[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76EW4ACBF91YVXBD14CZRNB":3,"skill-same:01M76EW4ACBF91YVXBD14CZRNB":48},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M76EW4ACBF91YVXBD14CZRNB","spatial-transcriptomics-analysis-squidpy",null,"Squidpy spatial statistics on annotated spatial transcriptomics: build the spatial graph (Visium grid, kNN, radius, Delaunay), neighbourhood enrichment z-scores, distance-resolved co-occurrence, interaction matrix and centrality scores, Ripley's L\u002FF\u002FG point patterns, spatially variable genes by Moran's I \u002F Geary's C, and permutation ligand-receptor tests (ligrec, OmniPath). Works on Visium spots and single-cell-resolution data (Xenium, MERFISH, CosMx, Slide-seq). Needs cluster or cell type labels for all but the spatially variable gene step. For an end-to-end ligand-receptor workflow use spatial-transcriptomics-cell-cell-communication.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fspatial-transcriptomics-analysis-squidpy\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: \"spatial-transcriptomics-analysis-squidpy\"\ndescription: \"Squidpy spatial statistics on annotated spatial transcriptomics: build the spatial graph (Visium grid, kNN, radius, Delaunay), neighbourhood enrichment z-scores, distance-resolved co-occurrence, interaction matrix and centrality scores, Ripley's L\u002FF\u002FG point patterns, spatially variable genes by Moran's I \u002F Geary's C, and permutation ligand-receptor tests (ligrec, OmniPath). Works on Visium spots and single-cell-resolution data (Xenium, MERFISH, CosMx, Slide-seq). Needs cluster or cell type labels for all but the spatially variable gene step. For an end-to-end ligand-receptor workflow use spatial-transcriptomics-cell-cell-communication.\"\nlicense: \"CC-BY-4.0\"\n---\n\n# Squidpy Spatial Analysis\n\n## Overview\n\nGraph and point-pattern statistics that describe how cell types (or spot\nclusters) are arranged in tissue and which genes follow a spatial pattern.\nEach Core API module answers one question and exports a CSV:\n\n| Question | Module |\n|---|---|\n| Which cell types sit next to each other more than chance? | 2 Neighbourhood enrichment |\n| At what distance do two types co-occur? | 3 Co-occurrence |\n| How many contacts between types; which types are central? | 4 Interaction matrix + centrality |\n| Is a type clustered, random or dispersed? | 5 Ripley's statistics |\n| Which genes are spatially patterned? | 6 Spatial autocorrelation |\n| Which LR pairs are specific to a cluster pair? | 7 Ligand-receptor test |\n\n## When to Use\n\n- Testing which cell types are neighbours more or less often than chance\n- Measuring the distance range over which two cell types stay together\n- Deciding whether a cell type is clustered, random or evenly dispersed in tissue\n- Finding spatially variable genes by Moran's I or Geary's C\n- Running a quick permutation ligand-receptor test between labels\n- Use `spatial-transcriptomics-cell-cell-communication` instead for a multi-method LIANA ligand-receptor ranking with a spatial adjacency filter\n- For tissue regions without labels, use `spatial-domain-detection` first; for cell labels use `spatial-transcriptomics-cell-type-annotation`\n\n## Prerequisites\n\n- **Input**: AnnData with `obsm[\"spatial\"]` and log-normalised `X`\n- **Labels**: a categorical column in `obs` (cell types for single-cell data; spot\n  clusters or domains for Visium - spots are mixtures, so read results as\n  region-level)\n- **Network**: Module 7 downloads OmniPath interactions\n- **Versions**: squidpy >= 1.6. `sq.gr.spatial_neighbors` is deprecated from 1.7 in favour\n  of `spatial_neighbors_knn\u002F_radius\u002F_delaunay\u002F_grid`; it still works through 1.8\n\n```bash\n# Install only what `import` reports missing. `--pypi` keeps the env's scanpy\u002Fnumba\n# stack; a conda add can swap it and bare pip can shadow it.\npixi add --pypi squidpy omnipath scanpy\npixi add --pypi liana        # only for the local-LR-list recipe\n```\n\n## Quick Start\n\n```python\nimport scanpy as sc\nimport squidpy as sq\n\nadata = sc.read_h5ad(\"celltype_annotated.h5ad\")\nadata.obs[\"cell_type\"] = adata.obs[\"cell_type\"].astype(\"category\")\nsq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)     # Visium: coord_type=\"grid\", n_rings=1\nsq.gr.nhood_enrichment(adata, cluster_key=\"cell_type\", n_perms=1000, seed=0)\nsq.pl.nhood_enrichment(adata, cluster_key=\"cell_type\", save=\"nhood_quick.png\")\n```\n\n## Core API\n\n### Module 1: Build the Spatial Graph\n\nAll graph-based modules (2, 4, 6) read `obsp[\"spatial_connectivities\"]`.