[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BA3XS4ZEGKZY97R0MS9Z1":3,"skill-same:01M73BA3XS4ZEGKZY97R0MS9Z1":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},"01M73BA3XS4ZEGKZY97R0MS9Z1","autodock-vina-docking",null,"Molecular docking with AutoDock Vina (Python API). Receptor\u002Fligand prep (Meeko + RDKit), grid box, docking, pose and binding energy analysis, and batch virtual screening.","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\u002Fautodock-vina-docking\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"autodock-vina-docking\"\ndescription: \"Molecular docking with AutoDock Vina (Python API). Receptor\u002Fligand prep (Meeko + RDKit), grid box, docking, pose and binding energy analysis, and batch virtual screening.\"\nlicense: \"CC-BY-4.0\"\n---\n\n# AutoDock Vina Molecular Docking\n\n## Overview\n\nAutoDock Vina is one of the fastest and most widely used open-source molecular docking engines for predicting protein–ligand binding modes and affinities. This skill covers the full Python-based pipeline: receptor preparation from PDB, ligand preparation from SMILES\u002FSDF via Meeko and RDKit, search box definition, docking execution, pose analysis, and batch virtual screening for hit identification.\n\n## When to Use\n\n- Predicting binding poses of small molecules to a protein target\n- Estimating relative binding affinities (kcal\u002Fmol) for ligand ranking\n- Virtual screening of compound libraries against a target receptor\n- Validating docking protocols by re-docking co-crystallized ligands\n- Preparing docking inputs from SMILES strings without intermediate files\n- Comparing binding modes of analogs in a structure-activity relationship study\n- Generating starting poses for molecular dynamics simulations\n- Use **DiffDock** instead for blind docking when the binding site is unknown; use **GNINA** as an alternative with CNN scoring\n\n## Prerequisites\n\n- **Python packages**: `vina`, `meeko`, `rdkit`, `prody` (for PDB fetch), `py3Dmol` (for visualization)\n- **External tools**: `ADFR Suite` (provides `prepare_receptor` for PDBQT conversion) — download from https:\u002F\u002Fccsb.scripps.edu\u002Fadfr\u002Fdownloads\u002F\n- **Data requirements**: Protein structure (PDB file or PDB ID), ligand(s) as SMILES, SDF, or MOL2\n- **Environment**: Python 3.8+, Linux or macOS recommended\n\n```bash\npip install vina meeko rdkit-pypi prody py3Dmol\n# ADFR Suite must be installed separately for prepare_receptor\n```\n\n## Workflow\n\n### Step 1: Fetch and Prepare the Receptor\n\nDownload the protein structure, remove water\u002Fheteroatoms, and convert to PDBQT format.\n\n```python\nimport prody\nimport subprocess\nfrom pathlib import Path\n\n# Download PDB structure (example: HIV-1 protease, PDB 1HPV)\npdb_id = \"1HPV\"\npdb_file = f\"{pdb_id}.pdb\"\nprody.fetchPDB(pdb_id, compressed=False)\n\n# Extract protein chain only (remove water and ligands)\nstructure = prody.parsePDB(pdb_file)\nprotein = structure.select(\"protein\")\nprody.writePDB(f\"{pdb_id}_protein.pdb\", protein)\nprint(f\"Protein atoms: {protein.numAtoms()}\")\n\n# Convert to PDBQT using ADFR Suite's prepare_receptor\nreceptor_pdbqt = f\"{pdb_id}_receptor.pdbqt\"\nsubprocess.run([\n    \"prepare_receptor\",\n    \"-r\", f\"{pdb_id}_protein.pdb\",\n    \"-o\", receptor_pdbqt,\n    \"-A\", \"hydrogens\",  # add hydrogens\n], check=True)\nprint(f\"Receptor PDBQT: {receptor_pdbqt}\")\n```\n\n### Step 2: Identify the Binding Site\n\nDefine the docking search box centered on the known binding site or co-crystallized ligand.\n\n```python\nimport numpy as np\n\n# Option A: Center on co-crystallized ligand coordinates\nstructure = prody.parsePDB(pdb_file)\nligand = structure.select(\"hetero and not water and not ion\")\nif ligand is not None:\n    center = ligand.getCoords().mean(axis=0)\n    # Box size = ligand extent + padding\n    extent = ligand.getCoords().max(axis=0) - ligand.getCoords().min(axis=0)\n    box_size = extent + 10.0  # 10 Å padding on each side\n    print(f\"Binding site center: {center}\")\n    print(f\"Box size: {box_size}\")\nelse:\n    # Option B: Manual coordinates (from literature or visual inspection)\n    center = np.array([15.0, 54.0, 17.0])\n    box_size = np.array([25.0, 25.0, 25.0])\n    print(f\"Using manual box: center={center}, size={box_size}\")\n```\n\n### Step 3: Prepare the Ligand from SMILES\n\nUse RDKit for 3D coordinate generation and Meeko for PDBQT conversion.