligand-receptor pairs on gene symbols from OmniPath, so it is\n# usually empty on a ~40-marker antibody panel -- prefer neighborhood enrichment for IMC.\nsq.gr.nhood_enrichment(adata, cluster_key='cell_type')   # see spatial-analysis for the null caveat\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| Impossible double-positive \"hybrid\" cell types | Spillover not corrected before phenotyping (channel and\u002For lateral) | NNLS channel compensation on pixels before segmentation; REDSEA on the per-cell table after; treat lineage-exclusive co-expression as a QC failure until proven |\n| Every boundary degraded, cells the wrong size | Wrong pixel size (Mesmer `image_mpp` defaults None=no rescaling, model trained at ~0.5; steinbock `--pixelsize` defaults 1.0) | Pass the true acquisition resolution explicitly (~1.0 um for IMC) |\n| Macrophages under-captured; biased comparison | Nuclear-expansion segmentation cross-compared with whole-cell data | Never quantitatively compare expansion-segmented vs whole-cell; report the expansion radius; use constrained (not free) dilation |\n| p~0 for a trivial effect | Pseudoreplication (cells\u002FROIs treated as replicates) | Aggregate to per-patient summaries; mixed model with patient random effect \u002F scCODA |\n| Markers over-compressed, noise clusters | Arcsinh cofactor 5 used on IMC | Cofactor 1 for IMC integer ion counts |\n| Acquisition batch drives the clusters | Batch confounded with \u002F not modeled against condition | Randomize acquisition order; batch-aware clustering (Harmony\u002FscVI) for clustering ONLY; model batch as a covariate; no rescue if batch==condition |\n\n## References\n\n- Windhager J, Zanotelli VRT, Schulz D, et al (2023) An end-to-end workflow for multiplexed image processing and analysis. *Nature Protocols* 18:3565-3613. DOI 10.1038\u002Fs41596-023-00881-0. (steinbock.)\n- Greenwald NF, Miller G, Moen E, et al (2022) Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. *Nature Biotechnology* 40:555-565. DOI 10.1038\u002Fs41587-021-01094-0. (Mesmer\u002FDeepCell.)\n- Bai Y, Zhu B, Rovira-Clave X, et al (2021) Adjacent cell marker lateral spillover compensation and reinforcement for multiplexed images. *Frontiers in Immunology* 12:652631. DOI 10.3389\u002Ffimmu.2021.652631. (REDSEA.)\n- Palla G, Spitzer H, Klein M, et al (2022) Squidpy: a scalable framework for spatial omics analysis. *Nature Methods* 19:171-178. DOI 10.1038\u002Fs41592-021-01358-2.\n- Hunter B, Nicorescu I, Foster E, et al (2024) OPTIMAL: an OPTimized Imaging Mass cytometry AnaLysis framework for benchmarking segmentation and data exploration. *Cytometry Part A* 105:36-53. DOI 10.1002\u002Fcyto.a.24803. (arcsinh cofactor 1 for IMC.)\n\n## Related Skills\n\n- imaging-mass-cytometry\u002Fdata-preprocessing - Hot pixel, spillover\n- imaging-mass-cytometry\u002Fcell-segmentation - Cellpose\u002FMesmer details\n- imaging-mass-cytometry\u002Fphenotyping - Cluster annotation\n- imaging-mass-cytometry\u002Fspatial-analysis - Spatial statistics\n- imaging-mass-cytometry\u002Fdifferential-analysis - Patient-level cross-condition testing\n- imaging-mass-cytometry\u002Finteractive-annotation - Manual cell labeling\n- imaging-mass-cytometry\u002Fquality-metrics - QC metrics\n- single-cell\u002Fclustering - Clustering methods\n- spatial-transcriptomics\u002Fspatial-statistics - Related spatial methods\n","## Version Compatibility\n\nReference examples tested with: Cellpose 4.0+ (cpsam model), anndata 0.10+, matplotlib 3.8+, numpy 1.26+, pandas 2.2+, scanpy 1.10+, scvi-tools 1.1+, squidpy 1.3+, steinbock 0.16+\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n- R: `packageVersion('\u003Cpkg>')` then `?function_name` to verify parameters\n- CLI: `\u003Ctool> --version` then `\u003Ctool> --help` to confirm flags\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# Imaging Mass Cytometry Pipeline\n\n**\"Process my imaging mass cytometry data from images to spatial analysis\"** -> Orchestrate image preprocessing (steinbock), cell segmentation (Cellpose), phenotyping (FlowSOM\u002Fscanpy), spatial neighborhood analysis (squidpy), and tissue community detection.