\n\n```python\nimport numpy as np\nimport pandas as pd\nimport scanpy as sc\nimport squidpy as sq\nimport matplotlib.pyplot as plt\n\nadata = sc.read_h5ad(\"celltype_annotated.h5ad\")\nCLUSTER_KEY = \"cell_type\"\nadata.obs[CLUSTER_KEY] = adata.obs[CLUSTER_KEY].astype(\"category\")\ncats = adata.obs[CLUSTER_KEY].cat.categories\n\nPLATFORM = \"single_cell\"      # \"visium\" for Visium spots\nif PLATFORM == \"visium\":\n    sq.gr.spatial_neighbors(adata, coord_type=\"grid\", n_neighs=6, n_rings=1)   # hexagonal ring\nelse:\n    sq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)\n    # alternatives: delaunay=True (natural neighbours) or radius=30 (same units as coordinates)\n\ndeg = np.asarray(adata.obsp[\"spatial_connectivities\"].sum(1)).ravel()\nprint(f\"{adata.n_obs} nodes, median degree {np.median(deg):.0f}, isolated {(deg == 0).sum()}\")\n```\n\n### Module 2: Neighbourhood Enrichment\n\nPermutation test of how often two labels are neighbours versus shuffled labels:\n\n```python\nsq.gr.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\nz = pd.DataFrame(adata.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=cats, columns=cats)\nz.to_csv(\"nhood_enrichment_z.csv\")\nsq.pl.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, method=\"average\", figsize=(8, 8),\n                       save=\"nhood_enrichment.png\")\n\npairs = z.where(np.triu(np.ones(z.shape, bool), k=1)).stack().sort_values()\nprint(\"most co-located:\\n\", pairs.tail(8).round(1))\nprint(\"most avoiding:\\n\", pairs.head(8).round(1))\n```\n\nz > 2: neighbours more often than chance; z \u003C -2: avoid each other. The\ndiagonal measures self-clustering.\n\n### Module 3: Co-occurrence Across Distances\n\nRatio of P(type B | within distance d of type A) to P(type B). Memory grows\nwith cell count squared, so subsample large data:\n\n```python\nMAX_CELLS = 20000\nsub = adata if adata.n_obs \u003C= MAX_CELLS else sc.pp.subsample(adata, n_obs=MAX_CELLS, random_state=0, copy=True)\nocc, interval = sq.gr.co_occurrence(sub, cluster_key=CLUSTER_KEY, interval=50, copy=True)\n# occ: n_clusters x n_clusters x n_distances; distance bins = interval[1:]\ndist = interval[1:] if len(interval) == occ.shape[2] + 1 else interval\nsub_cats = sub.obs[CLUSTER_KEY].cat.categories\nrows = [(a, b, d, occ[i, j, k]) for i, a in enumerate(sub_cats) for j, b in enumerate(sub_cats)\n        for k, d in enumerate(dist)]\nco = pd.DataFrame(rows, columns=[\"anchor\", \"other\", \"distance\", \"ratio\"])\nco.to_csv(\"co_occurrence.csv\", index=False)\n\nANCHOR = sub_cats[0]           # set to the cell type of interest\nsq.pl.co_occurrence(sub, cluster_key=CLUSTER_KEY, clusters=[ANCHOR], figsize=(8, 4),\n                    save=\"co_occurrence.png\")\n```\n\nRatio > 1 at short distance = attraction; the distance where it returns to 1\nis the spatial range of the association. Older squidpy versions also take\n`n_splits` to reduce memory.\n\n### Module 4: Interaction Matrix and Centrality\n\n```python\nim = sq.gr.interaction_matrix(adata, cluster_key=CLUSTER_KEY, normalized=True, copy=True)\nim = pd.DataFrame(im, index=cats, columns=cats)          # row-normalised share of each type's edges\nim.to_csv(\"interaction_matrix.csv\")\nsq.pl.interaction_matrix(adata, cluster_key=CLUSTER_KEY, save=\"interaction_matrix.png\")  # recomputes uns if needed\n\ncent = sq.gr.centrality_scores(adata, cluster_key=CLUSTER_KEY, copy=True)\ncent.to_csv(\"centrality_scores.csv\")\nprint(cent.sort_values(\"closeness_centrality\", ascending=False).round(3))\n```\n\nThe interaction matrix counts raw contacts (dominated by abundant types);\nuse Module 2 for enrichment over chance. Centrality: `degree_centrality` = share\nof graph connections, `closeness_centrality` = how central a type is in the\ntissue graph, `average_clustering` = how tightly its cells group.\n\n### Module 5: Ripley's Statistics\n\n```python\nMODE = \"L\"                     # \"L\" clustering scale, \"G\" nearest-neighbour, \"F\" empty space\nrip = sq.gr.ripley(adata, cluster_key=CLUSTER_KEY, mode=MODE, n_simulations=100, seed=0, copy=True)\nstat = rip[f\"{MODE}_stat\"]     # columns: bins, \u003Ccluster_key>, stats\nstat.to_csv(f\"ripley_{MODE}.csv\", index=False)\nfig, ax = plt.subplots(figsize=(8, 5))\nfor ct, d in stat.groupby(CLUSTER_KEY, observed=True):\n    ax.plot(d[\"bins\"], d[\"stats\"], label=ct)\nband = rip[\"sims_stat\"].groupby(\"bins\")[\"stats\"]      # columns: bins, simulations, stats\nlo, hi = band.min(), band.max()\nax.fill_between(lo.index, lo, hi, color=\"grey\", alpha=0.3, label=\"random (simulated)\")\nax.set_xlabel(\"distance\"); ax.set_ylabel(f\"Ripley's {MODE}\"); ax.legend(fontsize=7)\nplt.tight_layout(); plt.savefig(f\"ripley_{MODE}.png\", dpi=150); plt.close()\n```\n\nFor L, a curve above the simulated band = clustered at that distance, below =\ndispersed (regular). `rip[\"pvalues\"]` (cluster x bin) tests each curve\nagainst the simulations.