\n\n```python\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem\nfrom meeko import MoleculePreparation, PDBQTWriterLegacy\n\n# Define ligand (example: Indinavir, HIV protease inhibitor)\nsmiles = \"CC(C)(C)NC(=O)[C@@H]1CN(CCc2ccccc2)C[C@H]1O\"\nmol_name = \"indinavir_analog\"\n\n# Generate 3D coordinates with RDKit\nmol = Chem.MolFromSmiles(smiles)\nmol = Chem.AddHs(mol)\nAllChem.EmbedMolecule(mol, randomSeed=42)\nAllChem.MMFFOptimizeMolecule(mol)\n\n# Convert to PDBQT using Meeko\npreparator = MoleculePreparation()\nmol_setups = preparator.prepare(mol)\n\n# Write PDBQT string (for Vina API) or file\npdbqt_string = PDBQTWriterLegacy.write_string(mol_setups[0])[0]\nligand_pdbqt = f\"{mol_name}.pdbqt\"\nwith open(ligand_pdbqt, \"w\") as f:\n    f.write(pdbqt_string)\nprint(f\"Ligand PDBQT: {ligand_pdbqt} ({mol.GetNumAtoms()} atoms)\")\n```\n\n### Step 4: Run Docking\n\nInitialize AutoDock Vina, configure the search space, and execute docking.\n\n```python\nfrom vina import Vina\n\n# Initialize Vina\nv = Vina(sf_name=\"vina\", cpu=4)\n\n# Load receptor and ligand\nv.set_receptor(receptor_pdbqt)\nv.set_ligand_from_file(ligand_pdbqt)\n\n# Define search space\nv.compute_vina_maps(\n    center=center.tolist(),\n    box_size=box_size.tolist(),\n)\n\n# Run docking\nv.dock(\n    exhaustiveness=32,   # Higher = more thorough (default 8)\n    n_poses=10,          # Number of output poses\n)\n\n# Write output poses\noutput_file = f\"{mol_name}_docked.pdbqt\"\nv.write_poses(output_file, n_poses=10, overwrite=True)\nprint(f\"Docking complete. Poses written to {output_file}\")\n```\n\n### Step 5: Analyze Docking Results\n\nExtract binding energies and RMSD values from the docked poses using Vina's built-in API.\n\n```python\n# Method A: Vina built-in energies (most reliable)\nenergies = v.energies(n_poses=10)\n# Each row: [total, inter, intra, torsions, intra_best_pose]\nprint(f\"{'Pose':\u003C6} {'Total (kcal\u002Fmol)':\u003C18} {'Inter':\u003C10} {'Intra':\u003C10}\")\nprint(\"-\" * 44)\nfor i, e in enumerate(energies):\n    print(f\"{i+1:\u003C6} {e[0]:\u003C18.2f} {e[1]:\u003C10.2f} {e[2]:\u003C10.2f}\")\n\nprint(f\"\\nBest pose: {energies[0][0]:.2f} kcal\u002Fmol\")\n\n# Method B: Parse PDBQT output with Meeko (for RDKit conversion)\nfrom meeko import PDBQTMolecule, RDKitMolCreate\npdbqt_mol = PDBQTMolecule.from_file(output_file)\nbest_pose_rdkit = RDKitMolCreate.from_pdbqt_mol(pdbqt_mol)[0]\nprint(f\"Best pose converted to RDKit mol: {best_pose_rdkit.GetNumAtoms()} atoms\")\n```\n\n### Step 6: Visualize Docking Results\n\nGenerate a 3D visualization of the docked complex using py3Dmol.\n\n```python\nimport py3Dmol\n\n# Load receptor and best docked pose\nwith open(f\"{pdb_id}_protein.pdb\") as f:\n    receptor_pdb = f.read()\nwith open(output_file) as f:\n    docked_pdbqt = f.read()\n\n# Create 3D viewer\nview = py3Dmol.view(width=800, height=600)\nview.addModel(receptor_pdb, \"pdb\")\nview.setStyle({\"model\": 0}, {\"cartoon\": {\"color\": \"lightgrey\"}})\n\n# Add docked ligand (first model only)\nfirst_model = docked_pdbqt.split(\"ENDMDL\")[0] + \"ENDMDL\"\nview.addModel(first_model, \"pdb\")\nview.setStyle({\"model\": 1}, {\"stick\": {\"colorscheme\": \"greenCarbon\"}})\n\n# Zoom to ligand\nview.zoomTo({\"model\": 1})\nview.show()\n# In Jupyter: displays interactive 3D view\n# To save: view.png() or view.write_html(\"docking_result.html\")\nprint(\"3D visualization rendered\")\n```\n\n### Step 7: Batch Virtual Screening\n\nScreen a library of compounds against the same receptor.