[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EF451HSKJX026E3P66DMVD":3,"skill-same:01M7EF451HSKJX026E3P66DMVD":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},"01M7EF451HSKJX026E3P66DMVD","bio-reaction-enumeration",null,"Enumerates virtual chemical libraries via reaction SMARTS transformations using RDKit and reaction templates, with explicit handling of atom mapping, RDChiral template extraction, product validation, RECAP\u002FBRICS fragmentation, R-group decomposition, matched molecular pair analysis (MMPA), and Free-Wilson analysis. Use when generating combinatorial libraries from building blocks, enumerating analog series, deriving structure-activity rules, or extracting transformations from reaction data.","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-reaction-enumeration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-reaction-enumeration\ndescription: Enumerates virtual chemical libraries via reaction SMARTS transformations using RDKit and reaction templates, with explicit handling of atom mapping, RDChiral template extraction, product validation, RECAP\u002FBRICS fragmentation, R-group decomposition, matched molecular pair analysis (MMPA), and Free-Wilson analysis. Use when generating combinatorial libraries from building blocks, enumerating analog series, deriving structure-activity rules, or extracting transformations from reaction data.\ntool_type: python\nprimary_tool: RDKit\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"chemoinformatics\u002Freaction-enumeration\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: RDKit 2024.09+, RDChiral 1.1+, mmpdb 3.1+, scikit-learn 1.4+, numpy 1.26+.\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n\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# Reaction Enumeration\n\nGenerate virtual libraries by applying reaction SMARTS to building blocks, enumerate analog series via matched molecular pairs, decompose into R-groups for SAR modeling, or extract transformations from reaction data. Reaction enumeration sits at the intersection of medicinal chemistry, lead optimization, and de novo design; DOGS is one published example of reaction-driven de novo design (Hartenfeller et al. 2012). The two key operations are **transform** (apply known reactions to make new compounds) and **mine** (extract rules from observed analog series). RDKit's reaction SMARTS handles the former; mmpdb \u002F Free-Wilson handle analog-series analysis, while mapped-reaction template extraction requires separate tooling such as RDChiral.\n\nFor retrosynthetic planning (target-to-starting-material decomposition), see `chemoinformatics\u002Fretrosynthesis`. For ML-driven design, see `chemoinformatics\u002Fgenerative-design`. For scaffold-based design, see `chemoinformatics\u002Fscaffold-analysis`.\n\n## Operation Taxonomy\n\n| Operation | Goal | Tool | Fails when |\n|-----------|------|------|------------|\n| Forward enumeration | Apply reaction to building blocks -> products | RDKit `ReactionFromSmarts` + `RunReactants` | Wrong atom mapping; missing connectivity |\n| Reverse enumeration (retrosynthesis) | Product -> starting materials | AiZynthFinder, Chemformer | See retrosynthesis skill |\n| Template mining | Reaction database -> reaction SMARTS templates | RXNMapper + RDChiral | Atom mapping ambiguous; mechanism unclear |\n| RECAP fragmentation | Molecule -> retro-synthetic fragments | RDKit `Chem.Recap` | Inflexible bond rules |\n| BRICS fragmentation | Molecule -> retro-synthetic fragments | RDKit `BRICS` module | Many false fragments |\n| R-group decomposition | Set of mols + scaffold -> R-group table | RDKit `Chem.rdRGroupDecomposition` | Multiple scaffolds; ambiguous attachment |\n| Matched Molecular Pairs (MMPA) | Set of mols -> transformation rules | mmpdb | Sparse or context-confounded matched pairs |\n| Free-Wilson | Compounds + activities -> additive R-group contributions | scikit-learn linear regression | Strict additivity assumption |\n\n## Reaction SMARTS Basics\n\nA reaction SMARTS is `reactants >> products` with atom maps `[atom:idx]` tracking atoms through the transformation:\n\n```python\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem\n\namide = AllChem.ReactionFromSmarts(\n    '[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]'\n)\n\nerrors = amide.Validate()\nprint(errors)\n```\n\n**Atom mapping rules:**\n- Atoms with the same map index `[C:1]` in both reactant and product are tracked\n- Maps must be unique within each reactant\u002Fproduct\n- Atoms present in a reactant template but absent from the product template are removed; atoms present only in the product template are created\n- Atoms outside the matched reaction-center template are generally carried through with their reactant molecule\n- Bond orders may change; map index preserves identity\n\n**Common error:** Missing or inconsistent maps for atoms intended to survive within the reaction center can delete atoms, create duplicates, or obscure which reactant atom a product atom represents. Mapping alone does not define the transformation; the reactant and product templates do.