\n\n### Module 6: Spatially Variable Genes\n\n```python\nGENES = None                   # None -> highly variable genes; or a list of genes\nif GENES is None:\n    if \"highly_variable\" not in adata.var:\n        sc.pp.highly_variable_genes(adata, n_top_genes=min(2000, adata.n_vars))\n    GENES = adata.var_names[adata.var[\"highly_variable\"]].tolist()\n\nsq.gr.spatial_autocorr(adata, mode=\"moran\", genes=GENES, n_perms=100, n_jobs=4, seed=0)\nmoran = adata.uns[\"moranI\"].sort_values(\"I\", ascending=False)\nmoran.to_csv(\"moran_i.csv\")\nsig = moran[moran[\"pval_norm_fdr_bh\"] \u003C 0.05]\nprint(f\"{len(sig)} of {len(moran)} genes spatially autocorrelated (FDR \u003C 0.05)\")\nprint(sig.head(15)[[\"I\", \"pval_norm_fdr_bh\"]])\nsq.pl.spatial_scatter(adata, color=sig.index[:4].tolist(), shape=None, size=2, save=\"top_svg.png\")\n```\n\nMoran's I near 1 = smooth spatial pattern, near 0 = random. For a targeted\npanel (\u003C ~1,000 genes) test all genes with `GENES = adata.var_names.tolist()`.\n`mode=\"geary\"` writes `uns[\"gearyC\"]` (C near 0 = clustered, 1 = random).\nOn Visium use `sq.pl.spatial_scatter` with the default `shape` to draw spots\nover the image.\n\n### Module 7: Ligand-Receptor Permutation Test\n\nCellPhoneDB-style test with OmniPath LR pairs, between labels:\n\n```python\nres = sq.gr.ligrec(adata, cluster_key=CLUSTER_KEY, n_perms=1000, threshold=0.1, use_raw=False,\n                   corr_method=\"fdr_bh\", seed=0, copy=True,\n                   transmitter_params={\"categories\": \"ligand\"}, receiver_params={\"categories\": \"receptor\"})\n\ndef to_long(df, name):\n    d = df.copy()\n    d.columns = [f\"{a}|{b}\" for a, b in d.columns]\n    d.index = [f\"{a}|{b}\" for a, b in d.index]\n    return d.stack().rename(name).rename_axis([\"lr\", \"pair\"]).reset_index()\n\nlr = to_long(res[\"means\"], \"mean\").merge(to_long(res[\"pvalues\"], \"pval\"), on=[\"lr\", \"pair\"])\nlr[[\"ligand\", \"receptor\"]] = lr[\"lr\"].str.split(\"|\", n=1, expand=True)\nlr[[\"sender\", \"receiver\"]] = lr[\"pair\"].str.split(\"|\", n=1, expand=True)\nhits = lr[(lr[\"pval\"] \u003C 0.05) & (lr[\"mean\"] > 0)].sort_values(\"mean\", ascending=False)\nhits.to_csv(\"ligrec_significant.csv\", index=False)\nprint(f\"{len(hits)} significant LR x cluster pair combinations\")\nprint(hits.head(15)[[\"sender\", \"receiver\", \"ligand\", \"receptor\", \"mean\", \"pval\"]])\n```\n\nMeans index = (ligand, receptor), columns = (sender, receiver). For a\nconsensus across several LR methods and spatial filtering use\n`spatial-transcriptomics-cell-cell-communication`.\n\n## Common Workflows\n\n### Workflow: Cell Type Arrangement Report\n\nGraph, enrichment, contact counts and the distance range of the strongest\npair, in one pass:\n\n```python\nsq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)\nsq.gr.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\nz = pd.DataFrame(adata.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=cats, columns=cats)\nim = pd.DataFrame(sq.gr.interaction_matrix(adata, cluster_key=CLUSTER_KEY, normalized=True, copy=True),\n                  index=cats, columns=cats)\npairs = z.where(np.triu(np.ones(z.shape, bool), k=1)).stack()\na, b = pairs.idxmax()\nreport = pd.DataFrame({\"z\": pairs, \"contact_share\": [im.loc[x, y] for x, y in pairs.index]})\nreport.sort_values(\"z\", ascending=False).to_csv(\"arrangement_report.csv\")\n\nsub = adata if adata.n_obs \u003C= 20000 else sc.pp.subsample(adata, n_obs=20000, random_state=0, copy=True)\nocc, interval = sq.gr.co_occurrence(sub, cluster_key=CLUSTER_KEY, interval=50, copy=True)\nsc_ = list(sub.obs[CLUSTER_KEY].cat.categories)\ndist = interval[1:] if len(interval) == occ.shape[2] + 1 else interval\nprint(f\"strongest pair: {a} - {b} (z = {pairs.max():.1f})\")\nprint(pd.Series(occ[sc_.index(a), sc_.index(b)], index=np.round(dist, 1)).head(10).round(2))\n```\n\n### Workflow: Compare Arrangement Between Samples\n\nNeighbourhood z-scores are computed per sample (graphs must not connect\ncells across sections), then compared:\n\n```python\nSAMPLE_KEY = \"sample\"\nzs = {}\nfor s in adata.obs[SAMPLE_KEY].unique():\n    a_s = adata[adata.obs[SAMPLE_KEY] == s].copy()\n    a_s.obs[CLUSTER_KEY] = a_s.obs[CLUSTER_KEY].cat.remove_unused_categories()\n    sq.gr.spatial_neighbors(a_s, coord_type=\"generic\", n_neighs=10)\n    sq.gr.nhood_enrichment(a_s, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\n    c = a_s.obs[CLUSTER_KEY].cat.categories\n    zs[s] = pd.DataFrame(a_s.