[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EFZFAQX9CN7KSKEAR5K5ZX":3,"skill-same:01M7EFZFAQX9CN7KSKEAR5K5ZX":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7EFZFAQX9CN7KSKEAR5K5ZX","bio-substructure-search",null,"Searches molecular libraries for substructure matches using SMARTS patterns with explicit handling of recursive SMARTS, ring membership, aromaticity dialect, vector binding, atom map indices, and reactive\u002FPAINS\u002FREOS\u002FBrenk filter catalogs. Use when filtering compounds by pharmacophore features, functional groups, scaffold matches, or screening for assay-interference \u002F structural alerts.","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-substructure-search\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-substructure-search\ndescription: Searches molecular libraries for substructure matches using SMARTS patterns with explicit handling of recursive SMARTS, ring membership, aromaticity dialect, vector binding, atom map indices, and reactive\u002FPAINS\u002FREOS\u002FBrenk filter catalogs. Use when filtering compounds by pharmacophore features, functional groups, scaffold matches, or screening for assay-interference \u002F structural alerts.\ntool_type: python\nprimary_tool: RDKit\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"chemoinformatics\u002Fsubstructure-search\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: RDKit 2024.09+. SMARTS dialect follows Daylight specification with RDKit extensions.\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show rdkit` then `help(rdkit.Chem.MolFromSmarts)` to check signatures\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# Substructure Search\n\nSearch molecular collections for structural patterns using SMARTS. The choice of SMARTS dialect, atom\u002Fbond matching mode, and structural-alert catalog determines whether the search is correctly capturing the intended chemistry. PAINS (Baell & Holloway 2010) is the most-cited but most-misunderstood filter -- it identifies patterns of assay interference, not \"bad molecules\". Knowing when to apply each catalog and how to interpret hits is essential.\n\nFor SMARTS-based reactions (transforming matched substructures), see `chemoinformatics\u002Freaction-enumeration`. For 3D pharmacophore matching, see `chemoinformatics\u002Fpharmacophore-modeling`.\n\n## SMARTS Grammar Essentials\n\n| Token | Meaning | Example |\n|-------|---------|---------|\n| `[#6]` | Atom by atomic number | `[#6]` carbon (any hybridization) |\n| `c` | Lowercase = aromatic | `c1ccccc1` benzene aromatic |\n| `C` | Uppercase = aliphatic only | `C(=O)O` carboxylic acid carbon |\n| `[CX4]` | Atom + connection count X | `[CX4]` sp3 carbon (4 connections) |\n| `[CX3]=O` | Carbonyl (CX3 = sp2 with 3 bonds) | matches ketone, aldehyde, ester C |\n| `[#6;R]` | Atom in ring | `[#6;R]` ring carbon |\n| `[#6;!R]` | Atom not in ring | `[#6;!R]` acyclic carbon |\n| `[#6;r6]` | Atom in 6-membered ring | `[#6;r6]` six-ring carbon |\n| `[a]` | Any aromatic atom | `[a]` |\n| `[!#1]` | Anything except H | `[!#1]` heavy atom |\n| `[N;H2]` | N with exactly 2 H; neighboring chemistry unconstrained | `[NH2]` also matches non-amine `NH2` environments unless context is added |\n| `[N+]` | Positively charged N | `[N+](=O)[O-]` nitro |\n| `[$(...)]` | Recursive SMARTS | `[$(c1ccccc1)]` aromatic 6-ring atom |\n| `[c]([F,Cl,Br,I])` | OR within brackets | aryl halide |\n| `~` | Any bond type | `c~c` any aromatic-aromatic bond |\n| `@` | Ring bond | `c@c` requires the matched bond to be in a ring |\n| `-` | Single bond explicit | `C-C` |\n| `=` | Double bond | `C=O` |\n| `:` | Aromatic bond explicit | |\n\n## Common SMARTS Patterns\n\n| Pattern | SMARTS | Notes |\n|---------|--------|-------|\n| Hydroxyl (alcohol + phenol) | `[OX2H]` | OX2H avoids matching O- in OH- |\n| Phenol only | `[OX2H][c]` | OH attached to aromatic carbon |\n| Aliphatic OH only | `[OX2H][CX4]` | OH attached to sp3 C |\n| Carboxylic acid | `[CX3](=O)[OX2H1]` | C(=O)OH |\n| Carboxylate | `[CX3](=O)[O-]` | C(=O)O- (deprotonated) |\n| Ester | `[CX3](=O)[OX2][!H]` | C(=O)O-R |\n| Amide | `[CX3](=[OX1])[NX3]` | C(=O)N-R |\n| Primary amine attached to carbon (excluding common amide-like N) | `[NX3;H2;$(N-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NH2; extend the exclusions for a project-specific amine definition |\n| Secondary amine attached to two carbons | `[NX3;H1;$(N(-[#6])-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NH- excluding common amide-like N |\n| Neutral tertiary amine attached to three carbons | `[NX3;H0;+0;$(N(-[#6])(-[#6])-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NR2 