\n\nThis is a workflow skill: it owns the chaining decisions and hand-offs, not the internals of any one step.\n\n## The governing principle\n\nSegmentation is the largest irreversible error source, and it is spatial: every per-cell number is a mask-bounded pixel average, so a wrong boundary fabricates cell types before any expression QC can see them. The seam ORDER — and the patient-level unit — is therefore what decides trustworthiness.\n\n1. **The comparison frame (panel + segmentation frame + pixel size) is committed once and inherited by every per-cell number.** The summed membrane channel encodes a cell-type bias (sum BROADLY-expressed markers, or segmentation under-performs on cell types lacking a strong membrane marker); Mesmer was trained at model_mpp ~0.5 um and rescales the input to it, so passing the wrong pixel size (Mesmer's `image_mpp` defaults to None = NO rescaling, assuming the input is already at model resolution — the true pixel size must be passed explicitly; steinbock's `--pixelsize` flag wraps `image_mpp` and defaults to 1.0) rescales cells to the wrong learned size and degrades every boundary. No downstream step recovers a merged or split cell.\n2. **Channel spillover is compensated on PIXELS before segmentation; lateral spillover (REDSEA) runs on the per-cell table AFTER segmentation — they are DIFFERENT problems.** Metal-isotope crosstalk is a pixel-level NNLS correction whose compensated value must be what gets averaged into the per-cell mean (post-aggregation is wrong). REDSEA corrects real signal leaking across shared cell boundaries at ~1 um even with perfect segmentation and zero channel spillover — it is defined on segmented neighbors, so it must run after segmentation. Running REDSEA pre-segmentation, or channel comp post-aggregation, is a category error.\n3. **The experimental unit is the PATIENT, not the cell or the ROI.** Cells and ROIs from one patient are not independent replicates; a cell-level or per-image test over correlated cells is pseudoreplication (reports p~0 for trivial effects). Aggregate to per-patient proportions\u002Fsummaries, then a mixed model \u002F scCODA. Arcsinh cofactor is 1 for IMC integer ion counts, NOT the suspension-CyTOF 5 (which over-compresses them). Impossible lineage-exclusive co-expression is a segmentation\u002Fspillover ALARM, not a hybrid cell type.\n\n## Made-once commitments\n\n| Commitment | Consequence inherited downstream |\n|------------|----------------------------------|\n| Panel (metal->antibody; membrane-sum channels) | Which channels extract and phenotype; a narrow membrane sum biases segmentation against some cell types |\n| Segmentation frame (nuclear + membrane channels) | Every per-cell number (all are mask-bounded pixel averages); the largest irreversible error source |\n| Pixel size (steinbock `--pixelsize` \u002F Mesmer `image_mpp`, ~1.0 um for IMC) | Boundary quality + all spatial distances; the wrong value rescales cells to the wrong learned size |\n| Arcsinh cofactor = 1 (IMC), not 5 (CyTOF) | Clustering\u002Fphenotyping distances; cofactor 5 over-compresses integer ion counts |\n\n## Pipeline Overview\n\n```\nRaw MCD\u002FTIFF Files ──> Image Processing ──> Cell Masks\n                                                 │\n                                                 ▼\n                ┌─────────────────────────────────────────────┐\n                │              imc-pipeline                   │\n                ├─────────────────────────────────────────────┤\n                │  1. Data Preprocessing (spillover, hot px)  │\n                │  2. Cell Segmentation (Cellpose\u002FMesmer)     │\n                │  3. Single-cell Quantification              │\n                │  4. Clustering & Phenotyping                │\n                │  5. Spatial Analysis                        │\n                │  6. Visualization                           │\n                └─────────────────────────────────────────────┘\n                                                 │\n                                                 ▼\n                    Cell Types + Spatial Neighborhoods\n```\n\n## Decisions Threaded Through This Pipeline\n\nFour reframes govern every stage and are detailed in the depended-on skills: IMC pixels are integer ion COUNTS (arcsinh cofactor 1, not the suspension-CyTOF 5), and spillover is spatial so it must be NNLS-compensated before segmentation; segmentation is the largest irreversible error source, so impossible double-positives are a QC alarm, not biology; a spatial interaction is a hypothesis test whose null silently decides whether the result is real or a density artifact; and the experimental unit is the patient, not the cell, so cross-condition tests aggregate to patients before testing.\n\n## Complete steinbock Workflow\n\n### Step 1: Setup and Preprocessing\n\n```bash\n# generate the panel template; edit the keep column before extracting\nsteinbock preprocess imc panel\n\n# extract per-channel TIFFs (keep-filtered, panel-ordered) with hot-pixel removal\n# (--hpf is a signed 8-neighbor difference; 50 is a count, tune to dynamic range)\nsteinbock preprocess imc images --hpf 50\n\n# channel spillover is compensated with NNLS (CATALYST\u002Fcytomapper, R) on the pixel images\n# BEFORE segmentation when spatial analysis is the endpoint -- see data-preprocessing\n```\n\n### Step 2: Cell Segmentation\n\n```bash\n# Mesmer\u002FDeepCell whole-cell (nuclear-first); membrane channels aggregated via the panel column.\n# --pixelsize is steinbock's CLI flag for the acquisition resolution (it wraps Mesmer's image_mpp);\n# steinbock defaults it to 1.0 um for IMC, so pass the true value explicitly rather than relying on it.\nsteinbock segment deepcell --pixelsize 1.0 --minmax -o masks\n\n# Alternative: Cellpose container (Cellpose 4+ default model cpsam; channel order reversed vs native)\nsteinbock segment cellpose --minmax -o masks\n```\n\n### Step 3: Single-cell Quantification\n\n```bash\n# Extract per-cell MEAN intensities (mean is the default and the right phenotyping aggregator;\n# sum confounds cell size with expression)\nsteinbock measure intensities -o intensities\n\n# Measure cell properties (area, centroid, eccentricity)\nsteinbock measure regionprops -o regionprops\n\n# Build the spatial neighbor graph (expansion within a max distance; match the graph to the\n# biological claim -- contact vs proximity -- in spatial-analysis)\nsteinbock measure neighbors --type expansion --dmax 15 -o neighbors\n```\n\n## Complete Python Workflow\n\n```python\nimport pandas as pd\nimport numpy as np\nimport anndata as ad\nimport scanpy as sc\nimport squidpy as sq\nfrom pathlib import Path\n\n# === 1. LOAD DATA ===\ndata_dir = Path('steinbock_output')\n\nintensities = pd.read_csv(data_dir \u002F 'intensities.csv', index_col=0)\nregionprops = pd.read_csv(data_dir \u002F 'regionprops.csv', index_col=0)\nneighbors = pd.read_csv(data_dir \u002F 'neighbors.csv')\n\nprint(f'Loaded {len(intensities)} cells')\n\n# === 2. CREATE ANNDATA ===\nadata = ad.AnnData(X=intensities.values, obs=regionprops, var=pd.DataFrame(index=intensities.columns))\nadata.obs['image_id'] = pd.Categorical([idx.rsplit('_', 1)[0] for idx in intensities.index])   # strip only the trailing cell index: rsplit keeps Patient1_ROI002 distinct from Patient1_ROI001. squidpy library_key requires a categorical, not