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=c, columns=c).stack()\nzdf = pd.DataFrame(zs)\nzdf.to_csv(\"nhood_z_by_sample.csv\")\nprint(zdf.assign(spread=zdf.max(axis=1) - zdf.min(axis=1)).sort_values(\"spread\", ascending=False).head(15).round(1))\n```\n\nWith one section per condition the difference is descriptive; replicate\nsections are needed to call a change.\n\n## Key Parameters\n\n| Parameter | Module | Default | Effect |\n|---|---|---|---|\n| `n_neighs` \u002F `radius` \u002F `delaunay` | 1 | 10 \u002F - \u002F False | Defines \"neighbour\"; drives Steps 2, 4, 6 |\n| `n_rings` | 1 | 1 | Visium hex rings (1 = 6 neighbours) |\n| `n_perms` | 2, 6, 7 | 1000 \u002F 100 \u002F 1000 | Permutation precision |\n| `interval` | 3 | 50 | Number of distance bins |\n| `MODE` | 5 | \"L\" | Ripley's function |\n| `threshold` | 7 | 0.1 | Min fraction of a cluster expressing each gene |\n\n## Common Recipes\n\n### Recipe: Visium - Use Expression Clusters as Labels\n\nSpots have no cell type; cluster them on expression (or use domains from\n`spatial-domain-detection`) and run the modules on those labels:\n\n```python\nsc.pp.pca(adata, n_comps=30)\nsc.pp.neighbors(adata)\nsc.tl.leiden(adata, resolution=0.5, key_added=\"spot_cluster\", flavor=\"igraph\", n_iterations=2)\nsq.gr.spatial_neighbors(adata, coord_type=\"grid\", n_rings=1)\nsq.gr.nhood_enrichment(adata, cluster_key=\"spot_cluster\", n_perms=1000, seed=0)\nsq.pl.spatial_scatter(adata, color=\"spot_cluster\", save=\"spot_clusters.png\")   # spots over the H&E image\n```\n\n### Recipe: Ligrec with a Local LR List (no OmniPath download)\n\nPass interactions as a DataFrame with `source` (ligand) and `target`\n(receptor) columns, for example from LIANA's consensus resource:\n\n```python\nimport liana as li\n\npairs_df = li.rs.select_resource(\"consensus\").rename(columns={\"ligand\": \"source\", \"receptor\": \"target\"})\npairs_df = pairs_df[~pairs_df[\"source\"].str.contains(\"_\") & ~pairs_df[\"target\"].str.contains(\"_\")]   # simple genes only\nres = sq.gr.ligrec(adata, cluster_key=CLUSTER_KEY, interactions=pairs_df[[\"source\", \"target\"]],\n                   n_perms=1000, threshold=0.1, use_raw=False, corr_method=\"fdr_bh\", seed=0, copy=True)\nprint(res[\"pvalues\"].shape)\n```\n\nComplex (multi-subunit) pairs are dropped here; Module 7 with OmniPath or the\nCellPhoneDB route of `spatial-transcriptomics-cell-cell-communication` handles complexes.\n\n## Expected Outputs\n\n- `nhood_enrichment_z.csv`, `figures\u002Fnhood_enrichment.png`\n- `co_occurrence.csv`, `figures\u002Fco_occurrence.png`\n- `interaction_matrix.csv`, `centrality_scores.csv`\n- `ripley_L.csv`, `ripley_L.png`\n- `moran_i.csv`, `figures\u002Ftop_svg.png`\n- `ligrec_significant.csv`\n\n## Troubleshooting\n\n| Problem | Cause | Fix |\n|---|---|---|\n| `KeyError: spatial_connectivities` | Module 1 not run on this object | Run `sq.gr.spatial_neighbors` first |\n| `ValueError` on `coord_type=\"visium\"` | Not a valid value | Use `coord_type=\"grid\"` for Visium |\n| Co-occurrence out of memory | Too many cells | Lower `MAX_CELLS` |\n| Many isolated nodes | `radius` too small for the coordinate units | Check units (pixels vs microns); use kNN |\n| Ligrec fails to download | No internet \u002F omnipath missing | `pixi add --pypi omnipath`; or pass `interactions=` a DataFrame with `source`\u002F`target` columns |\n| Neighbourhood z-scores extreme for rare types | Few cells | Merge rare types or interpret with counts |\n| Deprecation warning for `spatial_neighbors` | squidpy >= 1.7 | Switch to `sq.gr.spatial_neighbors_knn` etc. |\n\n## Related Skills\n\n- `spatial-transcriptomics-cell-cell-communication` - LIANA\u002FCellPhoneDB ranking filtered by neighbourhood enrichment, local LR scores, MISTy\n- `spatial-transcriptomics-cell-type-annotation` - labels and niches for single-cell data\n- `spatial-domain-detection` - spatial domains to use as `CLUSTER_KEY`\n\n## References\n\n- Palla et al. (2022) Squidpy, Nature Methods: https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41592-021-01358-2\n- squidpy documentation: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002F\n- squidpy ligand-receptor test: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002Fapi\u002Fsquidpy.gr.ligrec.html\n- squidpy Ripley's statistics: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002Fapi\u002Fsquidpy.gr.ripley.html\n- OmniPath: https:\u002F\u002Fomnipathdb.org\u002F\n","# Squidpy Spatial Analysis\n\n## Overview\n\nGraph and point-pattern statistics that describe how cell types (or spot\nclusters) are arranged in tissue and which genes follow a spatial pattern.