\n\n```python\nimport pandas as pd\n\n# Define compound library\ncompounds = pd.DataFrame({\n    \"name\": [\"cpd_001\", \"cpd_002\", \"cpd_003\", \"cpd_004\", \"cpd_005\"],\n    \"smiles\": [\n        \"CC(=O)Oc1ccccc1C(=O)O\",          # Aspirin\n        \"CC(C)Cc1ccc(cc1)C(C)C(=O)O\",      # Ibuprofen\n        \"OC(=O)c1ccccc1O\",                  # Salicylic acid\n        \"CC12CCC3C(CCC4CC(=O)CCC34C)C1CCC2O\",  # Testosterone\n        \"c1ccc2c(c1)cc1ccc3cccc4ccc2c1c34\",     # Pyrene\n    ],\n})\n\n# Screen all compounds\nresults = []\nfor _, row in compounds.iterrows():\n    try:\n        # Prepare ligand\n        mol = Chem.MolFromSmiles(row[\"smiles\"])\n        mol = Chem.AddHs(mol)\n        AllChem.EmbedMolecule(mol, randomSeed=42)\n        AllChem.MMFFOptimizeMolecule(mol)\n\n        mol_setups = preparator.prepare(mol)\n        pdbqt_str = PDBQTWriterLegacy.write_string(mol_setups[0])[0]\n\n        # Dock\n        v_screen = Vina(sf_name=\"vina\", cpu=2)\n        v_screen.set_receptor(receptor_pdbqt)\n        v_screen.set_ligand_from_string(pdbqt_str)\n        v_screen.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n        v_screen.dock(exhaustiveness=16, n_poses=1)\n\n        energy = v_screen.energies(n_poses=1)[0][0]\n        results.append({\"name\": row[\"name\"], \"smiles\": row[\"smiles\"], \"energy_kcal\": energy})\n        print(f\"  {row['name']}: {energy:.2f} kcal\u002Fmol\")\n\n    except Exception as e:\n        results.append({\"name\": row[\"name\"], \"smiles\": row[\"smiles\"], \"energy_kcal\": None})\n        print(f\"  {row['name']}: FAILED ({e})\")\n\n# Rank by binding energy\nresults_df = pd.DataFrame(results).sort_values(\"energy_kcal\")\nresults_df.to_csv(\"screening_results.csv\", index=False)\nprint(f\"\\nTop hits:\\n{results_df.head()}\")\n```\n\n### Step 8: Save and Export\n\n```python\nimport os\nos.makedirs(\"results\", exist_ok=True)\n\n# Save summary\nresults_df.to_csv(\"results\u002Fscreening_results.csv\", index=False)\n\n# Save best poses for top hits\nfor _, row in results_df.head(3).iterrows():\n    print(f\"Top hit: {row['name']} → {row['energy_kcal']:.2f} kcal\u002Fmol\")\n\nprint(\"Virtual screening complete. Results in results\u002Fscreening_results.csv\")\n```\n\n## Key Parameters\n\n| Parameter | Default | Range \u002F Options | Effect |\n|-----------|---------|-----------------|--------|\n| `exhaustiveness` | `8` | `8`-`128` | Search thoroughness; 32+ recommended for publication |\n| `n_poses` | `9` | `1`-`20` | Number of output binding poses |\n| `energy_range` | `3.0` | `1.0`-`5.0` | Max energy difference (kcal\u002Fmol) from best pose to include |\n| `sf_name` | `\"vina\"` | `\"vina\"`, `\"ad4\"`, `\"vinardo\"` | Scoring function choice |\n| `cpu` | all | `1`-`N` | Number of CPU cores for docking |\n| `box_size` (xyz) | — | `15`-`30` Å per side | Search space dimensions; must enclose binding site + 5-10Å padding |\n| `center` (xyz) | — | Binding site coordinates | Center of the search box |\n| `randomSeed` (RDKit) | random | any int | Reproducible 3D conformer generation |\n| `padding` (box) | `10.0` Å | `5.0`-`15.0` Å | Extra space around known ligand for box definition |\n\n## Common Recipes\n\n### Recipe: Re-docking Validation (Cognate Docking)\n\nWhen to use: validating your protocol by re-docking the co-crystallized ligand and checking RMSD \u003C 2.0 Å.\n\n```python\nfrom rdkit.Chem import AllChem, rdMolAlign\n\n# Extract co-crystallized ligand from PDB\nref_ligand = Chem.MolFromPDBFile(f\"{pdb_id}_ligand.pdb\", removeHs=False)\n\n# Dock the same ligand\n# ... (use steps 3-4 above with the extracted ligand)\n\n# Calculate RMSD between docked pose and crystal structure\nrmsd = AllChem.GetBestRMS(ref_ligand, best_pose_rdkit)\nprint(f\"Re-docking RMSD: {rmsd:.2f} Å\")\nprint(f\"Validation: {'PASS' if rmsd \u003C 2.0 else 'FAIL'} (threshold: 2.0 Å)\")\n```\n\n### Recipe: Flexible Receptor Docking\n\nWhen to use: key binding-site residues need conformational freedom (e.g., induced fit).\n\n```python\n# Prepare receptor with flexible sidechains (using ADFR Suite)\n# prepare_receptor -r protein.pdb -o rigid.pdbqt -A hydrogens\n# prepare_flexreceptor -r rigid.pdbqt -s \"A:ARG8,A:ASP25,A:ILE50\"\n\nv_flex = Vina(sf_name=\"vina\", cpu=4)\nv_flex.set_receptor(\"rigid.pdbqt\", \"flex.pdbqt\")  # rigid + flexible parts\nv_flex.set_ligand_from_file(ligand_pdbqt)\nv_flex.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\nv_flex.dock(exhaustiveness=64, n_poses=10)\nv_flex.write_poses(\"docked_flex.pdbqt\", n_poses=5, overwrite=True)\n```\n\n### Recipe: Scoring Only (No Docking)\n\nWhen to use: evaluating the binding energy of a pre-positioned ligand without running a full search.