object\u002Fstring\nadata.obs['cell_id'] = intensities.index\n\n# Add spatial coordinates (skimage regionprops_table names them centroid-0 (y) \u002F centroid-1 (x))\nadata.obsm['spatial'] = regionprops[['centroid-0', 'centroid-1']].values\n\n# === 3. PREPROCESSING ===\n# Arcsinh transform: cofactor 1 for IMC single-cell means (Hunter 2024), NOT the\n# suspension-CyTOF cofactor 5, which over-compresses IMC's lower-count means\nadata.layers['counts'] = adata.X.copy()\nadata.X = np.arcsinh(adata.X \u002F 1)\n\n# Scale for clustering\nsc.pp.scale(adata, max_value=10)\nadata.raw = adata.copy()\n\n# === 4. DIMENSIONALITY REDUCTION ===\nsc.pp.pca(adata, n_comps=20)\nsc.pp.neighbors(adata, n_neighbors=15)\nsc.tl.umap(adata)\n\n# === 5. CLUSTERING ===\nsc.tl.leiden(adata, resolution=0.8)\nprint(f'Found {adata.obs[\"leiden\"].nunique()} clusters')\n\n# === 6. PHENOTYPING ===\n# Marker expression per cluster\nsc.tl.rank_genes_groups(adata, 'leiden', method='wilcoxon')\nmarker_genes = sc.get.rank_genes_groups_df(adata, group=None)\n\n# Annotate clusters based on markers\ncluster_annotations = {\n    '0': 'T cells',\n    '1': 'Macrophages',\n    '2': 'Tumor',\n    '3': 'B cells',\n    '4': 'Stromal'\n}\nadata.obs['cell_type'] = adata.obs['leiden'].map(cluster_annotations)\n\n# === 7. SPATIAL ANALYSIS ===\n# Build spatial graph PER IMAGE (library_key), else Delaunay fabricates edges across ROIs\nsq.gr.spatial_neighbors(adata, coord_type='generic', delaunay=True, library_key='image_id')\n\n# Neighborhood enrichment\nsq.gr.nhood_enrichment(adata, cluster_key='cell_type')\n\n# Co-occurrence analysis\nsq.gr.co_occurrence(adata, cluster_key='cell_type')\n\n# Ripley's statistics\nsq.gr.ripley(adata, cluster_key='cell_type', mode='L')\n\n# === 8. VISUALIZATION ===\nimport matplotlib.pyplot as plt\n\n# UMAP by cell type\nfig, axes = plt.subplots(1, 2, figsize=(14, 5))\nsc.pl.umap(adata, color='cell_type', ax=axes[0], show=False)\nsc.pl.umap(adata, color='leiden', ax=axes[1], show=False)\nplt.savefig('umap_celltypes.png', dpi=150, bbox_inches='tight')\n\n# Spatial plot. Pick the image dynamically: image_id is derived from the cell index, so a hardcoded\n# literal selects zero cells and spatial_scatter errors on the empty subset.\nfig, ax = plt.subplots(figsize=(10, 10))\nfirst_image = adata.obs['image_id'].iloc[0]\nsq.pl.spatial_scatter(adata[adata.obs['image_id'] == first_image],\n                      color='cell_type', shape=None, size=10, ax=ax)\nplt.savefig('spatial_celltypes.png', dpi=150, bbox_inches='tight')\n\n# Neighborhood enrichment heatmap\nsq.pl.nhood_enrichment(adata, cluster_key='cell_type')\nplt.savefig('neighborhood_enrichment.png', dpi=150, bbox_inches='tight')\n\n# === 9. DIFFERENTIAL ANALYSIS (patient is the unit, NOT the cell) ===\nimport statsmodels.formula.api as smf\n\n# aggregate to per-image proportions, then test across PATIENTS -- a cell-level or per-image\n# test over correlated cells is pseudoreplication and reports p~0 for trivial effects.\n# obs must carry patient and condition columns; see differential-analysis for scCODA\n# (compositional) and the spatial differential path.\ncounts = adata.obs.groupby(['patient', 'condition', 'image_id', 'cell_type'], observed=True).size().unstack(fill_value=0)   # observed=True: image_id is categorical; the default expands the full cartesian product into all-zero phantom rows -> NaN proportions\nimage_prop = counts.div(counts.sum(axis=1), axis=0).reset_index()\ntarget = 'Tumor'   # an actual cell_type column from cluster_annotations above (single-word for the formula)\nres = smf.mixedlm(f'{target} ~ condition', image_prop, groups=image_prop['patient']).fit()  # patient random effect\nprint(res.summary())\n\nadata.write('imc_analysis.h5ad')\nprint('Analysis complete!')