\n\n## Common Reaction Templates\n\n```python\nREACTIONS = {\n    'amide_coupling': '[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]',\n    'reductive_amination': '[C:1](=O).[NH2:2]>>[CH:1][NH:2]',\n    'suzuki': '[c:1][Br].[c:2][B](O)O>>[c:1][c:2]',\n    'buchwald_hartwig': '[c:1][Br].[NH:2]>>[c:1][N:2]',\n    'sn2_substitution': '[CH:1][Br].[N:2]>>[CH:1][N:2]',\n    'sonogashira': '[c:1][Br].[CH:2]#[C:3]>>[c:1][C:2]#[C:3]',\n    'click_chemistry': '[N-:1]=[N+:2]=[N:3][CH2:4].[CH:5]#[C:6]>>[N:3]1[N:2]=[N:1][C:6]=[C:5]1[CH2:4]',\n    'esterification': '[C:1](=[O:2])O.[OH:3][C:4]>>[C:1](=[O:2])[O:3][C:4]',\n    'urea_formation': '[N:1]=C=O.[NH:2]>>[N:1]C(=O)[N:2]',\n    'sulfonamide': '[S:1](=O)(=O)Cl.[NH:2]>>[S:1](=O)(=O)[N:2]',\n}\n```\n\nThese are illustrative templates; real reactions need stereo, protecting-group, and chemoselectivity considerations. For production library enumeration, use a separately curated and validated template collection, such as a vendor catalog. RXNMapper maps atoms in reaction records; it does not by itself supply or validate reaction templates.\n\n## Combinatorial Library Enumeration\n\n**Goal:** Generate every (R1, R2, ..., Rn) product combination from sets of building blocks.\n\n**Approach:** Cartesian product of reactant lists; apply reaction SMARTS; sanitize + deduplicate.\n\n```python\nfrom itertools import product\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem, Descriptors\n\ndef enumerate_library(rxn_smarts, reactant_lists, mw_max=600):\n    rxn = AllChem.ReactionFromSmarts(rxn_smarts)\n    num_warnings, num_errors = rxn.Validate()\n    if num_errors:\n        raise ValueError(f'Invalid reaction: {rxn_smarts}')\n\n    seen = set()\n    products = []\n    for combo in product(*reactant_lists):\n        mols = [Chem.MolFromSmiles(s) for s in combo]\n        if None in mols:\n            continue\n\n        for prod_tuple in rxn.RunReactants(tuple(mols)):\n            for prod in prod_tuple:\n                try:\n                    Chem.SanitizeMol(prod)\n                    smi = Chem.MolToSmiles(prod)\n                    if smi in seen:\n                        continue\n                    if Descriptors.MolWt(prod) > mw_max:\n                        continue\n                    seen.add(smi)\n                    products.append(smi)\n                except Exception:\n                    continue\n    return products\n```\n\n**Scaling:** For a 100x100x100 enumeration (1M products), parallelize with multiprocessing. For 1k x 1k x 1k (1B products), use a streaming approach + filter before materializing.\n\n## RECAP Fragmentation\n\nRECAP (Lewell 1998) breaks molecules at retrosynthetically reasonable bonds into reusable fragments.\n\n```python\nfrom rdkit.Chem import Recap\n\nmol = Chem.MolFromSmiles('c1ccc(C(=O)Nc2ccc(F)cc2)cc1')\nhier = Recap.RecapDecompose(mol)\nfragments = list(hier.GetLeaves().keys())\n```\n\nRDKit's current `Recap.reactionDefs` contains 12 cleavage definitions. Inspect the installed definitions when exact coverage matters instead of relying on a shortened functional-group list. Use cases include building-block library generation and scaffold-decoration enumeration.\n\n## BRICS Fragmentation\n\nBRICS (Degen 2008) is an extension of RECAP with more bond types. Better fragment coverage; more fragments per molecule.\n\n```python\nfrom itertools import islice\nfrom rdkit.Chem import BRICS\n\nmol = Chem.MolFromSmiles('CCN(CC)c1ccc(C(=O)NC2CCCC2)cc1')\nfragments = BRICS.BRICSDecompose(mol)\n\nbuilder = BRICS.BRICSBuild([Chem.MolFromSmiles(f) for f in fragments])\nnew_mols = list(islice(builder, 10))\n```\n\n`BRICSDecompose` produces SMILES with isotope\u002Fenvironment-labeled dummy atoms such as `[1*]`, `[5*]`, and `[16*]`; `BRICSBuild` uses those labels when recombining compatible fragments.\n\n## R-Group Decomposition\n\n**Goal:** Given a set of compounds sharing a scaffold, extract the R-group at each attachment point into a tabular SAR matrix.\n\n**Approach:** Define scaffold with `[*:1]`, `[*:2]` placeholders; RDKit matches each compound and extracts R-groups.\n\n```python\nfrom rdkit.Chem import rdRGroupDecomposition as rgd\nfrom rdkit import Chem\n\nscaffold = Chem.MolFromSmiles('c1ccc(-[*:1])cc1-[*:2]')\n\nmols = [Chem.MolFromSmiles(smi) for smi in [\n    'c1ccc(C)cc1F',\n    'c1ccc(CC)cc1Cl',\n    'c1ccc(CCC)cc1Br',\n]]\n\ndecomp, _ = rgd.RGroupDecompose([scaffold], mols, asSmiles=True)\n```\n\n`decomp` is a list of dicts such as `{'Core': scaffold_smi, 'R1': r1_smi, 'R2': r2_smi}`. It does not contain assay values. Preserve compound identifiers and explicitly join the decomposition to the activity table before Free-Wilson analysis:\n\n```python\nimport pandas as pd\n\ncompound_ids = ['cmpd-1', 'cmpd-2', 'cmpd-3']\nactivities = pd.DataFrame({\n    'compound_id': compound_ids,\n    'pIC50': [6.2, 6.8, 7.1],  # example measurements\n})\ndecomp, unmatched = rgd.RGroupDecompose([scaffold], mols, asSmiles=True)\nunmatched = set(unmatched)\nmatched_ids = [cid for i, cid in enumerate(compound_ids) if i not in unmatched]\ndecomp_df = pd.DataFrame(decomp)\ndecomp_df.insert(0, 'compound_id', matched_ids)\nsar_table = decomp_df.merge(\n    activities, on='compound_id', how='inner', validate='one_to_one'\n)\n```\n\n## Matched Molecular Pairs Analysis (MMPA)\n\nMMPA (Hussain & Rea 2010) extracts SAR rules from compound pairs differing by a single transformation.