excluding common amide-like N |\n| Quaternary amine | `[NX4+]` | -NR4+ |\n| Nitro | `[N+](=O)[O-]` | -NO2 |\n| Nitrile | `[CX2]#[NX1]` | -C#N |\n| Sulfonamide | `[SX4](=[OX1])(=[OX1])[NX3]` | -S(=O)(=O)N |\n| Aryl halide | `[c][F,Cl,Br,I]` | halogen on aromatic |\n| Aliphatic halide | `[CX4][F,Cl,Br,I]` | halogen on sp3 C |\n| Hydrogen bond donor | Use a named feature definition such as RDKit `BaseFeatures.fdef` or `Lipinski.NumHDonors` | `[#7,#8;!H0]` is only a simplified N\u002FO-H query and is not a universal HBD model |\n| Hydrogen bond acceptor | Use a named feature definition such as RDKit `BaseFeatures.fdef` or `Lipinski.NumHAcceptors` | No short universal SMARTS correctly captures every accepted HBA chemistry model |\n| Michael acceptor | `[CX3]=[CX3][CX3]=O` | enone, acrylamide warhead |\n| Aldehyde | `[CX3H1](=O)` | -CHO |\n| Ketone | `[CX3;H0](=[OX1])([#6])[#6]` | Carbonyl carbon has two carbon substituents and no hydrogen |\n\n## Basic Substructure Match\n\n**Goal:** Test whether a molecule contains a SMARTS pattern and enumerate the matching atom indices.\n\n**Approach:** Parse the molecule with `MolFromSmiles` and the pattern with `MolFromSmarts`, gate with `HasSubstructMatch`, then call `GetSubstructMatches` and map each atom index back to the molecule for inspection.\n\n```python\nfrom rdkit import Chem\n\nmol = Chem.MolFromSmiles('c1ccc(O)cc1CCO')\npattern = Chem.MolFromSmarts('[OX2H]')\n\nif mol.HasSubstructMatch(pattern):\n    matches = mol.GetSubstructMatches(pattern)\n    for match in matches:\n        atoms = [mol.GetAtomWithIdx(i).GetSymbol() for i in match]\n```\n\n`HasSubstructMatch` returns bool, `GetSubstructMatches` returns tuple of tuples of atom indices.\n\n## Recursive SMARTS for Context-Aware Patterns\n\n`[$(pattern)]` matches an atom that *also* matches the entire pattern starting from itself. Critical for context-aware matching.\n\n```python\n# Aromatic carbon attached to a carbonyl\npat = Chem.MolFromSmarts('[$(c[C](=O))]')\n\n# Aniline-type N (aromatic carbon-N-H)\npat = Chem.MolFromSmarts('[$([NX3;H2][c])]')\n\n# Neutral tertiary amine with three sp3-carbon neighbors\npat = Chem.MolFromSmarts('[$([NX3]([CX4])([CX4])[CX4])]')\n\n# H-bond donor (per Lipinski, exclude quaternary)\nhbd = Chem.MolFromSmarts('[#7,#8;!H0;!$([NX3+])]')\n\n# For H-bond acceptors, use RDKit's maintained Lipinski\u002Ffeature definitions\n# instead of an ad hoc universal SMARTS.\nfrom rdkit.Chem import Lipinski\nn_acceptors = Lipinski.NumHAcceptors(mol)\n```\n\n## Structural-Alert Filter Catalogs\n\n| Filter | Origin | Patterns | Use case | Failure mode |\n|--------|--------|----------|----------|--------------|\n| PAINS_A | Baell & Holloway 2010 | 16 | Most populated source-data patterns (>=150 analogues per pattern) | Many false positives in primary screens; legitimate medicines flagged |\n| PAINS_B | Baell & Holloway 2010 | 55 | Intermediate source-data population (15-149 analogues per pattern) | Similar |\n| PAINS_C | Baell & Holloway 2010 | 409 | Least populated source-data patterns (1-14 analogues per pattern) | Most permissive |\n| BRENK | Brenk 2008 (DDS unsuitable) | 105 | Reactive \u002F toxicity \u002F undesirable | Useful for fragment \u002F virtual library |\n| NIH | NIH MLSMR | 180 in RDKit 2024.09 | Reactive groups, unstable | Legacy filter; verify count after toolkit upgrades |\n| ZINC | ZINC clean-leads | 50 in RDKit 2024.09 | Drug-like cleanup | Verify definitions after toolkit upgrades |\n| Glaxo \u002F Eli Lilly | Vendor lists | varies | Internal \"ugly\" filters | Often unpublished |\n| REOS | Walters & Murcko 2002 | property + structural | Drug-likeness combined filter | Hand-curated thresholds |\n\nThe PAINS A\u002FB\u002FC families encode pattern population in the original screening dataset, not increasing or decreasing external evidence strength.\n\n## When to Apply Each Filter\n\n| Scenario | Catalog | Reason |\n|----------|---------|--------|\n| Hit validation from biochemical screen | PAINS_A | Identify assay-interference candidates |\n| Library prep for HTS | PAINS_A + Brenk + ZINC | Remove clearly bad |\n| Fragment library design | Brenk + ZINC | Remove reactive; PAINS less critical at fragments |\n| Lead optimization | None mandatory | Filters can exclude valid leads |\n| Natural product analog | None | Filters trained on synthetic chemistry |\n| Covalent inhibitor design | Skip warhead filter | Warheads ARE the design |\n\n**Critical:** Capuzzi et al. (2017) found PAINS alerts in 87 FDA-approved small-molecule drugs. PAINS is a *flag for assay validation*, not a *killing filter*.