\n\n```python\nv_score = Vina(sf_name=\"vina\")\nv_score.set_receptor(receptor_pdbqt)\nv_score.set_ligand_from_file(\"pre_positioned_ligand.pdbqt\")\nv_score.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n\n# Score current pose\nenergy = v_score.score()\nprint(f\"Score: {energy[0]:.2f} kcal\u002Fmol\")\n\n# Local minimization\nenergy_min = v_score.optimize()\nprint(f\"After local optimization: {energy_min[0]:.2f} kcal\u002Fmol\")\nv_score.write_pose(\"minimized.pdbqt\", overwrite=True)\n```\n\n### Recipe: Multiple Scoring Functions Comparison\n\nWhen to use: consensus scoring to increase confidence in docking results.\n\n```python\nscoring_results = {}\nfor sf in [\"vina\", \"vinardo\", \"ad4\"]:\n    v_sf = Vina(sf_name=sf, cpu=2)\n    v_sf.set_receptor(receptor_pdbqt)\n    v_sf.set_ligand_from_file(ligand_pdbqt)\n    v_sf.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n    v_sf.dock(exhaustiveness=16, n_poses=1)\n    scoring_results[sf] = v_sf.energies(n_poses=1)[0][0]\n\nfor sf, energy in scoring_results.items():\n    print(f\"  {sf}: {energy:.2f} kcal\u002Fmol\")\n```\n\n## Expected Outputs\n\n- `{name}_docked.pdbqt` — Docked poses in PDBQT format with binding energies in header\n- `results\u002Fscreening_results.csv` — Virtual screening results: compound name, SMILES, binding energy (kcal\u002Fmol)\n- `{pdb_id}_receptor.pdbqt` — Prepared receptor in PDBQT format\n- Figures: 3D docking visualization (interactive py3Dmol or static image)\n- Console output: ranked binding energies and RMSD values per pose\n\n## Troubleshooting\n\n| Problem | Cause | Solution |\n|---------|-------|----------|\n| `prepare_receptor` not found | ADFR Suite not in PATH | Add ADFR Suite bin to `$PATH` or use full path |\n| `RuntimeError: receptor not set` | Forgot to call `set_receptor` | Call `v.set_receptor(pdbqt_file)` before docking |\n| Very positive docking scores (>0) | Ligand outside box or bad geometry | Check box center\u002Fsize covers binding site; verify 3D coords |\n| All poses identical | `exhaustiveness` too low | Increase to 32-64 for reliable sampling |\n| `Meeko MoleculePreparation` error | Missing hydrogens on input mol | Always call `Chem.AddHs(mol)` before Meeko |\n| RMSD > 2Å in re-docking | Box too small or wrong center | Expand box by 5Å; verify center on co-crystallized ligand |\n| `EmbedMolecule` returns -1 | RDKit failed to generate 3D coords | Use `AllChem.EmbedMolecule(mol, maxAttempts=1000)` or try `useRandomCoords=True` |\n| Slow screening (>1min\u002Fcompound) | High exhaustiveness + large box | Reduce `exhaustiveness` to 8-16 for screening; narrow box |\n| `PDBQTWriterLegacy` not found | Old Meeko version | `pip install meeko>=0.5` — API changed from `write_pdbqt_string` |\n| Inconsistent energies across runs | Non-deterministic search | Set `seed` parameter in `v.dock(seed=42)` for reproducibility |\n\n## Bundled Resources\n\nThis skill includes reference files for deeper lookup. Read these on demand.\n\n### references\u002Freceptor_preparation_guide.md\nDetailed guide for receptor preparation: handling missing residues, protonation states (pH-dependent), metal ions, cofactors, and multi-chain complexes. Decision tree for when to use PDB2PQR, PROPKA, or manual protonation.\n\n### references\u002Fscoring_functions_comparison.md\nComparison of Vina, Vinardo, and AD4 scoring functions: accuracy benchmarks, speed trade-offs, and recommendations by target class (kinase, protease, GPCR, nuclear receptor).\n\n## References\n\n- [AutoDock Vina documentation](https:\u002F\u002Fautodock-vina.readthedocs.io\u002F) — Official docs and Python API (Apache-2.0)\n- [Eberhardt et al. (2021)](https:\u002F\u002Fdoi.org\u002F10.1021\u002Facs.jcim.1c00203) — \"AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings\", *J Chem Inf Model*\n- [Meeko: Preparation of small molecules for AutoDock](https:\u002F\u002Fgithub.com\u002Fforlilab\u002FMeeko) — Ligand PDBQT preparation from RDKit (LGPL)\n- [ADFR Suite](https:\u002F\u002Fccsb.scripps.edu\u002Fadfr\u002Fdownloads\u002F) — Receptor preparation tools from Scripps (free academic license)\n- [Forli et al. (2016)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fnprot.2016.051) — \"Computational protein-ligand docking and virtual drug screening with the AutoDock suite\", *Nat Protoc*\n- [RDKit documentation](https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002F) — Cheminformatics toolkit for ligand handling (BSD)\n","# AutoDock Vina Molecular Docking\n\n## Overview\n\nAutoDock Vina is one of the fastest and most widely used open-source molecular docking engines for predicting protein–ligand binding modes and affinities. This skill covers the full Python-based pipeline: receptor preparation from PDB, ligand preparation from SMILES\u002FSDF via Meeko and RDKit, search box definition, docking execution, pose analysis, and batch virtual screening for hit identification.