\n\n```bash\nmmpdb fragment data.smi -o data.fragments\nmmpdb index data.fragments -o data.mmpdb\nmmpdb transform --smiles 'COc1ccccc1' data.mmpdb\n```\n\n`mmpdb` produces a database of transformations + statistics on activity changes. The values below are synthetic examples showing the output schema; they are not observations from a cited dataset.\n\n| Transformation | Avg delta(pIC50) | N pairs | Confidence |\n|----------------|-------------------|---------|------------|\n| Me -> F | +0.5 | 152 | high |\n| OMe -> OH | -0.3 | 89 | moderate |\n| Ph -> 4-pyridine | +1.2 | 23 | moderate |\n\n**Use case:** Lead optimization. Given a hit, ask \"what transformations have improved similar series?\" Apply top-ranked transformations to generate analog suggestions.\n\n**Context-based MMPA** conditions transformation statistics on local chemical context (for example, \"Me -> F adjacent to an amide\"). Raut and Dixit (2025) applied this approach to identify transformations associated with reduced CYP1A2 inhibition; that endpoint-specific result should not be generalized as universal superiority over classical MMPA.\n\n## Free-Wilson Analysis\n\n**Goal:** Decompose activity into additive R-group contributions.\n\n**Approach:** Linear regression with R-group identity as binary features.\n\n```python\nimport pandas as pd\nfrom sklearn.linear_model import Ridge\n\ndef free_wilson(decomp_results, activity_col='pIC50'):\n    df = pd.DataFrame(decomp_results)\n    r_groups = pd.get_dummies(df[['R1', 'R2']], prefix=['R1', 'R2'])\n    X = r_groups.values\n    y = df[activity_col].values\n    model = Ridge(alpha=0.1).fit(X, y)\n    contributions = dict(zip(r_groups.columns, model.coef_))\n    return contributions, model.intercept_\n```\n\n**Trade-off:** Free-Wilson assumes additivity (R1 contribution independent of R2). Real SAR has interactions; Free-Wilson predictions for un-synthesized combinations are biased when synergy exists. Use as a *first-pass model* for analog prioritization; validate with QSAR.\n\n## Template Extraction from Reaction Data\n\n**Goal:** Given an atom-mapped reaction SMILES, extract a generalizable SMARTS template.\n\n**Approach:** Use `rxnmapper` (Schwaller et al. 2021) for atom mapping, then a template extractor such as RDChiral (Coley et al. 2019).\n\n```python\nfrom rxnmapper import RXNMapper\n\nmapper = RXNMapper()\nrxns = ['CCO.OC(=O)c1ccccc1>>CCOC(=O)c1ccccc1']\nresults = mapper.get_attention_guided_atom_maps(rxns)\nmapped_smiles = results[0]['mapped_rxn']\n```\n\nRDKit does not provide a `ChemicalReaction.GetReactionTemplateFromMappedReaction` method. Pass the mapped reaction to RDChiral's published template-extraction workflow, checking the installed package's interface and expected reaction-record schema, or use a separately implemented and validated extractor.\n\n## Per-Tool Failure Modes\n\n### Reaction SMARTS -- atom mapping mismatch\n\n**Trigger:** An atom intended to survive the reaction center is absent from, or inconsistently mapped in, the product template.\n\n**Mechanism:** RDKit constructs products from the reaction templates. Reactant-template atoms omitted from the product template are deleted, product-only atoms are created, and inconsistent maps can prevent intended atom identity from being carried across the transformation.\n\n**Symptom:** Products missing expected atoms; valences wrong; sanitize fails.\n\n**Fix:** Validate with `rxn.Validate()`, inspect warnings separately from errors, and manually verify that every reaction-center atom intended to survive has one consistent map number on both sides.\n\n### RECAP\u002FBRICS -- over-fragmentation\n\n**Trigger:** Highly substituted molecule with many breakable bonds.\n\n**Mechanism:** Default bond list breaks at every retrosynthetic position; one molecule yields tens of fragments.\n\n**Symptom:** Building-block enumeration explodes; many small irrelevant fragments.\n\n**Fix:** Filter fragments by MW (>=80 Da), heavy atom count (>=4); use only meaningful fragments downstream.\n\n### MMPA -- insufficient pair count\n\n**Trigger:** The dataset yields few matched pairs for a transformation in the relevant chemical context.\n\n**Mechanism:** Sparse or heterogeneous pairs give imprecise, context-confounded estimates. There is no universal minimum dataset size or pair count that guarantees a meaningful effect.\n\n**Symptom:** Transformations report with N=1-3 pairs; effect sizes erratic.