\n\n## PAINS Filter\n\n**Goal:** Split a molecule list into PAINS-flagged and PAINS-clean sets using one or more PAINS catalog tiers.\n\n**Approach:** Configure `FilterCatalogParams` with the requested catalog enums, build a `FilterCatalog` once, and for each molecule use `GetFirstMatch` to either bucket it as clean or record the matching pattern description.\n\n```python\nfrom rdkit.Chem.FilterCatalog import FilterCatalog, FilterCatalogParams\n\ndef pains_filter(mols, catalogs=('PAINS_A',)):\n    params = FilterCatalogParams()\n    for cat in catalogs:\n        params.AddCatalog(getattr(FilterCatalogParams.FilterCatalogs, cat))\n    catalog = FilterCatalog(params)\n\n    flagged = []\n    clean = []\n    for mol in mols:\n        if mol is None:\n            continue\n        entry = catalog.GetFirstMatch(mol)\n        if entry is None:\n            clean.append(mol)\n        else:\n            flagged.append((mol, entry.GetDescription()))\n    return clean, flagged\n```\n\nAvailable catalog names: `PAINS_A`, `PAINS_B`, `PAINS_C`, `PAINS` (all), `BRENK`, `NIH`, `ZINC`, `ALL`.\n\n## Reaction-Reactive Group Filter (custom)\n\nFor HTS triage, filter electrophilic warheads (acrylamide, chloroacetamide, etc.) unless designing covalent inhibitors.\n\n**Goal:** Flag molecules containing electrophilic warheads or other reactive functional groups that would interfere with biochemical HTS.\n\n**Approach:** Maintain a named SMARTS dictionary of reactive groups (acid halides, epoxides, Michael acceptors, etc.), then per molecule scan each pattern with `HasSubstructMatch` and return the first matching warhead name.\n\n```python\nREACTIVE_SMARTS = {\n    'acid_anhydride': '[CX3](=O)O[CX3](=O)',\n    'acid_halide': '[CX3](=O)[F,Cl,Br,I]',\n    'alpha_halo_carbonyl': '[CX3](=O)C([F,Cl,Br,I])',\n    'aldehyde_reactive': '[CX3H1](=O)[#6;X4]',  # aliphatic aldehydes\n    'epoxide': 'C1OC1',\n    'aziridine': 'C1NC1',\n    'isocyanate': '[NX2]=C=[OX1]',\n    'isothiocyanate': '[NX2]=C=[SX1]',\n    'beta_lactam': 'C1(=O)NCC1',\n    'sulfonyl_halide': '[SX4](=O)(=O)[F,Cl,Br,I]',\n    'Michael_acceptor': '[CX3]=[CX3][CX3]=O',\n    'vinyl_sulfone': '[SX4](=O)(=O)C=C',\n}\n\ndef reactive_filter(mol, exclude_warheads=True):\n    if not exclude_warheads:\n        return False, None\n    for name, smarts in REACTIVE_SMARTS.items():\n        if mol.HasSubstructMatch(Chem.MolFromSmarts(smarts)):\n            return True, name\n    return False, None\n```\n\nFor covalent-inhibitor design, see `chemoinformatics\u002Fcovalent-design`; these warheads are the desired chemistry, not noise to filter.\n\n## Library Filtering with Multiple Patterns\n\n**Goal:** Reduce a molecule library to those that match all required SMARTS patterns and none of the excluded ones.\n\n**Approach:** Start from the full molecule list, iteratively intersect with each `include` SMARTS using `HasSubstructMatch`, then subtract any molecule matching an `exclude` SMARTS.\n\n```python\ndef filter_library(mols, include=None, exclude=None):\n    keep = list(mols)\n    if include:\n        for s in include:\n            p = Chem.MolFromSmarts(s)\n            keep = [m for m in keep if m and m.HasSubstructMatch(p)]\n    if exclude:\n        for s in exclude:\n            p = Chem.MolFromSmarts(s)\n            keep = [m for m in keep if m and not m.HasSubstructMatch(p)]\n    return keep\n```\n\n## Atom Map Indices in SMARTS\n\nAtom maps `[C:1]` track atoms through transformations. Used in reactions (`reaction-enumeration` skill) but also for substructure-based extraction:\n\n```python\n# Find amide N with attached aryl\npat = Chem.MolFromSmarts('[CX3:1](=O)[NX3:2][c:3]')\nmatch = mol.GetSubstructMatch(pat)\n\namide_C, amide_N, aryl_C = match\n```\n\n## Per-Tool Failure Modes\n\n### PAINS -- false positive on natural product\n\n**Trigger:** Library contains natural products, polyphenols, flavonoids, quinones.\n\n**Mechanism:** PAINS_A patterns target rhodanines, curcumins, polyhydroxylated polyphenols -- legitimate scaffolds in natural-product chemistry.\n\n**Symptom:** Library hits flagged as PAINS but trace back to validated natural products with confirmed activity.\n\n**Fix:** Use PAINS as a *flag* not a *delete*. Cross-check flagged compounds for orthogonal-assay confirmation (label-free e.g. SPR, ITC).\n\n### Aromaticity dialect mismatch\n\n**Trigger:** SMARTS pattern with `c` (aromatic) for a heteroatom-rich ring; molecule parsed with different aromaticity model.\n\n**Mechanism:** RDKit, OpenEye, ChemAxon differ on whether furan, thiazole, tropone, etc. are aromatic.\n\n**Symptom:** Same pattern matches in one toolkit, not in another.