\n\n## When to Use\n\n- Predicting binding poses of small molecules to a protein target\n- Estimating relative binding affinities (kcal\u002Fmol) for ligand ranking\n- Virtual screening of compound libraries against a target receptor\n- Validating docking protocols by re-docking co-crystallized ligands\n- Preparing docking inputs from SMILES strings without intermediate files\n- Comparing binding modes of analogs in a structure-activity relationship study\n- Generating starting poses for molecular dynamics simulations\n- Use **DiffDock** instead for blind docking when the binding site is unknown; use **GNINA** as an alternative with CNN scoring\n\n## Prerequisites\n\n- **Python packages**: `vina`, `meeko`, `rdkit`, `prody` (for PDB fetch), `py3Dmol` (for visualization)\n- **External tools**: `ADFR Suite` (provides `prepare_receptor` for PDBQT conversion) — download from https:\u002F\u002Fccsb.scripps.edu\u002Fadfr\u002Fdownloads\u002F\n- **Data requirements**: Protein structure (PDB file or PDB ID), ligand(s) as SMILES, SDF, or MOL2\n- **Environment**: Python 3.8+, Linux or macOS recommended\n\n```bash\npip install vina meeko rdkit-pypi prody py3Dmol\n# ADFR Suite must be installed separately for prepare_receptor\n```\n\n## Workflow\n\n### Step 1: Fetch and Prepare the Receptor\n\nDownload the protein structure, remove water\u002Fheteroatoms, and convert to PDBQT format.\n\n```python\nimport prody\nimport subprocess\nfrom pathlib import Path\n\n# Download PDB structure (example: HIV-1 protease, PDB 1HPV)\npdb_id = \"1HPV\"\npdb_file = f\"{pdb_id}.pdb\"\nprody.fetchPDB(pdb_id, compressed=False)\n\n# Extract protein chain only (remove water and ligands)\nstructure = prody.parsePDB(pdb_file)\nprotein = structure.select(\"protein\")\nprody.writePDB(f\"{pdb_id}_protein.pdb\", protein)\nprint(f\"Protein atoms: {protein.numAtoms()}\")\n\n# Convert to PDBQT using ADFR Suite's prepare_receptor\nreceptor_pdbqt = f\"{pdb_id}_receptor.pdbqt\"\nsubprocess.run([\n    \"prepare_receptor\",\n    \"-r\", f\"{pdb_id}_protein.pdb\",\n    \"-o\", receptor_pdbqt,\n    \"-A\", \"hydrogens\",  # add hydrogens\n], check=True)\nprint(f\"Receptor PDBQT: {receptor_pdbqt}\")\n```\n\n### Step 2: Identify the Binding Site\n\nDefine the docking search box centered on the known binding site or co-crystallized ligand.\n\n```python\nimport numpy as np\n\n# Option A: Center on co-crystallized ligand coordinates\nstructure = prody.parsePDB(pdb_file)\nligand = structure.select(\"hetero and not water and not ion\")\nif ligand is not None:\n    center = ligand.getCoords().mean(axis=0)\n    # Box size = ligand extent + padding\n    extent = ligand.getCoords().max(axis=0) - ligand.getCoords().min(axis=0)\n    box_size = extent + 10.0  # 10 Å padding on each side\n    print(f\"Binding site center: {center}\")\n    print(f\"Box size: {box_size}\")\nelse:\n    # Option B: Manual coordinates (from literature or visual inspection)\n    center = np.array([15.0, 54.0, 17.0])\n    box_size = np.array([25.0, 25.0, 25.0])\n    print(f\"Using manual box: center={center}, size={box_size}\")\n```\n\n### Step 3: Prepare the Ligand from SMILES\n\nUse RDKit for 3D coordinate generation and Meeko for PDBQT conversion.