\n\n**Fix:** Report pair counts and uncertainty, examine local contexts, use a project-justified precision threshold, and supplement with experimental or literature SAR knowledge.\n\n### Free-Wilson -- non-additive interactions\n\n**Trigger:** R1 and R2 interact through hydrogen bonding, steric clash, or electronic effects.\n\n**Mechanism:** Free-Wilson is purely additive; cannot capture R1+R2 synergy.\n\n**Symptom:** Predicted activities for un-synthesized combinations are biased low for synergistic pairs.\n\n**Fix:** Use Free-Wilson as first-pass screen; validate predictions with QSAR (random forest, chemprop) which captures interactions.\n\n### R-group decomposition -- multiple scaffolds\n\n**Trigger:** Compound matches multiple scaffold templates.\n\n**Mechanism:** RDKit accepts cores ordered from most to least specific and exposes parameters for multi-core matching and alignment. Ambiguous or inconsistently specified cores can change the resulting labels and SAR table.\n\n**Symptom:** Same compound's R-groups differ between runs.\n\n**Fix:** Order cores from most to least specific, label attachment points explicitly, inspect unmatched compounds, and keep a compound only when its selected core assignment matches the intended SAR series.\n\n### Reaction enumeration -- combinatorial explosion\n\n**Trigger:** Large building-block sets (1k x 1k = 1M products).\n\n**Mechanism:** Cartesian product * RunReactants is O(N^d) where d is reactant count.\n\n**Symptom:** Memory blowup, multi-hour runtime.\n\n**Fix:** Pre-filter building blocks; stream products to file rather than list; use mmpdb-style sparse enumeration only for valid pairings.\n\n## Reconciliation: Free-Wilson vs MMPA\n\nBoth methods derive R-group rules but from different perspectives:\n- Free-Wilson: linear regression on assembled SAR table; gives R-group contributions\n- MMPA: transformation-based; gives delta(activity) for each substitution\n\nIf they agree on direction (Me->F improves activity), high confidence. If they disagree, investigate non-additive interactions or look for context dependence in MMPA.\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `rxn.Validate()` reports a nonzero error count | Bad atom mapping or invalid SMARTS | Unpack `(num_warnings, num_errors)` and reject on `num_errors`; inspect warnings separately |\n| Products contain unexpected fragments | Reactants matched in unintended way | Use more specific SMARTS; constrain with explicit ring members |\n| Sanitize fails on products | Reaction breaks valence | Filter via `Chem.SanitizeMol(prod, catchErrors=True)` |\n| Duplicate products | Same product from different reactant orientations | Deduplicate by canonical SMILES |\n| RECAP produces single fragment | Molecule has no retrosynthetic bonds | Try BRICS for more aggressive fragmentation |\n| mmpdb empty output | No pairs satisfy the fragmentation, property, and context criteria | Inspect input parsing and fragmentation output; relax justified filters or obtain relevant analogues |\n| R-group decomposition wrong R | Scaffold dummy not aligned | Re-check `[*:1]` \u002F `[*:2]` placement |\n\n## References\n\n- Hartenfeller M et al. \"DOGS: Reaction-Driven de novo Design of Bioactive Compounds.\" *PLoS Comput. Biol.* 8:e1002380 (2012). DOI: 10.1371\u002Fjournal.pcbi.1002380.\n- Lewell XQ, Judd DB, Watson SP, Hann MM. \"RECAP—Retrosynthetic Combinatorial Analysis Procedure.\" *J. Chem. Inf. Comput. Sci.* 38:511–522 (1998). DOI: 10.1021\u002Fci970429i.\n- Degen J, Wegscheid-Gerlach C, Zaliani A, Rarey M. \"On the Art of Compiling and Using 'Drug-Like' Chemical Fragment Spaces.\" *ChemMedChem* 3:1503–1507 (2008). DOI: 10.1002\u002Fcmdc.200800178.\n- Hussain J, Rea C. \"Computationally Efficient Algorithm to Identify Matched Molecular Pairs (MMPs) in Large Data Sets.\" *J. Chem. Inf. Model.* 50:339–348 (2010). DOI: 10.1021\u002Fci900450m.\n- Dossetter AG, Griffen EJ, Leach AG. \"Matched molecular pair analysis in drug discovery.\" *Drug Discov. Today* 18:724–731 (2013). DOI: 10.1016\u002Fj.drudis.2013.03.003.\n- Free SM, Wilson JW. \"A Mathematical Contribution to Structure-Activity Studies.\" *J. Med. Chem.* 7:395–399 (1964). DOI: 10.1021\u002Fjm00334a001.\n- Schwaller P et al. \"Unsupervised attention-guided atom-mapping.\" *Sci. Adv.* 7:eabe4166 (2021). DOI: 10.1126\u002Fsciadv.abe4166.\n- Raut JA, Dixit VA. \"A context-based matched molecular pair analysis identifies structural transformations that reduce CYP1A2 inhibition.\" *RSC Med. Chem.* 16:3281–3290 (2025). DOI: 10.1039\u002FD4MD01012D.\n- Coley CW, Green WH, Jensen KF. \"RDChiral: An RDKit Wrapper for Handling Stereochemistry in Retrosynthetic Template Extraction and Application.\" *J. Chem. Inf. Model.* 59:2529–2537 (2019). DOI: 10.1021\u002Facs.jcim.9b00286.\n- Dalke A, Hert J, Kramer C. \"mmpdb: An Open-Source Matched Molecular Pair Platform for Large Multiproperty Data Sets.\" *J. Chem. Inf. Model.