\n\n**Fix:** Re-canonicalize molecules within RDKit before applying SMARTS. Or use `[#6]:[#6]` instead of `c:c` (explicit element + bond type).\n\n### Tautomer-sensitive pattern miss\n\n**Trigger:** SMARTS targets keto form `C(=O)` but molecule is enol `C(O)=C`.\n\n**Mechanism:** Default canonical form differs by toolkit + standardization choice.\n\n**Symptom:** Known matching molecule reports no match.\n\n**Fix:** Use tautomer-aware match: enumerate tautomers and OR-match. Or canonicalize first via `chemoinformatics\u002Fmolecular-standardization`. Or expand pattern with `[$(C(=O)),$(C(O)=C)]`.\n\n### Stereochemistry ignored\n\n**Trigger:** SMARTS without `\u002F\\@` stereo markers applied to mol with explicit stereo.\n\n**Mechanism:** SMARTS matching is stereo-agnostic by default.\n\n**Symptom:** Wrong stereoisomer is matched as well as right one.\n\n**Fix:** `mol.GetSubstructMatches(pattern, useChirality=True)` to require chirality match.\n\n### Ring closure \u002F fused-ring specificity\n\n**Trigger:** A query must distinguish an isolated benzene ring from a six-membered aromatic ring embedded in a fused system.\n\n**Mechanism:** `c1ccccc1` matches six-membered aromatic cycles and therefore does match benzene cycles within naphthalene. Extra ring-membership or fusion constraints are required to exclude fused systems.\n\n**Symptom:** A nominal \"benzene\" query returns fused polyaromatics that the project intended to exclude.\n\n**Fix:** Keep `c1ccccc1` when any aromatic six-cycle is desired. When an isolated ring is required, add explicit ring-degree\u002Ffusion constraints and test the query against benzene, naphthalene, indole, and representative substituted controls.\n\n### Recursive SMARTS performance\n\n**Trigger:** Deeply nested recursive SMARTS over a large library.\n\n**Mechanism:** Each `[$()]` re-evaluates the inner pattern for every candidate atom.\n\n**Symptom:** Search 10x-100x slower than expected.\n\n**Fix:** Flatten recursion where possible; pre-filter with simpler pattern, then re-test with the recursive one.\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `Chem.MolFromSmarts` returns None | Invalid SMARTS grammar | Validate with `Chem.MolFromSmarts(smi, mergeHs=False)`; check parens, brackets |\n| `[OH]` gives unexpected hydroxyl matches | Query does not state the intended valence\u002Fconnectivity model | Use `[OX2H]` for neutral alcohol\u002Fphenol oxygen or a more specific context-aware pattern |\n| Pattern matches but library is \"empty\" | Mol failed sanitize | Try `Chem.SDMolSupplier(sanitize=False)` then catch errors |\n| Multiple matches per molecule | Single-match query expected | `GetSubstructMatch` returns first; `GetSubstructMatches` returns all |\n| Match indices but no fragment | Match returns atom indices in pattern order | Map to original mol via `mol.GetAtomWithIdx(i)` |\n| PAINS catalog initialization slow | Loading 1000+ patterns on every call | Build catalog once, reuse for batch |\n| Stereo SMARTS not matching | `useChirality=False` (default) | `mol.GetSubstructMatches(p, useChirality=True)` |\n\n## References\n\n- Baell & Holloway, *J. Med. Chem.* 53:2719-2740 (2010) -- original PAINS filter and tier evidence. https:\u002F\u002Fdoi.org\u002F10.1021\u002Fjm901137j\n- Capuzzi et al., *J. Chem. Inf. Model.* 57:417-427 (2017) -- PAINS reality check (FDA drug overlap). https:\u002F\u002Fdoi.org\u002F10.1021\u002Facs.jcim.6b00465\n- Brenk et al., *ChemMedChem* 3:435-444 (2008) -- structural alerts (BRENK filter). https:\u002F\u002Fdoi.org\u002F10.1002\u002Fcmdc.200700139\n- Walters & Murcko, *Adv. Drug Deliv. Rev.* 54:255-271 (2002) -- drug-likeness filtering, including REOS. https:\u002F\u002Fdoi.org\u002F10.1016\u002FS0169-409X(02)00003-0\n- Bruns & Watson, *J. Med. Chem.* 55:9763-9772 (2012) -- Eli Lilly medchem rules. https:\u002F\u002Fdoi.org\u002F10.1021\u002Fjm301008n\n- Daylight Chemical Information Systems, SMARTS theory documentation -- complete grammar reference. https:\u002F\u002Fwww.daylight.com\u002Fdayhtml\u002Fdoc\u002Ftheory\u002Ftheory.smarts.html\n\n## Related Skills\n\n- chemoinformatics\u002Fmolecular-io - Parse molecules before searching\n- chemoinformatics\u002Fmolecular-standardization - Canonicalize tautomers before SMARTS\n- chemoinformatics\u002Fsimilarity-searching - Fingerprint-based fuzzy matching\n- chemoinformatics\u002Fscaffold-analysis - Scaffold-based pattern derivation\n- chemoinformatics\u002Freaction-enumeration - SMARTS for chemical transformations\n- chemoinformatics\u002Fadmet-prediction - PAINS as ADMET filter\n- chemoinformatics\u002Fcovalent-design - Warhead chemistry\n","## Version Compatibility\n\nReference examples tested with: RDKit 2024.09+. SMARTS dialect follows Daylight specification with RDKit extensions.