\n\n```python\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem\nfrom meeko import MoleculePreparation, PDBQTWriterLegacy\n\n# Define ligand (example: Indinavir, HIV protease inhibitor)\nsmiles = \"CC(C)(C)NC(=O)[C@@H]1CN(CCc2ccccc2)C[C@H]1O\"\nmol_name = \"indinavir_analog\"\n\n# Generate 3D coordinates with RDKit\nmol = Chem.MolFromSmiles(smiles)\nmol = Chem.AddHs(mol)\nAllChem.EmbedMolecule(mol, randomSeed=42)\nAllChem.MMFFOptimizeMolecule(mol)\n\n# Convert to PDBQT using Meeko\npreparator = MoleculePreparation()\nmol_setups = preparator.prepare(mol)\n\n# Write PDBQT string (for Vina API) or file\npdbqt_string = PDBQTWriterLegacy.write_string(mol_setups[0])[0]\nligand_pdbqt = f\"{mol_name}.pdbqt\"\nwith open(ligand_pdbqt, \"w\") as f:\n    f.write(pdbqt_string)\nprint(f\"Ligand PDBQT: {ligand_pdbqt} ({mol.GetNumAtoms()} atoms)\")\n```\n\n### Step 4: Run Docking\n\nInitialize AutoDock Vina, configure the search space, and execute docking.\n\n```python\nfrom vina import Vina\n\n# Initialize Vina\nv = Vina(sf_name=\"vina\", cpu=4)\n\n# Load receptor and ligand\nv.set_receptor(receptor_pdbqt)\nv.set_ligand_from_file(ligand_pdbqt)\n\n# Define search space\nv.compute_vina_maps(\n    center=center.tolist(),\n    box_size=box_size.tolist(),\n)\n\n# Run docking\nv.dock(\n    exhaustiveness=32,   # Higher = more thorough (default 8)\n    n_poses=10,          # Number of output poses\n)\n\n# Write output poses\noutput_file = f\"{mol_name}_docked.pdbqt\"\nv.write_poses(output_file, n_poses=10, overwrite=True)\nprint(f\"Docking complete. Poses written to {output_file}\")\n```\n\n### Step 5: Analyze Docking Results\n\nExtract binding energies and RMSD values from the docked poses using Vina's built-in API.\n\n```python\n# Method A: Vina built-in energies (most reliable)\nenergies = v.energies(n_poses=10)\n# Each row: [total, inter, intra, torsions, intra_best_pose]\nprint(f\"{'Pose':\u003C6} {'Total (kcal\u002Fmol)':\u003C18} {'Inter':\u003C10} {'Intra':\u003C10}\")\nprint(\"-\" * 44)\nfor i, e in enumerate(energies):\n    print(f\"{i+1:\u003C6} {e[0]:\u003C18.2f} {e[1]:\u003C10.2f} {e[2]:\u003C10.2f}\")\n\nprint(f\"\\nBest pose: {energies[0][0]:.2f} kcal\u002Fmol\")\n\n# Method B: Parse PDBQT output with Meeko (for RDKit conversion)\nfrom meeko import PDBQTMolecule, RDKitMolCreate\npdbqt_mol = PDBQTMolecule.from_file(output_file)\nbest_pose_rdkit = RDKitMolCreate.from_pdbqt_mol(pdbqt_mol)[0]\nprint(f\"Best pose converted to RDKit mol: {best_pose_rdkit.GetNumAtoms()} atoms\")\n```\n\n### Step 6: Visualize Docking Results\n\nGenerate a 3D visualization of the docked complex using py3Dmol.\n\n```python\nimport py3Dmol\n\n# Load receptor and best docked pose\nwith open(f\"{pdb_id}_protein.pdb\") as f:\n    receptor_pdb = f.read()\nwith open(output_file) as f:\n    docked_pdbqt = f.read()\n\n# Create 3D viewer\nview = py3Dmol.view(width=800, height=600)\nview.addModel(receptor_pdb, \"pdb\")\nview.setStyle({\"model\": 0}, {\"cartoon\": {\"color\": \"lightgrey\"}})\n\n# Add docked ligand (first model only)\nfirst_model = docked_pdbqt.split(\"ENDMDL\")[0] + \"ENDMDL\"\nview.addModel(first_model, \"pdb\")\nview.setStyle({\"model\": 1}, {\"stick\": {\"colorscheme\": \"greenCarbon\"}})\n\n# Zoom to ligand\nview.zoomTo({\"model\": 1})\nview.show()\n# In Jupyter: displays interactive 3D view\n# To save: view.png() or view.write_html(\"docking_result.html\")\nprint(\"3D visualization rendered\")\n```\n\n### Step 7: Batch Virtual Screening\n\nScreen a library of compounds against the same receptor.\n\n```python\nimport pandas as pd\n\n# Define compound library\ncompounds = pd.DataFrame({\n    \"name\": [\"cpd_001\", \"cpd_002\", \"cpd_003\", \"cpd_004\", \"cpd_005\"],\n    \"smiles\": [\n        \"CC(=O)Oc1ccccc1C(=O)O\",          # Aspirin\n        \"CC(C)Cc1ccc(cc1)C(C)C(=O)O\",      # Ibuprofen\n        \"OC(=O)c1ccccc1O\",                  # Salicylic acid\n        \"CC12CCC3C(CCC4CC(=O)CCC34C)C1CCC2O\",  # Testosterone\n        \"c1ccc2c(c1)cc1ccc3cccc4ccc2c1c34\",     # Pyrene\n    ],\n})\n\n# Screen all compounds\nresults = []\nfor _, row in compounds.iterrows():\n    try:\n        # Prepare ligand\n        mol = Chem.MolFromSmiles(row[\"smiles\"])\n        mol = Chem.AddHs(mol)\n        AllChem.EmbedMolecule(mol, randomSeed=42)\n        AllChem.MMFFOptimizeMolecule(mol)\n\n        mol_setups = preparator.prepare(mol)\n        pdbqt_str = PDBQTWriterLegacy.write_string(mol_setups[0])[0]\n\n        # Dock\n        v_screen = Vina(sf_name=\"vina\", cpu=2)\n        v_screen.set_receptor(receptor_pdbqt)\n        v_screen.set_ligand_from_string(pdbqt_str)\n        v_screen.