\n```\n\n## R Alternative (imcRtools)\n\n```r\nlibrary(imcRtools)\nlibrary(cytomapper)\nlibrary(CATALYST)\n\n# Read steinbock output\nspe \u003C- read_steinbock('steinbock_output\u002F')\n\n# Transform (cofactor 1 for IMC single-cell means, not 5)\nassay(spe, 'exprs') \u003C- asinh(counts(spe) \u002F 1)\n\n# Cluster (CATALYST runDR takes assay=; cluster() always uses the 'exprs' assay, no assay arg)\nspe \u003C- runDR(spe, features = rownames(spe), assay = 'exprs', dr = 'UMAP')\nspe \u003C- cluster(spe, features = rownames(spe), xdim = 10, ydim = 10, maxK = 20)\n\n# Spatial analysis. buildSpatialGraph names the colPair '\u003Ctype>_interaction_graph';\n# aggregateNeighbors counts a label via aggregate_by='metadata' + count_by=.\nspe \u003C- buildSpatialGraph(spe, img_id = 'sample_id', type = 'expansion', threshold = 20)\nspe \u003C- aggregateNeighbors(spe, colPairName = 'expansion_interaction_graph',\n                          aggregate_by = 'metadata', count_by = 'cluster_id')\n\n# Spatial context\nspe \u003C- detectCommunity(spe, colPairName = 'expansion_interaction_graph',\n                       size_threshold = 10, group_by = 'sample_id')\n\n# Plot (img_id is the colData COLUMN used to facet; read_steinbock names it 'sample_id', not 'image_id')\nplotSpatial(spe, img_id = 'sample_id', node_color_by = 'cluster_id')\n```\n\n## QC Checkpoints\n\n| Stage | Check | Action if Failed |\n|-------|-------|------------------|\n| Preprocessing | No hot pixel streaks | Lower threshold |\n| Segmentation | >80% cells detected | Adjust diameter |\n| Quantification | All markers extracted | Check panel.csv |\n| Clustering | 5-20 clusters | Adjust resolution |\n| Spatial | Neighbors detected | Check distance |\n\n## Workflow Variants\n\n### High-plex Panels (40+ markers)\n```python\n# Use batch-aware clustering\nimport scvi\n\nscvi.model.SCVI.setup_anndata(adata, batch_key='image_id')\nmodel = scvi.model.SCVI(adata)\nmodel.train()\nadata.obsm['X_scvi'] = model.get_latent_representation()\nsc.pp.neighbors(adata, use_rep='X_scvi')\n```\n\n### Tumor Microenvironment Analysis\n```python\n# Spatial cell-cell co-location around tumor (per-image, then aggregate to patient).\n# Note: sq.gr.ligrec keys ligand-receptor pairs on gene symbols from OmniPath, so it is\n# usually empty on a ~40-marker antibody panel -- prefer neighborhood enrichment for IMC.\nsq.gr.nhood_enrichment(adata, cluster_key='cell_type')   # see spatial-analysis for the null caveat\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| Impossible double-positive \"hybrid\" cell types | Spillover not corrected before phenotyping (channel and\u002For lateral) | NNLS channel compensation on pixels before segmentation; REDSEA on the per-cell table after; treat lineage-exclusive co-expression as a QC failure until proven |\n| Every boundary degraded, cells the wrong size | Wrong pixel size (Mesmer `image_mpp` defaults None=no rescaling, model trained at ~0.5; steinbock `--pixelsize` defaults 1.0) | Pass the true acquisition resolution explicitly (~1.0 um for IMC) |\n| Macrophages under-captured; biased comparison | Nuclear-expansion segmentation cross-compared with whole-cell data | Never quantitatively compare expansion-segmented vs whole-cell; report the expansion radius; use constrained (not free) dilation |\n| p~0 for a trivial effect | Pseudoreplication (cells\u002FROIs treated as replicates) | Aggregate to per-patient summaries; mixed model with patient random effect \u002F scCODA |\n| Markers over-compressed, noise clusters | Arcsinh cofactor 5 used on IMC | Cofactor 1 for IMC integer ion counts |\n| Acquisition batch drives the clusters | Batch confounded with \u002F not modeled against condition | Randomize acquisition order; batch-aware clustering (Harmony\u002FscVI) for clustering ONLY; model batch as a covariate; no rescue if batch==condition |\n\n## References\n\n- Windhager J, Zanotelli VRT, Schulz D, et al (2023) An end-to-end workflow for multiplexed image processing and analysis. *Nature Protocols* 18:3565-3613. DOI 10.1038\u002Fs41596-023-00881-0. (steinbock.)