* 58:902–910 (2018). DOI: 10.1021\u002Facs.jcim.8b00173.\n- RDKit Book, reaction SMARTS and reaction handling: https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002FRDKit_Book.html.\n- RDKit R-group decomposition API: https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002Fsource\u002Frdkit.Chem.rdRGroupDecomposition.html.\n\n## Related Skills\n\n- chemoinformatics\u002Fmolecular-io - Read\u002Fwrite reaction SMILES\n- chemoinformatics\u002Fsubstructure-search - SMARTS pattern matching\n- chemoinformatics\u002Fscaffold-analysis - Bemis-Murcko scaffolds for R-decomp\n- chemoinformatics\u002Fmolecular-descriptors - Featurize products\n- chemoinformatics\u002Fadmet-prediction - Filter enumerated products\n- chemoinformatics\u002Fretrosynthesis - Reverse direction (target -> starting materials)\n- chemoinformatics\u002Fgenerative-design - Generative alternatives to template enumeration\n- chemoinformatics\u002Fqsar-modeling - Validate Free-Wilson predictions\n","## Version Compatibility\n\nReference examples tested with: RDKit 2024.09+, RDChiral 1.1+, mmpdb 3.1+, scikit-learn 1.4+, numpy 1.26+.\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n\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# Reaction Enumeration\n\nGenerate virtual libraries by applying reaction SMARTS to building blocks, enumerate analog series via matched molecular pairs, decompose into R-groups for SAR modeling, or extract transformations from reaction data. Reaction enumeration sits at the intersection of medicinal chemistry, lead optimization, and de novo design; DOGS is one published example of reaction-driven de novo design (Hartenfeller et al. 2012). The two key operations are **transform** (apply known reactions to make new compounds) and **mine** (extract rules from observed analog series). RDKit's reaction SMARTS handles the former; mmpdb \u002F Free-Wilson handle analog-series analysis, while mapped-reaction template extraction requires separate tooling such as RDChiral.\n\nFor retrosynthetic planning (target-to-starting-material decomposition), see `chemoinformatics\u002Fretrosynthesis`. For ML-driven design, see `chemoinformatics\u002Fgenerative-design`. For scaffold-based design, see `chemoinformatics\u002Fscaffold-analysis`.\n\n## Operation Taxonomy\n\n| Operation | Goal | Tool | Fails when |\n|-----------|------|------|------------|\n| Forward enumeration | Apply reaction to building blocks -> products | RDKit `ReactionFromSmarts` + `RunReactants` | Wrong atom mapping; missing connectivity |\n| Reverse enumeration (retrosynthesis) | Product -> starting materials | AiZynthFinder, Chemformer | See retrosynthesis skill |\n| Template mining | Reaction database -> reaction SMARTS templates | RXNMapper + RDChiral | Atom mapping ambiguous; mechanism unclear |\n| RECAP fragmentation | Molecule -> retro-synthetic fragments | RDKit `Chem.Recap` | Inflexible bond rules |\n| BRICS fragmentation | Molecule -> retro-synthetic fragments | RDKit `BRICS` module | Many false fragments |\n| R-group decomposition | Set of mols + scaffold -> R-group table | RDKit `Chem.rdRGroupDecomposition` | Multiple scaffolds; ambiguous attachment |\n| Matched Molecular Pairs (MMPA) | Set of mols -> transformation rules | mmpdb | Sparse or context-confounded matched pairs |\n| Free-Wilson | Compounds + activities -> additive R-group contributions | scikit-learn linear regression | Strict additivity assumption |\n\n## Reaction SMARTS Basics\n\nA reaction SMARTS is `reactants >> products` with atom maps `[atom:idx]` tracking atoms through the transformation:\n\n```python\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem\n\namide = AllChem.ReactionFromSmarts(\n    '[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]'\n)\n\nerrors = amide.Validate()\nprint(errors)\n```\n\n**Atom mapping rules:**\n- Atoms with the same map index `[C:1]` in both reactant and product are tracked\n- Maps must be unique within each reactant\u002Fproduct\n- Atoms present in a reactant template but absent from the product template are removed; atoms present only in the product template are created\n- Atoms outside the matched reaction-center template are generally carried through with their reactant molecule\n- Bond orders may change; map index preserves identity\n\n**Common error:** Missing or inconsistent maps for atoms intended to survive within the reaction center can delete atoms, create duplicates, or obscure which reactant atom a product atom represents. Mapping alone does not define the transformation; the reactant and product templates do.\n\n## Common Reaction Templates\n\n```python\nREACTIONS = {\n    'amide_coupling': '[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]',\n    'reductive_amination': '[C:1](=O).[NH2:2]>>[CH:1][NH:2]',\n    'suzuki': '[c:1][Br].[c:2][B](O)O>>[c:1][c:2]',\n    'buchwald_hartwig': '[c:1][Br].[NH:2]>>[c:1][N:2]',\n    'sn2_substitution': '[CH:1][Br].[N:2]>>[CH:1][N:2]',\n    'sonogashira': '[c:1][Br].