\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show rdkit` then `help(rdkit.Chem.MolFromSmarts)` to check signatures\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# Substructure Search\n\nSearch molecular collections for structural patterns using SMARTS. The choice of SMARTS dialect, atom\u002Fbond matching mode, and structural-alert catalog determines whether the search is correctly capturing the intended chemistry. PAINS (Baell & Holloway 2010) is the most-cited but most-misunderstood filter -- it identifies patterns of assay interference, not \"bad molecules\". Knowing when to apply each catalog and how to interpret hits is essential.\n\nFor SMARTS-based reactions (transforming matched substructures), see `chemoinformatics\u002Freaction-enumeration`. For 3D pharmacophore matching, see `chemoinformatics\u002Fpharmacophore-modeling`.\n\n## SMARTS Grammar Essentials\n\n| Token | Meaning | Example |\n|-------|---------|---------|\n| `[#6]` | Atom by atomic number | `[#6]` carbon (any hybridization) |\n| `c` | Lowercase = aromatic | `c1ccccc1` benzene aromatic |\n| `C` | Uppercase = aliphatic only | `C(=O)O` carboxylic acid carbon |\n| `[CX4]` | Atom + connection count X | `[CX4]` sp3 carbon (4 connections) |\n| `[CX3]=O` | Carbonyl (CX3 = sp2 with 3 bonds) | matches ketone, aldehyde, ester C |\n| `[#6;R]` | Atom in ring | `[#6;R]` ring carbon |\n| `[#6;!R]` | Atom not in ring | `[#6;!R]` acyclic carbon |\n| `[#6;r6]` | Atom in 6-membered ring | `[#6;r6]` six-ring carbon |\n| `[a]` | Any aromatic atom | `[a]` |\n| `[!#1]` | Anything except H | `[!#1]` heavy atom |\n| `[N;H2]` | N with exactly 2 H; neighboring chemistry unconstrained | `[NH2]` also matches non-amine `NH2` environments unless context is added |\n| `[N+]` | Positively charged N | `[N+](=O)[O-]` nitro |\n| `[$(...)]` | Recursive SMARTS | `[$(c1ccccc1)]` aromatic 6-ring atom |\n| `[c]([F,Cl,Br,I])` | OR within brackets | aryl halide |\n| `~` | Any bond type | `c~c` any aromatic-aromatic bond |\n| `@` | Ring bond | `c@c` requires the matched bond to be in a ring |\n| `-` | Single bond explicit | `C-C` |\n| `=` | Double bond | `C=O` |\n| `:` | Aromatic bond explicit | |\n\n## Common SMARTS Patterns\n\n| Pattern | SMARTS | Notes |\n|---------|--------|-------|\n| Hydroxyl (alcohol + phenol) | `[OX2H]` | OX2H avoids matching O- in OH- |\n| Phenol only | `[OX2H][c]` | OH attached to aromatic carbon |\n| Aliphatic OH only | `[OX2H][CX4]` | OH attached to sp3 C |\n| Carboxylic acid | `[CX3](=O)[OX2H1]` | C(=O)OH |\n| Carboxylate | `[CX3](=O)[O-]` | C(=O)O- (deprotonated) |\n| Ester | `[CX3](=O)[OX2][!H]` | C(=O)O-R |\n| Amide | `[CX3](=[OX1])[NX3]` | C(=O)N-R |\n| Primary amine attached to carbon (excluding common amide-like N) | `[NX3;H2;$(N-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NH2; extend the exclusions for a project-specific amine definition |\n| Secondary amine attached to two carbons | `[NX3;H1;$(N(-[#6])-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NH- excluding common amide-like N |\n| Neutral tertiary amine attached to three carbons | `[NX3;H0;+0;$(N(-[#6])(-[#6])-[#6]);!$(N-[C,S,P]=[O,S,N])]` | Carbon-substituted -NR2 excluding common amide-like N |\n| Quaternary amine | `[NX4+]` | -NR4+ |\n| Nitro | `[N+](=O)[O-]` | -NO2 |\n| Nitrile | `[CX2]#[NX1]` | -C#N |\n| Sulfonamide | `[SX4](=[OX1])(=[OX1])[NX3]` | -S(=O)(=O)N |\n| Aryl halide | `[c][F,Cl,Br,I]` | halogen on aromatic |\n| Aliphatic halide | `[CX4][F,Cl,Br,I]` | halogen on sp3 C |\n| Hydrogen bond donor | Use a named feature definition such as RDKit `BaseFeatures.fdef` or `Lipinski.NumHDonors` | `[#7,#8;!H0]` is only a simplified N\u002FO-H query and is not a universal HBD model |\n| Hydrogen bond acceptor | Use a named feature definition such as RDKit `BaseFeatures.fdef` or `Lipinski.NumHAcceptors` | No short universal SMARTS correctly captures every accepted HBA chemistry model |\n| Michael acceptor | `[CX3]=[CX3][CX3]=O` | enone, acrylamide warhead |\n| Aldehyde | `[CX3H1](=O)` | -CHO |\n| Ketone | `[CX3;H0](=[OX1])([#6])[#6]` | Carbonyl carbon has two carbon substituents and no hydrogen |\n\n## Basic Substructure Match\n\n**Goal:** Test whether a molecule contains a SMARTS pattern and enumerate the matching atom indices.\n\n**Approach:** Parse the molecule with `MolFromSmiles` and the pattern with `MolFromSmarts`, gate with `HasSubstructMatch`, then call `GetSubstructMatches` and map each atom index back to the molecule for inspection.