\nEach Core API module answers one question and exports a CSV:\n\n| Question | Module |\n|---|---|\n| Which cell types sit next to each other more than chance? | 2 Neighbourhood enrichment |\n| At what distance do two types co-occur? | 3 Co-occurrence |\n| How many contacts between types; which types are central? | 4 Interaction matrix + centrality |\n| Is a type clustered, random or dispersed? | 5 Ripley's statistics |\n| Which genes are spatially patterned? | 6 Spatial autocorrelation |\n| Which LR pairs are specific to a cluster pair? | 7 Ligand-receptor test |\n\n## When to Use\n\n- Testing which cell types are neighbours more or less often than chance\n- Measuring the distance range over which two cell types stay together\n- Deciding whether a cell type is clustered, random or evenly dispersed in tissue\n- Finding spatially variable genes by Moran's I or Geary's C\n- Running a quick permutation ligand-receptor test between labels\n- Use `spatial-transcriptomics-cell-cell-communication` instead for a multi-method LIANA ligand-receptor ranking with a spatial adjacency filter\n- For tissue regions without labels, use `spatial-domain-detection` first; for cell labels use `spatial-transcriptomics-cell-type-annotation`\n\n## Prerequisites\n\n- **Input**: AnnData with `obsm[\"spatial\"]` and log-normalised `X`\n- **Labels**: a categorical column in `obs` (cell types for single-cell data; spot\n  clusters or domains for Visium - spots are mixtures, so read results as\n  region-level)\n- **Network**: Module 7 downloads OmniPath interactions\n- **Versions**: squidpy >= 1.6. `sq.gr.spatial_neighbors` is deprecated from 1.7 in favour\n  of `spatial_neighbors_knn\u002F_radius\u002F_delaunay\u002F_grid`; it still works through 1.8\n\n```bash\n# Install only what `import` reports missing. `--pypi` keeps the env's scanpy\u002Fnumba\n# stack; a conda add can swap it and bare pip can shadow it.\npixi add --pypi squidpy omnipath scanpy\npixi add --pypi liana        # only for the local-LR-list recipe\n```\n\n## Quick Start\n\n```python\nimport scanpy as sc\nimport squidpy as sq\n\nadata = sc.read_h5ad(\"celltype_annotated.h5ad\")\nadata.obs[\"cell_type\"] = adata.obs[\"cell_type\"].astype(\"category\")\nsq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)     # Visium: coord_type=\"grid\", n_rings=1\nsq.gr.nhood_enrichment(adata, cluster_key=\"cell_type\", n_perms=1000, seed=0)\nsq.pl.nhood_enrichment(adata, cluster_key=\"cell_type\", save=\"nhood_quick.png\")\n```\n\n## Core API\n\n### Module 1: Build the Spatial Graph\n\nAll graph-based modules (2, 4, 6) read `obsp[\"spatial_connectivities\"]`.\n\n```python\nimport numpy as np\nimport pandas as pd\nimport scanpy as sc\nimport squidpy as sq\nimport matplotlib.pyplot as plt\n\nadata = sc.read_h5ad(\"celltype_annotated.h5ad\")\nCLUSTER_KEY = \"cell_type\"\nadata.obs[CLUSTER_KEY] = adata.obs[CLUSTER_KEY].astype(\"category\")\ncats = adata.obs[CLUSTER_KEY].cat.categories\n\nPLATFORM = \"single_cell\"      # \"visium\" for Visium spots\nif PLATFORM == \"visium\":\n    sq.gr.spatial_neighbors(adata, coord_type=\"grid\", n_neighs=6, n_rings=1)   # hexagonal ring\nelse:\n    sq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)\n    # alternatives: delaunay=True (natural neighbours) or radius=30 (same units as coordinates)\n\ndeg = np.asarray(adata.obsp[\"spatial_connectivities\"].sum(1)).ravel()\nprint(f\"{adata.n_obs} nodes, median degree {np.median(deg):.0f}, isolated {(deg == 0).sum()}\")\n```\n\n### Module 2: Neighbourhood Enrichment\n\nPermutation test of how often two labels are neighbours versus shuffled labels:\n\n```python\nsq.gr.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\nz = pd.DataFrame(adata.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=cats, columns=cats)\nz.to_csv(\"nhood_enrichment_z.csv\")\nsq.pl.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, method=\"average\", figsize=(8, 8),\n                       save=\"nhood_enrichment.png\")\n\npairs = z.where(np.triu(np.ones(z.shape, bool), k=1)).stack().sort_values()\nprint(\"most co-located:\\n\", pairs.tail(8).round(1))\nprint(\"most avoiding:\\n\", pairs.head(8).round(1))\n```\n\nz > 2: neighbours more often than chance; z \u003C -2: avoid each other. The\ndiagonal measures self-clustering.