[CH:2]#[C:3]>>[c:1][C:2]#[C:3]',\n    'click_chemistry': '[N-:1]=[N+:2]=[N:3][CH2:4].[CH:5]#[C:6]>>[N:3]1[N:2]=[N:1][C:6]=[C:5]1[CH2:4]',\n    'esterification': '[C:1](=[O:2])O.[OH:3][C:4]>>[C:1](=[O:2])[O:3][C:4]',\n    'urea_formation': '[N:1]=C=O.[NH:2]>>[N:1]C(=O)[N:2]',\n    'sulfonamide': '[S:1](=O)(=O)Cl.[NH:2]>>[S:1](=O)(=O)[N:2]',\n}\n```\n\nThese are illustrative templates; real reactions need stereo, protecting-group, and chemoselectivity considerations. For production library enumeration, use a separately curated and validated template collection, such as a vendor catalog. RXNMapper maps atoms in reaction records; it does not by itself supply or validate reaction templates.\n\n## Combinatorial Library Enumeration\n\n**Goal:** Generate every (R1, R2, ..., Rn) product combination from sets of building blocks.\n\n**Approach:** Cartesian product of reactant lists; apply reaction SMARTS; sanitize + deduplicate.\n\n```python\nfrom itertools import product\nfrom rdkit import Chem\nfrom rdkit.Chem import AllChem, Descriptors\n\ndef enumerate_library(rxn_smarts, reactant_lists, mw_max=600):\n    rxn = AllChem.ReactionFromSmarts(rxn_smarts)\n    num_warnings, num_errors = rxn.Validate()\n    if num_errors:\n        raise ValueError(f'Invalid reaction: {rxn_smarts}')\n\n    seen = set()\n    products = []\n    for combo in product(*reactant_lists):\n        mols = [Chem.MolFromSmiles(s) for s in combo]\n        if None in mols:\n            continue\n\n        for prod_tuple in rxn.RunReactants(tuple(mols)):\n            for prod in prod_tuple:\n                try:\n                    Chem.SanitizeMol(prod)\n                    smi = Chem.MolToSmiles(prod)\n                    if smi in seen:\n                        continue\n                    if Descriptors.MolWt(prod) > mw_max:\n                        continue\n                    seen.add(smi)\n                    products.append(smi)\n                except Exception:\n                    continue\n    return products\n```\n\n**Scaling:** For a 100x100x100 enumeration (1M products), parallelize with multiprocessing. For 1k x 1k x 1k (1B products), use a streaming approach + filter before materializing.\n\n## RECAP Fragmentation\n\nRECAP (Lewell 1998) breaks molecules at retrosynthetically reasonable bonds into reusable fragments.\n\n```python\nfrom rdkit.Chem import Recap\n\nmol = Chem.MolFromSmiles('c1ccc(C(=O)Nc2ccc(F)cc2)cc1')\nhier = Recap.RecapDecompose(mol)\nfragments = list(hier.GetLeaves().keys())\n```\n\nRDKit's current `Recap.reactionDefs` contains 12 cleavage definitions. Inspect the installed definitions when exact coverage matters instead of relying on a shortened functional-group list. Use cases include building-block library generation and scaffold-decoration enumeration.\n\n## BRICS Fragmentation\n\nBRICS (Degen 2008) is an extension of RECAP with more bond types. Better fragment coverage; more fragments per molecule.\n\n```python\nfrom itertools import islice\nfrom rdkit.Chem import BRICS\n\nmol = Chem.MolFromSmiles('CCN(CC)c1ccc(C(=O)NC2CCCC2)cc1')\nfragments = BRICS.BRICSDecompose(mol)\n\nbuilder = BRICS.BRICSBuild([Chem.MolFromSmiles(f) for f in fragments])\nnew_mols = list(islice(builder, 10))\n```\n\n`BRICSDecompose` produces SMILES with isotope\u002Fenvironment-labeled dummy atoms such as `[1*]`, `[5*]`, and `[16*]`; `BRICSBuild` uses those labels when recombining compatible fragments.\n\n## R-Group Decomposition\n\n**Goal:** Given a set of compounds sharing a scaffold, extract the R-group at each attachment point into a tabular SAR matrix.\n\n**Approach:** Define scaffold with `[*:1]`, `[*:2]` placeholders; RDKit matches each compound and extracts R-groups.\n\n```python\nfrom rdkit.Chem import rdRGroupDecomposition as rgd\nfrom rdkit import Chem\n\nscaffold = Chem.MolFromSmiles('c1ccc(-[*:1])cc1-[*:2]')\n\nmols = [Chem.MolFromSmiles(smi) for smi in [\n    'c1ccc(C)cc1F',\n    'c1ccc(CC)cc1Cl',\n    'c1ccc(CCC)cc1Br',\n]]\n\ndecomp, _ = rgd.RGroupDecompose([scaffold], mols, asSmiles=True)\n```\n\n`decomp` is a list of dicts such as `{'Core': scaffold_smi, 'R1': r1_smi, 'R2': r2_smi}`. It does not contain assay values. Preserve compound identifiers and explicitly join the decomposition to the activity table before Free-Wilson analysis:\n\n```python\nimport pandas as pd\n\ncompound_ids = ['cmpd-1', 'cmpd-2', 'cmpd-3']\nactivities = pd.DataFrame({\n    'compound_id': compound_ids,\n    'pIC50': [6.2, 6.8, 7.1],  # example measurements\n})\ndecomp, unmatched = rgd.RGroupDecompose([scaffold], mols, asSmiles=True)\nunmatched = set(unmatched)\nmatched_ids = [cid for i, cid in enumerate(compound_ids) if i not in unmatched]\ndecomp_df = pd.DataFrame(decomp)\ndecomp_df.insert(0, 'compound_id', matched_ids)\nsar_table = decomp_df.merge(\n    activities, on='compound_id', how='inner', validate='one_to_one'\n)\n```\n\n## Matched Molecular Pairs Analysis (MMPA)\n\nMMPA (Hussain & Rea 2010) extracts SAR rules from compound pairs differing by a single transformation.