\n\n```python\nfrom rdkit import Chem\n\nmol = Chem.MolFromSmiles('c1ccc(O)cc1CCO')\npattern = Chem.MolFromSmarts('[OX2H]')\n\nif mol.HasSubstructMatch(pattern):\n    matches = mol.GetSubstructMatches(pattern)\n    for match in matches:\n        atoms = [mol.GetAtomWithIdx(i).GetSymbol() for i in match]\n```\n\n`HasSubstructMatch` returns bool, `GetSubstructMatches` returns tuple of tuples of atom indices.\n\n## Recursive SMARTS for Context-Aware Patterns\n\n`[$(pattern)]` matches an atom that *also* matches the entire pattern starting from itself. Critical for context-aware matching.\n\n```python\n# Aromatic carbon attached to a carbonyl\npat = Chem.MolFromSmarts('[$(c[C](=O))]')\n\n# Aniline-type N (aromatic carbon-N-H)\npat = Chem.MolFromSmarts('[$([NX3;H2][c])]')\n\n# Neutral tertiary amine with three sp3-carbon neighbors\npat = Chem.MolFromSmarts('[$([NX3]([CX4])([CX4])[CX4])]')\n\n# H-bond donor (per Lipinski, exclude quaternary)\nhbd = Chem.MolFromSmarts('[#7,#8;!H0;!$([NX3+])]')\n\n# For H-bond acceptors, use RDKit's maintained Lipinski\u002Ffeature definitions\n# instead of an ad hoc universal SMARTS.\nfrom rdkit.Chem import Lipinski\nn_acceptors = Lipinski.NumHAcceptors(mol)\n```\n\n## Structural-Alert Filter Catalogs\n\n| Filter | Origin | Patterns | Use case | Failure mode |\n|--------|--------|----------|----------|--------------|\n| PAINS_A | Baell & Holloway 2010 | 16 | Most populated source-data patterns (>=150 analogues per pattern) | Many false positives in primary screens; legitimate medicines flagged |\n| PAINS_B | Baell & Holloway 2010 | 55 | Intermediate source-data population (15-149 analogues per pattern) | Similar |\n| PAINS_C | Baell & Holloway 2010 | 409 | Least populated source-data patterns (1-14 analogues per pattern) | Most permissive |\n| BRENK | Brenk 2008 (DDS unsuitable) | 105 | Reactive \u002F toxicity \u002F undesirable | Useful for fragment \u002F virtual library |\n| NIH | NIH MLSMR | 180 in RDKit 2024.09 | Reactive groups, unstable | Legacy filter; verify count after toolkit upgrades |\n| ZINC | ZINC clean-leads | 50 in RDKit 2024.09 | Drug-like cleanup | Verify definitions after toolkit upgrades |\n| Glaxo \u002F Eli Lilly | Vendor lists | varies | Internal \"ugly\" filters | Often unpublished |\n| REOS | Walters & Murcko 2002 | property + structural | Drug-likeness combined filter | Hand-curated thresholds |\n\nThe PAINS A\u002FB\u002FC families encode pattern population in the original screening dataset, not increasing or decreasing external evidence strength.\n\n## When to Apply Each Filter\n\n| Scenario | Catalog | Reason |\n|----------|---------|--------|\n| Hit validation from biochemical screen | PAINS_A | Identify assay-interference candidates |\n| Library prep for HTS | PAINS_A + Brenk + ZINC | Remove clearly bad |\n| Fragment library design | Brenk + ZINC | Remove reactive; PAINS less critical at fragments |\n| Lead optimization | None mandatory | Filters can exclude valid leads |\n| Natural product analog | None | Filters trained on synthetic chemistry |\n| Covalent inhibitor design | Skip warhead filter | Warheads ARE the design |\n\n**Critical:** Capuzzi et al. (2017) found PAINS alerts in 87 FDA-approved small-molecule drugs. PAINS is a *flag for assay validation*, not a *killing filter*.\n\n## PAINS Filter\n\n**Goal:** Split a molecule list into PAINS-flagged and PAINS-clean sets using one or more PAINS catalog tiers.\n\n**Approach:** Configure `FilterCatalogParams` with the requested catalog enums, build a `FilterCatalog` once, and for each molecule use `GetFirstMatch` to either bucket it as clean or record the matching pattern description.\n\n```python\nfrom rdkit.Chem.FilterCatalog import FilterCatalog, FilterCatalogParams\n\ndef pains_filter(mols, catalogs=('PAINS_A',)):\n    params = FilterCatalogParams()\n    for cat in catalogs:\n        params.AddCatalog(getattr(FilterCatalogParams.FilterCatalogs, cat))\n    catalog = FilterCatalog(params)\n\n    flagged = []\n    clean = []\n    for mol in mols:\n        if mol is None:\n            continue\n        entry = catalog.GetFirstMatch(mol)\n        if entry is None:\n            clean.append(mol)\n        else:\n            flagged.append((mol, entry.GetDescription()))\n    return clean, flagged\n```\n\nAvailable catalog names: `PAINS_A`, `PAINS_B`, `PAINS_C`, `PAINS` (all), `BRENK`, `NIH`, `ZINC`, `ALL`.\n\n## Reaction-Reactive Group Filter (custom)\n\nFor HTS triage, filter electrophilic warheads (acrylamide, chloroacetamide, etc.) unless designing covalent inhibitors.\n\n**Goal:** Flag molecules containing electrophilic warheads or other reactive functional groups that would interfere with biochemical HTS.