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n        v_screen.dock(exhaustiveness=16, n_poses=1)\n\n        energy = v_screen.energies(n_poses=1)[0][0]\n        results.append({\"name\": row[\"name\"], \"smiles\": row[\"smiles\"], \"energy_kcal\": energy})\n        print(f\"  {row['name']}: {energy:.2f} kcal\u002Fmol\")\n\n    except Exception as e:\n        results.append({\"name\": row[\"name\"], \"smiles\": row[\"smiles\"], \"energy_kcal\": None})\n        print(f\"  {row['name']}: FAILED ({e})\")\n\n# Rank by binding energy\nresults_df = pd.DataFrame(results).sort_values(\"energy_kcal\")\nresults_df.to_csv(\"screening_results.csv\", index=False)\nprint(f\"\\nTop hits:\\n{results_df.head()}\")\n```\n\n### Step 8: Save and Export\n\n```python\nimport os\nos.makedirs(\"results\", exist_ok=True)\n\n# Save summary\nresults_df.to_csv(\"results\u002Fscreening_results.csv\", index=False)\n\n# Save best poses for top hits\nfor _, row in results_df.head(3).iterrows():\n    print(f\"Top hit: {row['name']} → {row['energy_kcal']:.2f} kcal\u002Fmol\")\n\nprint(\"Virtual screening complete. Results in results\u002Fscreening_results.csv\")\n```\n\n## Key Parameters\n\n| Parameter | Default | Range \u002F Options | Effect |\n|-----------|---------|-----------------|--------|\n| `exhaustiveness` | `8` | `8`-`128` | Search thoroughness; 32+ recommended for publication |\n| `n_poses` | `9` | `1`-`20` | Number of output binding poses |\n| `energy_range` | `3.0` | `1.0`-`5.0` | Max energy difference (kcal\u002Fmol) from best pose to include |\n| `sf_name` | `\"vina\"` | `\"vina\"`, `\"ad4\"`, `\"vinardo\"` | Scoring function choice |\n| `cpu` | all | `1`-`N` | Number of CPU cores for docking |\n| `box_size` (xyz) | — | `15`-`30` Å per side | Search space dimensions; must enclose binding site + 5-10Å padding |\n| `center` (xyz) | — | Binding site coordinates | Center of the search box |\n| `randomSeed` (RDKit) | random | any int | Reproducible 3D conformer generation |\n| `padding` (box) | `10.0` Å | `5.0`-`15.0` Å | Extra space around known ligand for box definition |\n\n## Common Recipes\n\n### Recipe: Re-docking Validation (Cognate Docking)\n\nWhen to use: validating your protocol by re-docking the co-crystallized ligand and checking RMSD \u003C 2.0 Å.\n\n```python\nfrom rdkit.Chem import AllChem, rdMolAlign\n\n# Extract co-crystallized ligand from PDB\nref_ligand = Chem.MolFromPDBFile(f\"{pdb_id}_ligand.pdb\", removeHs=False)\n\n# Dock the same ligand\n# ... (use steps 3-4 above with the extracted ligand)\n\n# Calculate RMSD between docked pose and crystal structure\nrmsd = AllChem.GetBestRMS(ref_ligand, best_pose_rdkit)\nprint(f\"Re-docking RMSD: {rmsd:.2f} Å\")\nprint(f\"Validation: {'PASS' if rmsd \u003C 2.0 else 'FAIL'} (threshold: 2.0 Å)\")\n```\n\n### Recipe: Flexible Receptor Docking\n\nWhen to use: key binding-site residues need conformational freedom (e.g., induced fit).\n\n```python\n# Prepare receptor with flexible sidechains (using ADFR Suite)\n# prepare_receptor -r protein.pdb -o rigid.pdbqt -A hydrogens\n# prepare_flexreceptor -r rigid.pdbqt -s \"A:ARG8,A:ASP25,A:ILE50\"\n\nv_flex = Vina(sf_name=\"vina\", cpu=4)\nv_flex.set_receptor(\"rigid.pdbqt\", \"flex.pdbqt\")  # rigid + flexible parts\nv_flex.set_ligand_from_file(ligand_pdbqt)\nv_flex.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\nv_flex.dock(exhaustiveness=64, n_poses=10)\nv_flex.write_poses(\"docked_flex.pdbqt\", n_poses=5, overwrite=True)\n```\n\n### Recipe: Scoring Only (No Docking)\n\nWhen to use: evaluating the binding energy of a pre-positioned ligand without running a full search.\n\n```python\nv_score = Vina(sf_name=\"vina\")\nv_score.set_receptor(receptor_pdbqt)\nv_score.set_ligand_from_file(\"pre_positioned_ligand.pdbqt\")\nv_score.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n\n# Score current pose\nenergy = v_score.score()\nprint(f\"Score: {energy[0]:.2f} kcal\u002Fmol\")\n\n# Local minimization\nenergy_min = v_score.optimize()\nprint(f\"After local optimization: {energy_min[0]:.2f} kcal\u002Fmol\")\nv_score.write_pose(\"minimized.pdbqt\", overwrite=True)\n```\n\n### Recipe: Multiple Scoring Functions Comparison\n\nWhen to use: consensus scoring to increase confidence in docking results.