\n\n### Module 3: Co-occurrence Across Distances\n\nRatio of P(type B | within distance d of type A) to P(type B). Memory grows\nwith cell count squared, so subsample large data:\n\n```python\nMAX_CELLS = 20000\nsub = adata if adata.n_obs \u003C= MAX_CELLS else sc.pp.subsample(adata, n_obs=MAX_CELLS, random_state=0, copy=True)\nocc, interval = sq.gr.co_occurrence(sub, cluster_key=CLUSTER_KEY, interval=50, copy=True)\n# occ: n_clusters x n_clusters x n_distances; distance bins = interval[1:]\ndist = interval[1:] if len(interval) == occ.shape[2] + 1 else interval\nsub_cats = sub.obs[CLUSTER_KEY].cat.categories\nrows = [(a, b, d, occ[i, j, k]) for i, a in enumerate(sub_cats) for j, b in enumerate(sub_cats)\n        for k, d in enumerate(dist)]\nco = pd.DataFrame(rows, columns=[\"anchor\", \"other\", \"distance\", \"ratio\"])\nco.to_csv(\"co_occurrence.csv\", index=False)\n\nANCHOR = sub_cats[0]           # set to the cell type of interest\nsq.pl.co_occurrence(sub, cluster_key=CLUSTER_KEY, clusters=[ANCHOR], figsize=(8, 4),\n                    save=\"co_occurrence.png\")\n```\n\nRatio > 1 at short distance = attraction; the distance where it returns to 1\nis the spatial range of the association. Older squidpy versions also take\n`n_splits` to reduce memory.\n\n### Module 4: Interaction Matrix and Centrality\n\n```python\nim = sq.gr.interaction_matrix(adata, cluster_key=CLUSTER_KEY, normalized=True, copy=True)\nim = pd.DataFrame(im, index=cats, columns=cats)          # row-normalised share of each type's edges\nim.to_csv(\"interaction_matrix.csv\")\nsq.pl.interaction_matrix(adata, cluster_key=CLUSTER_KEY, save=\"interaction_matrix.png\")  # recomputes uns if needed\n\ncent = sq.gr.centrality_scores(adata, cluster_key=CLUSTER_KEY, copy=True)\ncent.to_csv(\"centrality_scores.csv\")\nprint(cent.sort_values(\"closeness_centrality\", ascending=False).round(3))\n```\n\nThe interaction matrix counts raw contacts (dominated by abundant types);\nuse Module 2 for enrichment over chance. Centrality: `degree_centrality` = share\nof graph connections, `closeness_centrality` = how central a type is in the\ntissue graph, `average_clustering` = how tightly its cells group.\n\n### Module 5: Ripley's Statistics\n\n```python\nMODE = \"L\"                     # \"L\" clustering scale, \"G\" nearest-neighbour, \"F\" empty space\nrip = sq.gr.ripley(adata, cluster_key=CLUSTER_KEY, mode=MODE, n_simulations=100, seed=0, copy=True)\nstat = rip[f\"{MODE}_stat\"]     # columns: bins, \u003Ccluster_key>, stats\nstat.to_csv(f\"ripley_{MODE}.csv\", index=False)\nfig, ax = plt.subplots(figsize=(8, 5))\nfor ct, d in stat.groupby(CLUSTER_KEY, observed=True):\n    ax.plot(d[\"bins\"], d[\"stats\"], label=ct)\nband = rip[\"sims_stat\"].groupby(\"bins\")[\"stats\"]      # columns: bins, simulations, stats\nlo, hi = band.min(), band.max()\nax.fill_between(lo.index, lo, hi, color=\"grey\", alpha=0.3, label=\"random (simulated)\")\nax.set_xlabel(\"distance\"); ax.set_ylabel(f\"Ripley's {MODE}\"); ax.legend(fontsize=7)\nplt.tight_layout(); plt.savefig(f\"ripley_{MODE}.png\", dpi=150); plt.close()\n```\n\nFor L, a curve above the simulated band = clustered at that distance, below =\ndispersed (regular). `rip[\"pvalues\"]` (cluster x bin) tests each curve\nagainst the simulations.\n\n### Module 6: Spatially Variable Genes\n\n```python\nGENES = None                   # None -> highly variable genes; or a list of genes\nif GENES is None:\n    if \"highly_variable\" not in adata.var:\n        sc.pp.highly_variable_genes(adata, n_top_genes=min(2000, adata.n_vars))\n    GENES = adata.var_names[adata.var[\"highly_variable\"]].tolist()\n\nsq.gr.spatial_autocorr(adata, mode=\"moran\", genes=GENES, n_perms=100, n_jobs=4, seed=0)\nmoran = adata.uns[\"moranI\"].sort_values(\"I\", ascending=False)\nmoran.to_csv(\"moran_i.csv\")\nsig = moran[moran[\"pval_norm_fdr_bh\"] \u003C 0.05]\nprint(f\"{len(sig)} of {len(moran)} genes spatially autocorrelated (FDR \u003C 0.05)\")\nprint(sig.head(15)[[\"I\", \"pval_norm_fdr_bh\"]])\nsq.pl.spatial_scatter(adata, color=sig.index[:4].tolist(), shape=None, size=2, save=\"top_svg.png\")\n```\n\nMoran's I near 1 = smooth spatial pattern, near 0 = random. For a targeted\npanel (\u003C ~1,000 genes) test all genes with `GENES = adata.var_names.tolist()`.\n`mode=\"geary\"` writes `uns[\"gearyC\"]` (C near 0 = clustered, 1 = random).