\n\n**Approach:** Maintain a named SMARTS dictionary of reactive groups (acid halides, epoxides, Michael acceptors, etc.), then per molecule scan each pattern with `HasSubstructMatch` and return the first matching warhead name.\n\n```python\nREACTIVE_SMARTS = {\n    'acid_anhydride': '[CX3](=O)O[CX3](=O)',\n    'acid_halide': '[CX3](=O)[F,Cl,Br,I]',\n    'alpha_halo_carbonyl': '[CX3](=O)C([F,Cl,Br,I])',\n    'aldehyde_reactive': '[CX3H1](=O)[#6;X4]',  # aliphatic aldehydes\n    'epoxide': 'C1OC1',\n    'aziridine': 'C1NC1',\n    'isocyanate': '[NX2]=C=[OX1]',\n    'isothiocyanate': '[NX2]=C=[SX1]',\n    'beta_lactam': 'C1(=O)NCC1',\n    'sulfonyl_halide': '[SX4](=O)(=O)[F,Cl,Br,I]',\n    'Michael_acceptor': '[CX3]=[CX3][CX3]=O',\n    'vinyl_sulfone': '[SX4](=O)(=O)C=C',\n}\n\ndef reactive_filter(mol, exclude_warheads=True):\n    if not exclude_warheads:\n        return False, None\n    for name, smarts in REACTIVE_SMARTS.items():\n        if mol.HasSubstructMatch(Chem.MolFromSmarts(smarts)):\n            return True, name\n    return False, None\n```\n\nFor covalent-inhibitor design, see `chemoinformatics\u002Fcovalent-design`; these warheads are the desired chemistry, not noise to filter.\n\n## Library Filtering with Multiple Patterns\n\n**Goal:** Reduce a molecule library to those that match all required SMARTS patterns and none of the excluded ones.\n\n**Approach:** Start from the full molecule list, iteratively intersect with each `include` SMARTS using `HasSubstructMatch`, then subtract any molecule matching an `exclude` SMARTS.\n\n```python\ndef filter_library(mols, include=None, exclude=None):\n    keep = list(mols)\n    if include:\n        for s in include:\n            p = Chem.MolFromSmarts(s)\n            keep = [m for m in keep if m and m.HasSubstructMatch(p)]\n    if exclude:\n        for s in exclude:\n            p = Chem.MolFromSmarts(s)\n            keep = [m for m in keep if m and not m.HasSubstructMatch(p)]\n    return keep\n```\n\n## Atom Map Indices in SMARTS\n\nAtom maps `[C:1]` track atoms through transformations. Used in reactions (`reaction-enumeration` skill) but also for substructure-based extraction:\n\n```python\n# Find amide N with attached aryl\npat = Chem.MolFromSmarts('[CX3:1](=O)[NX3:2][c:3]')\nmatch = mol.GetSubstructMatch(pat)\n\namide_C, amide_N, aryl_C = match\n```\n\n## Per-Tool Failure Modes\n\n### PAINS -- false positive on natural product\n\n**Trigger:** Library contains natural products, polyphenols, flavonoids, quinones.\n\n**Mechanism:** PAINS_A patterns target rhodanines, curcumins, polyhydroxylated polyphenols -- legitimate scaffolds in natural-product chemistry.\n\n**Symptom:** Library hits flagged as PAINS but trace back to validated natural products with confirmed activity.\n\n**Fix:** Use PAINS as a *flag* not a *delete*. Cross-check flagged compounds for orthogonal-assay confirmation (label-free e.g. SPR, ITC).\n\n### Aromaticity dialect mismatch\n\n**Trigger:** SMARTS pattern with `c` (aromatic) for a heteroatom-rich ring; molecule parsed with different aromaticity model.\n\n**Mechanism:** RDKit, OpenEye, ChemAxon differ on whether furan, thiazole, tropone, etc. are aromatic.\n\n**Symptom:** Same pattern matches in one toolkit, not in another.\n\n**Fix:** Re-canonicalize molecules within RDKit before applying SMARTS. Or use `[#6]:[#6]` instead of `c:c` (explicit element + bond type).\n\n### Tautomer-sensitive pattern miss\n\n**Trigger:** SMARTS targets keto form `C(=O)` but molecule is enol `C(O)=C`.\n\n**Mechanism:** Default canonical form differs by toolkit + standardization choice.\n\n**Symptom:** Known matching molecule reports no match.\n\n**Fix:** Use tautomer-aware match: enumerate tautomers and OR-match. Or canonicalize first via `chemoinformatics\u002Fmolecular-standardization`. Or expand pattern with `[$(C(=O)),$(C(O)=C)]`.\n\n### Stereochemistry ignored\n\n**Trigger:** SMARTS without `\u002F\\@` stereo markers applied to mol with explicit stereo.\n\n**Mechanism:** SMARTS matching is stereo-agnostic by default.\n\n**Symptom:** Wrong stereoisomer is matched as well as right one.\n\n**Fix:** `mol.GetSubstructMatches(pattern, useChirality=True)` to require chirality match.\n\n### Ring closure \u002F fused-ring specificity\n\n**Trigger:** A query must distinguish an isolated benzene ring from a six-membered aromatic ring embedded in a fused system.\n\n**Mechanism:** `c1ccccc1` matches six-membered aromatic cycles and therefore does match benzene cycles within naphthalene. Extra ring-membership or fusion constraints are required to exclude fused systems.\n\n**Symptom:** A nominal \"benzene\" query returns fused polyaromatics that the project intended to exclude.