\n\n```python\nscoring_results = {}\nfor sf in [\"vina\", \"vinardo\", \"ad4\"]:\n    v_sf = Vina(sf_name=sf, cpu=2)\n    v_sf.set_receptor(receptor_pdbqt)\n    v_sf.set_ligand_from_file(ligand_pdbqt)\n    v_sf.compute_vina_maps(center=center.tolist(), box_size=box_size.tolist())\n    v_sf.dock(exhaustiveness=16, n_poses=1)\n    scoring_results[sf] = v_sf.energies(n_poses=1)[0][0]\n\nfor sf, energy in scoring_results.items():\n    print(f\"  {sf}: {energy:.2f} kcal\u002Fmol\")\n```\n\n## Expected Outputs\n\n- `{name}_docked.pdbqt` — Docked poses in PDBQT format with binding energies in header\n- `results\u002Fscreening_results.csv` — Virtual screening results: compound name, SMILES, binding energy (kcal\u002Fmol)\n- `{pdb_id}_receptor.pdbqt` — Prepared receptor in PDBQT format\n- Figures: 3D docking visualization (interactive py3Dmol or static image)\n- Console output: ranked binding energies and RMSD values per pose\n\n## Troubleshooting\n\n| Problem | Cause | Solution |\n|---------|-------|----------|\n| `prepare_receptor` not found | ADFR Suite not in PATH | Add ADFR Suite bin to `$PATH` or use full path |\n| `RuntimeError: receptor not set` | Forgot to call `set_receptor` | Call `v.set_receptor(pdbqt_file)` before docking |\n| Very positive docking scores (>0) | Ligand outside box or bad geometry | Check box center\u002Fsize covers binding site; verify 3D coords |\n| All poses identical | `exhaustiveness` too low | Increase to 32-64 for reliable sampling |\n| `Meeko MoleculePreparation` error | Missing hydrogens on input mol | Always call `Chem.AddHs(mol)` before Meeko |\n| RMSD > 2Å in re-docking | Box too small or wrong center | Expand box by 5Å; verify center on co-crystallized ligand |\n| `EmbedMolecule` returns -1 | RDKit failed to generate 3D coords | Use `AllChem.EmbedMolecule(mol, maxAttempts=1000)` or try `useRandomCoords=True` |\n| Slow screening (>1min\u002Fcompound) | High exhaustiveness + large box | Reduce `exhaustiveness` to 8-16 for screening; narrow box |\n| `PDBQTWriterLegacy` not found | Old Meeko version | `pip install meeko>=0.5` — API changed from `write_pdbqt_string` |\n| Inconsistent energies across runs | Non-deterministic search | Set `seed` parameter in `v.dock(seed=42)` for reproducibility |\n\n## Bundled Resources\n\nThis skill includes reference files for deeper lookup. Read these on demand.\n\n### references\u002Freceptor_preparation_guide.md\nDetailed guide for receptor preparation: handling missing residues, protonation states (pH-dependent), metal ions, cofactors, and multi-chain complexes. Decision tree for when to use PDB2PQR, PROPKA, or manual protonation.\n\n### references\u002Fscoring_functions_comparison.md\nComparison of Vina, Vinardo, and AD4 scoring functions: accuracy benchmarks, speed trade-offs, and recommendations by target class (kinase, protease, GPCR, nuclear receptor).\n\n## References\n\n- [AutoDock Vina documentation](https:\u002F\u002Fautodock-vina.readthedocs.io\u002F) — Official docs and Python API (Apache-2.0)\n- [Eberhardt et al. (2021)](https:\u002F\u002Fdoi.org\u002F10.1021\u002Facs.jcim.1c00203) — \"AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings\", *J Chem Inf Model*\n- [Meeko: Preparation of small molecules for AutoDock](https:\u002F\u002Fgithub.com\u002Fforlilab\u002FMeeko) — Ligand PDBQT preparation from RDKit (LGPL)\n- [ADFR Suite](https:\u002F\u002Fccsb.scripps.edu\u002Fadfr\u002Fdownloads\u002F) — Receptor preparation tools from Scripps (free academic license)\n- [Forli et al. (2016)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fnprot.2016.051) — \"Computational protein-ligand docking and virtual drug screening with the AutoDock suite\", *Nat Protoc*\n- [RDKit documentation](https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002F) — Cheminformatics toolkit for ligand handling (BSD)\n",{"name":5,"license":15,"description":7},"master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fawesome-skills\u002Fautodock-vina-docking",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 autodock-vina-docking",{"tool":40,"command":41},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill autodock-vina-docking",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill autodock-vina-docking","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fautodock-vina-docking\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",[],[]]