\n- Greenwald NF, Miller G, Moen E, et al (2022) Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. *Nature Biotechnology* 40:555-565. DOI 10.1038\u002Fs41587-021-01094-0. (Mesmer\u002FDeepCell.)\n- Bai Y, Zhu B, Rovira-Clave X, et al (2021) Adjacent cell marker lateral spillover compensation and reinforcement for multiplexed images. *Frontiers in Immunology* 12:652631. DOI 10.3389\u002Ffimmu.2021.652631. (REDSEA.)\n- Palla G, Spitzer H, Klein M, et al (2022) Squidpy: a scalable framework for spatial omics analysis. *Nature Methods* 19:171-178. DOI 10.1038\u002Fs41592-021-01358-2.\n- Hunter B, Nicorescu I, Foster E, et al (2024) OPTIMAL: an OPTimized Imaging Mass cytometry AnaLysis framework for benchmarking segmentation and data exploration. *Cytometry Part A* 105:36-53. DOI 10.1002\u002Fcyto.a.24803. (arcsinh cofactor 1 for IMC.)\n\n## Related Skills\n\n- imaging-mass-cytometry\u002Fdata-preprocessing - Hot pixel, spillover\n- imaging-mass-cytometry\u002Fcell-segmentation - Cellpose\u002FMesmer details\n- imaging-mass-cytometry\u002Fphenotyping - Cluster annotation\n- imaging-mass-cytometry\u002Fspatial-analysis - Spatial statistics\n- imaging-mass-cytometry\u002Fdifferential-analysis - Patient-level cross-condition testing\n- imaging-mass-cytometry\u002Finteractive-annotation - Manual cell labeling\n- imaging-mass-cytometry\u002Fquality-metrics - QC metrics\n- single-cell\u002Fclustering - Clustering methods\n- spatial-transcriptomics\u002Fspatial-statistics - Related spatial methods\n",{"name":5,"source":24,"license":15,"workflow":25,"tool_type":26,"depends_on":27,"description":7,"imported_at":35,"source_path":36,"primary_tool":37,"source_repository":38,"goal_approach_exempt":25},"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills",true,"python",[28,29,30,31,32,33,34],"imaging-mass-cytometry\u002Fdata-preprocessing","imaging-mass-cytometry\u002Fcell-segmentation","imaging-mass-cytometry\u002Fphenotyping","imaging-mass-cytometry\u002Fspatial-analysis","imaging-mass-cytometry\u002Fdifferential-analysis","imaging-mass-cytometry\u002Finteractive-annotation","imaging-mass-cytometry\u002Fquality-metrics","2026-09-20","workflows\u002Fimc-pipeline\u002FSKILL.md","steinbock","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-workflows-imc-pipeline","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":46,"prompt":56,"zipAvailable":25},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-workflows-imc-pipeline",{"tool":51,"command":52},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-workflows-imc-pipeline",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-workflows-imc-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-workflows-imc-pipeline\u002FSKILL.md",[58,64],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"examples\u002Fimc_analysis.py","SCRIPT","脚本",2972,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-workflows-imc-pipeline\u002Fexamples\u002Fimc_analysis.py",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"usage-guide.md","REFERENCE","参考文档",5029,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-workflows-imc-pipeline\u002Fusage-guide.md",[71,79,86,93,100,107],{"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":78},"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":78},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":78},"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":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":99,"publishedAt":78},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":78},"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":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":113,"publishedAt":78},"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",[],[]]