\n\n```bash\nmmpdb fragment data.smi -o data.fragments\nmmpdb index data.fragments -o data.mmpdb\nmmpdb transform --smiles 'COc1ccccc1' data.mmpdb\n```\n\n`mmpdb` produces a database of transformations + statistics on activity changes. The values below are synthetic examples showing the output schema; they are not observations from a cited dataset.\n\n| Transformation | Avg delta(pIC50) | N pairs | Confidence |\n|----------------|-------------------|---------|------------|\n| Me -> F | +0.5 | 152 | high |\n| OMe -> OH | -0.3 | 89 | moderate |\n| Ph -> 4-pyridine | +1.2 | 23 | moderate |\n\n**Use case:** Lead optimization. Given a hit, ask \"what transformations have improved similar series?\" Apply top-ranked transformations to generate analog suggestions.\n\n**Context-based MMPA** conditions transformation statistics on local chemical context (for example, \"Me -> F adjacent to an amide\"). Raut and Dixit (2025) applied this approach to identify transformations associated with reduced CYP1A2 inhibition; that endpoint-specific result should not be generalized as universal superiority over classical MMPA.\n\n## Free-Wilson Analysis\n\n**Goal:** Decompose activity into additive R-group contributions.\n\n**Approach:** Linear regression with R-group identity as binary features.\n\n```python\nimport pandas as pd\nfrom sklearn.linear_model import Ridge\n\ndef free_wilson(decomp_results, activity_col='pIC50'):\n    df = pd.DataFrame(decomp_results)\n    r_groups = pd.get_dummies(df[['R1', 'R2']], prefix=['R1', 'R2'])\n    X = r_groups.values\n    y = df[activity_col].values\n    model = Ridge(alpha=0.1).fit(X, y)\n    contributions = dict(zip(r_groups.columns, model.coef_))\n    return contributions, model.intercept_\n```\n\n**Trade-off:** Free-Wilson assumes additivity (R1 contribution independent of R2). Real SAR has interactions; Free-Wilson predictions for un-synthesized combinations are biased when synergy exists. Use as a *first-pass model* for analog prioritization; validate with QSAR.\n\n## Template Extraction from Reaction Data\n\n**Goal:** Given an atom-mapped reaction SMILES, extract a generalizable SMARTS template.\n\n**Approach:** Use `rxnmapper` (Schwaller et al. 2021) for atom mapping, then a template extractor such as RDChiral (Coley et al. 2019).\n\n```python\nfrom rxnmapper import RXNMapper\n\nmapper = RXNMapper()\nrxns = ['CCO.OC(=O)c1ccccc1>>CCOC(=O)c1ccccc1']\nresults = mapper.get_attention_guided_atom_maps(rxns)\nmapped_smiles = results[0]['mapped_rxn']\n```\n\nRDKit does not provide a `ChemicalReaction.GetReactionTemplateFromMappedReaction` method. Pass the mapped reaction to RDChiral's published template-extraction workflow, checking the installed package's interface and expected reaction-record schema, or use a separately implemented and validated extractor.\n\n## Per-Tool Failure Modes\n\n### Reaction SMARTS -- atom mapping mismatch\n\n**Trigger:** An atom intended to survive the reaction center is absent from, or inconsistently mapped in, the product template.\n\n**Mechanism:** RDKit constructs products from the reaction templates. Reactant-template atoms omitted from the product template are deleted, product-only atoms are created, and inconsistent maps can prevent intended atom identity from being carried across the transformation.\n\n**Symptom:** Products missing expected atoms; valences wrong; sanitize fails.\n\n**Fix:** Validate with `rxn.Validate()`, inspect warnings separately from errors, and manually verify that every reaction-center atom intended to survive has one consistent map number on both sides.\n\n### RECAP\u002FBRICS -- over-fragmentation\n\n**Trigger:** Highly substituted molecule with many breakable bonds.\n\n**Mechanism:** Default bond list breaks at every retrosynthetic position; one molecule yields tens of fragments.\n\n**Symptom:** Building-block enumeration explodes; many small irrelevant fragments.\n\n**Fix:** Filter fragments by MW (>=80 Da), heavy atom count (>=4); use only meaningful fragments downstream.\n\n### MMPA -- insufficient pair count\n\n**Trigger:** The dataset yields few matched pairs for a transformation in the relevant chemical context.\n\n**Mechanism:** Sparse or heterogeneous pairs give imprecise, context-confounded estimates. There is no universal minimum dataset size or pair count that guarantees a meaningful effect.\n\n**Symptom:** Transformations report with N=1-3 pairs; effect sizes erratic.\n\n**Fix:** Report pair counts and uncertainty, examine local contexts, use a project-justified precision threshold, and supplement with experimental or literature SAR knowledge.\n\n### Free-Wilson -- non-additive interactions\n\n**Trigger:** R1 and R2 interact through hydrogen bonding, steric clash, or electronic effects.\n\n**Mechanism:** Free-Wilson is purely additive; cannot capture R1+R2 synergy.\n\n**Symptom:** Predicted activities for un-synthesized combinations are biased low for synergistic pairs.