\n\n**Fix:** Keep `c1ccccc1` when any aromatic six-cycle is desired. When an isolated ring is required, add explicit ring-degree\u002Ffusion constraints and test the query against benzene, naphthalene, indole, and representative substituted controls.\n\n### Recursive SMARTS performance\n\n**Trigger:** Deeply nested recursive SMARTS over a large library.\n\n**Mechanism:** Each `[$()]` re-evaluates the inner pattern for every candidate atom.\n\n**Symptom:** Search 10x-100x slower than expected.\n\n**Fix:** Flatten recursion where possible; pre-filter with simpler pattern, then re-test with the recursive one.\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `Chem.MolFromSmarts` returns None | Invalid SMARTS grammar | Validate with `Chem.MolFromSmarts(smi, mergeHs=False)`; check parens, brackets |\n| `[OH]` gives unexpected hydroxyl matches | Query does not state the intended valence\u002Fconnectivity model | Use `[OX2H]` for neutral alcohol\u002Fphenol oxygen or a more specific context-aware pattern |\n| Pattern matches but library is \"empty\" | Mol failed sanitize | Try `Chem.SDMolSupplier(sanitize=False)` then catch errors |\n| Multiple matches per molecule | Single-match query expected | `GetSubstructMatch` returns first; `GetSubstructMatches` returns all |\n| Match indices but no fragment | Match returns atom indices in pattern order | Map to original mol via `mol.GetAtomWithIdx(i)` |\n| PAINS catalog initialization slow | Loading 1000+ patterns on every call | Build catalog once, reuse for batch |\n| Stereo SMARTS not matching | `useChirality=False` (default) | `mol.GetSubstructMatches(p, useChirality=True)` |\n\n## References\n\n- Baell & Holloway, *J. Med. Chem.* 53:2719-2740 (2010) -- original PAINS filter and tier evidence. https:\u002F\u002Fdoi.org\u002F10.1021\u002Fjm901137j\n- Capuzzi et al., *J. Chem. Inf. Model.* 57:417-427 (2017) -- PAINS reality check (FDA drug overlap). https:\u002F\u002Fdoi.org\u002F10.1021\u002Facs.jcim.6b00465\n- Brenk et al., *ChemMedChem* 3:435-444 (2008) -- structural alerts (BRENK filter). https:\u002F\u002Fdoi.org\u002F10.1002\u002Fcmdc.200700139\n- Walters & Murcko, *Adv. Drug Deliv. Rev.* 54:255-271 (2002) -- drug-likeness filtering, including REOS. https:\u002F\u002Fdoi.org\u002F10.1016\u002FS0169-409X(02)00003-0\n- Bruns & Watson, *J. Med. Chem.* 55:9763-9772 (2012) -- Eli Lilly medchem rules. https:\u002F\u002Fdoi.org\u002F10.1021\u002Fjm301008n\n- Daylight Chemical Information Systems, SMARTS theory documentation -- complete grammar reference. https:\u002F\u002Fwww.daylight.com\u002Fdayhtml\u002Fdoc\u002Ftheory\u002Ftheory.smarts.html\n\n## Related Skills\n\n- chemoinformatics\u002Fmolecular-io - Parse molecules before searching\n- chemoinformatics\u002Fmolecular-standardization - Canonicalize tautomers before SMARTS\n- chemoinformatics\u002Fsimilarity-searching - Fingerprint-based fuzzy matching\n- chemoinformatics\u002Fscaffold-analysis - Scaffold-based pattern derivation\n- chemoinformatics\u002Freaction-enumeration - SMARTS for chemical transformations\n- chemoinformatics\u002Fadmet-prediction - PAINS as ADMET filter\n- chemoinformatics\u002Fcovalent-design - Warhead chemistry\n",{"name":5,"source":24,"license":15,"tool_type":25,"description":7,"imported_at":26,"source_path":27,"primary_tool":28,"source_repository":29},"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills","python","2026-09-20","chemoinformatics\u002Fsubstructure-search\u002FSKILL.md","RDKit","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-substructure-search","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-substructure-search",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-substructure-search",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-substructure-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-substructure-search\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002Fsubstructure_search.py","SCRIPT","脚本",4245,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-substructure-search\u002Fexamples\u002Fsubstructure_search.py",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"usage-guide.md","REFERENCE","参考文档",1938,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-substructure-search\u002Fusage-guide.md",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":70},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":70},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":70},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":70},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":70},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]