\nOn Visium use `sq.pl.spatial_scatter` with the default `shape` to draw spots\nover the image.\n\n### Module 7: Ligand-Receptor Permutation Test\n\nCellPhoneDB-style test with OmniPath LR pairs, between labels:\n\n```python\nres = sq.gr.ligrec(adata, cluster_key=CLUSTER_KEY, n_perms=1000, threshold=0.1, use_raw=False,\n                   corr_method=\"fdr_bh\", seed=0, copy=True,\n                   transmitter_params={\"categories\": \"ligand\"}, receiver_params={\"categories\": \"receptor\"})\n\ndef to_long(df, name):\n    d = df.copy()\n    d.columns = [f\"{a}|{b}\" for a, b in d.columns]\n    d.index = [f\"{a}|{b}\" for a, b in d.index]\n    return d.stack().rename(name).rename_axis([\"lr\", \"pair\"]).reset_index()\n\nlr = to_long(res[\"means\"], \"mean\").merge(to_long(res[\"pvalues\"], \"pval\"), on=[\"lr\", \"pair\"])\nlr[[\"ligand\", \"receptor\"]] = lr[\"lr\"].str.split(\"|\", n=1, expand=True)\nlr[[\"sender\", \"receiver\"]] = lr[\"pair\"].str.split(\"|\", n=1, expand=True)\nhits = lr[(lr[\"pval\"] \u003C 0.05) & (lr[\"mean\"] > 0)].sort_values(\"mean\", ascending=False)\nhits.to_csv(\"ligrec_significant.csv\", index=False)\nprint(f\"{len(hits)} significant LR x cluster pair combinations\")\nprint(hits.head(15)[[\"sender\", \"receiver\", \"ligand\", \"receptor\", \"mean\", \"pval\"]])\n```\n\nMeans index = (ligand, receptor), columns = (sender, receiver). For a\nconsensus across several LR methods and spatial filtering use\n`spatial-transcriptomics-cell-cell-communication`.\n\n## Common Workflows\n\n### Workflow: Cell Type Arrangement Report\n\nGraph, enrichment, contact counts and the distance range of the strongest\npair, in one pass:\n\n```python\nsq.gr.spatial_neighbors(adata, coord_type=\"generic\", n_neighs=10)\nsq.gr.nhood_enrichment(adata, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\nz = pd.DataFrame(adata.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=cats, columns=cats)\nim = pd.DataFrame(sq.gr.interaction_matrix(adata, cluster_key=CLUSTER_KEY, normalized=True, copy=True),\n                  index=cats, columns=cats)\npairs = z.where(np.triu(np.ones(z.shape, bool), k=1)).stack()\na, b = pairs.idxmax()\nreport = pd.DataFrame({\"z\": pairs, \"contact_share\": [im.loc[x, y] for x, y in pairs.index]})\nreport.sort_values(\"z\", ascending=False).to_csv(\"arrangement_report.csv\")\n\nsub = adata if adata.n_obs \u003C= 20000 else sc.pp.subsample(adata, n_obs=20000, random_state=0, copy=True)\nocc, interval = sq.gr.co_occurrence(sub, cluster_key=CLUSTER_KEY, interval=50, copy=True)\nsc_ = list(sub.obs[CLUSTER_KEY].cat.categories)\ndist = interval[1:] if len(interval) == occ.shape[2] + 1 else interval\nprint(f\"strongest pair: {a} - {b} (z = {pairs.max():.1f})\")\nprint(pd.Series(occ[sc_.index(a), sc_.index(b)], index=np.round(dist, 1)).head(10).round(2))\n```\n\n### Workflow: Compare Arrangement Between Samples\n\nNeighbourhood z-scores are computed per sample (graphs must not connect\ncells across sections), then compared:\n\n```python\nSAMPLE_KEY = \"sample\"\nzs = {}\nfor s in adata.obs[SAMPLE_KEY].unique():\n    a_s = adata[adata.obs[SAMPLE_KEY] == s].copy()\n    a_s.obs[CLUSTER_KEY] = a_s.obs[CLUSTER_KEY].cat.remove_unused_categories()\n    sq.gr.spatial_neighbors(a_s, coord_type=\"generic\", n_neighs=10)\n    sq.gr.nhood_enrichment(a_s, cluster_key=CLUSTER_KEY, n_perms=1000, seed=0)\n    c = a_s.obs[CLUSTER_KEY].cat.categories\n    zs[s] = pd.DataFrame(a_s.uns[f\"{CLUSTER_KEY}_nhood_enrichment\"][\"zscore\"], index=c, columns=c).stack()\nzdf = pd.DataFrame(zs)\nzdf.to_csv(\"nhood_z_by_sample.csv\")\nprint(zdf.assign(spread=zdf.max(axis=1) - zdf.min(axis=1)).sort_values(\"spread\", ascending=False).head(15).round(1))\n```\n\nWith one section per condition the difference is descriptive; replicate\nsections are needed to call a change.\n\n## Key Parameters\n\n| Parameter | Module | Default | Effect |\n|---|---|---|---|\n| `n_neighs` \u002F `radius` \u002F `delaunay` | 1 | 10 \u002F - \u002F False | Defines \"neighbour\"; drives Steps 2, 4, 6 |\n| `n_rings` | 1 | 1 | Visium hex rings (1 = 6 neighbours) |\n| `n_perms` | 2, 6, 7 | 1000 \u002F 100 \u002F 1000 | Permutation precision |\n| `interval` | 3 | 50 | Number of distance bins |\n| `MODE` | 5 | \"L\" | Ripley's function |\n| `threshold` | 7 | 0.1 | Min fraction of a cluster expressing each gene |\n\n## Common Recipes\n\n### Recipe: Visium - Use Expression Clusters as Labels\n\nSpots have no cell type; cluster them on expression (or use domains from\n`spatial-domain-detection`) and run the modules on those labels:\n\n```python\nsc.pp.pca(adata, n_comps=30)\nsc.pp.neighbors(adata)\nsc.tl.leiden(adata, resolution=0.5, key_added=\"spot_cluster\", flavor=\"igraph\", n_iterations=2)\nsq.gr.spatial_neighbors(adata, coord_type=\"grid\", n_rings=1)\nsq.gr.nhood_enrichment(adata, cluster_key=\"spot_cluster\", n_perms=1000, seed=0)\nsq.pl.spatial_scatter(adata, color=\"spot_cluster\", save=\"spot_clusters.png\")   # spots over the H&E image\n```\n\n### Recipe: Ligrec with a Local LR List (no OmniPath download)\n\nPass interactions as a DataFrame with `source` (ligand) and `target`\n(receptor) columns, for example from LIANA's consensus resource:\n\n```python\nimport liana as li\n\npairs_df = li.rs.select_resource(\"consensus\").rename(columns={\"ligand\": \"source\", \"receptor\": \"target\"})\npairs_df = pairs_df[~pairs_df[\"source\"].str.contains(\"_\") & ~pairs_df[\"target\"].str.contains(\"_\")]   # simple genes only\nres = sq.gr.ligrec(adata, cluster_key=CLUSTER_KEY, interactions=pairs_df[[\"source\", \"target\"]],\n                   n_perms=1000, threshold=0.1, use_raw=False, corr_method=\"fdr_bh\", seed=0, copy=True)\nprint(res[\"pvalues\"].shape)\n```\n\nComplex (multi-subunit) pairs are dropped here; Module 7 with OmniPath or the\nCellPhoneDB route of `spatial-transcriptomics-cell-cell-communication` handles complexes.\n\n## Expected Outputs\n\n- `nhood_enrichment_z.csv`, `figures\u002Fnhood_enrichment.png`\n- `co_occurrence.csv`, `figures\u002Fco_occurrence.png`\n- `interaction_matrix.csv`, `centrality_scores.csv`\n- `ripley_L.csv`, `ripley_L.png`\n- `moran_i.csv`, `figures\u002Ftop_svg.png`\n- `ligrec_significant.csv`\n\n## Troubleshooting\n\n| Problem | Cause | Fix |\n|---|---|---|\n| `KeyError: spatial_connectivities` | Module 1 not run on this object | Run `sq.gr.spatial_neighbors` first |\n| `ValueError` on `coord_type=\"visium\"` | Not a valid value | Use `coord_type=\"grid\"` for Visium |\n| Co-occurrence out of memory | Too many cells | Lower `MAX_CELLS` |\n| Many isolated nodes | `radius` too small for the coordinate units | Check units (pixels vs microns); use kNN |\n| Ligrec fails to download | No internet \u002F omnipath missing | `pixi add --pypi omnipath`; or pass `interactions=` a DataFrame with `source`\u002F`target` columns |\n| Neighbourhood z-scores extreme for rare types | Few cells | Merge rare types or interpret with counts |\n| Deprecation warning for `spatial_neighbors` | squidpy >= 1.7 | Switch to `sq.gr.spatial_neighbors_knn` etc. |\n\n## Related Skills\n\n- `spatial-transcriptomics-cell-cell-communication` - LIANA\u002FCellPhoneDB ranking filtered by neighbourhood enrichment, local LR scores, MISTy\n- `spatial-transcriptomics-cell-type-annotation` - labels and niches for single-cell data\n- `spatial-domain-detection` - spatial domains to use as `CLUSTER_KEY`\n\n## References\n\n- Palla et al. (2022) Squidpy, Nature Methods: https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41592-021-01358-2\n- squidpy documentation: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002F\n- squidpy ligand-receptor test: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002Fapi\u002Fsquidpy.gr.ligrec.html\n- squidpy Ripley's statistics: https:\u002F\u002Fsquidpy.readthedocs.io\u002Fen\u002Fstable\u002Fapi\u002Fsquidpy.gr.ripley.html\n- OmniPath: https:\u002F\u002Fomnipathdb.org\u002F\n",{"name":5,"license":15,"description":7},"master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fawesome-skills\u002Fspatial-transcriptomics-analysis-squidpy",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill spatial-transcriptomics-analysis-squidpy",{"tool":40,"command":41},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill spatial-transcriptomics-analysis-squidpy",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill spatial-transcriptomics-analysis-squidpy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fspatial-transcriptomics-analysis-squidpy\u002FSKILL.md",true,[],[49,58,65,72,79,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":57},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":57},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":57},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":57},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"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":53,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":57},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\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":53,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":57},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]