\n\n**Fix:** Use Free-Wilson as first-pass screen; validate predictions with QSAR (random forest, chemprop) which captures interactions.\n\n### R-group decomposition -- multiple scaffolds\n\n**Trigger:** Compound matches multiple scaffold templates.\n\n**Mechanism:** RDKit accepts cores ordered from most to least specific and exposes parameters for multi-core matching and alignment. Ambiguous or inconsistently specified cores can change the resulting labels and SAR table.\n\n**Symptom:** Same compound's R-groups differ between runs.\n\n**Fix:** Order cores from most to least specific, label attachment points explicitly, inspect unmatched compounds, and keep a compound only when its selected core assignment matches the intended SAR series.\n\n### Reaction enumeration -- combinatorial explosion\n\n**Trigger:** Large building-block sets (1k x 1k = 1M products).\n\n**Mechanism:** Cartesian product * RunReactants is O(N^d) where d is reactant count.\n\n**Symptom:** Memory blowup, multi-hour runtime.\n\n**Fix:** Pre-filter building blocks; stream products to file rather than list; use mmpdb-style sparse enumeration only for valid pairings.\n\n## Reconciliation: Free-Wilson vs MMPA\n\nBoth methods derive R-group rules but from different perspectives:\n- Free-Wilson: linear regression on assembled SAR table; gives R-group contributions\n- MMPA: transformation-based; gives delta(activity) for each substitution\n\nIf they agree on direction (Me->F improves activity), high confidence. If they disagree, investigate non-additive interactions or look for context dependence in MMPA.\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `rxn.Validate()` reports a nonzero error count | Bad atom mapping or invalid SMARTS | Unpack `(num_warnings, num_errors)` and reject on `num_errors`; inspect warnings separately |\n| Products contain unexpected fragments | Reactants matched in unintended way | Use more specific SMARTS; constrain with explicit ring members |\n| Sanitize fails on products | Reaction breaks valence | Filter via `Chem.SanitizeMol(prod, catchErrors=True)` |\n| Duplicate products | Same product from different reactant orientations | Deduplicate by canonical SMILES |\n| RECAP produces single fragment | Molecule has no retrosynthetic bonds | Try BRICS for more aggressive fragmentation |\n| mmpdb empty output | No pairs satisfy the fragmentation, property, and context criteria | Inspect input parsing and fragmentation output; relax justified filters or obtain relevant analogues |\n| R-group decomposition wrong R | Scaffold dummy not aligned | Re-check `[*:1]` \u002F `[*:2]` placement |\n\n## References\n\n- Hartenfeller M et al. \"DOGS: Reaction-Driven de novo Design of Bioactive Compounds.\" *PLoS Comput. Biol.* 8:e1002380 (2012). DOI: 10.1371\u002Fjournal.pcbi.1002380.\n- Lewell XQ, Judd DB, Watson SP, Hann MM. \"RECAP—Retrosynthetic Combinatorial Analysis Procedure.\" *J. Chem. Inf. Comput. Sci.* 38:511–522 (1998). DOI: 10.1021\u002Fci970429i.\n- Degen J, Wegscheid-Gerlach C, Zaliani A, Rarey M. \"On the Art of Compiling and Using 'Drug-Like' Chemical Fragment Spaces.\" *ChemMedChem* 3:1503–1507 (2008). DOI: 10.1002\u002Fcmdc.200800178.\n- Hussain J, Rea C. \"Computationally Efficient Algorithm to Identify Matched Molecular Pairs (MMPs) in Large Data Sets.\" *J. Chem. Inf. Model.* 50:339–348 (2010). DOI: 10.1021\u002Fci900450m.\n- Dossetter AG, Griffen EJ, Leach AG. \"Matched molecular pair analysis in drug discovery.\" *Drug Discov. Today* 18:724–731 (2013). DOI: 10.1016\u002Fj.drudis.2013.03.003.\n- Free SM, Wilson JW. \"A Mathematical Contribution to Structure-Activity Studies.\" *J. Med. Chem.* 7:395–399 (1964). DOI: 10.1021\u002Fjm00334a001.\n- Schwaller P et al. \"Unsupervised attention-guided atom-mapping.\" *Sci. Adv.* 7:eabe4166 (2021). DOI: 10.1126\u002Fsciadv.abe4166.\n- Raut JA, Dixit VA. \"A context-based matched molecular pair analysis identifies structural transformations that reduce CYP1A2 inhibition.\" *RSC Med. Chem.* 16:3281–3290 (2025). DOI: 10.1039\u002FD4MD01012D.\n- Coley CW, Green WH, Jensen KF. \"RDChiral: An RDKit Wrapper for Handling Stereochemistry in Retrosynthetic Template Extraction and Application.\" *J. Chem. Inf. Model.* 59:2529–2537 (2019). DOI: 10.1021\u002Facs.jcim.9b00286.\n- Dalke A, Hert J, Kramer C. \"mmpdb: An Open-Source Matched Molecular Pair Platform for Large Multiproperty Data Sets.\" *J. Chem. Inf. Model.* 58:902–910 (2018). DOI: 10.1021\u002Facs.jcim.8b00173.\n- RDKit Book, reaction SMARTS and reaction handling: https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002FRDKit_Book.html.\n- RDKit R-group decomposition API: https:\u002F\u002Fwww.rdkit.org\u002Fdocs\u002Fsource\u002Frdkit.Chem.rdRGroupDecomposition.html.\n\n## Related Skills\n\n- chemoinformatics\u002Fmolecular-io - Read\u002Fwrite reaction SMILES\n- chemoinformatics\u002Fsubstructure-search - SMARTS pattern matching\n- chemoinformatics\u002Fscaffold-analysis - Bemis-Murcko scaffolds for R-decomp\n- chemoinformatics\u002Fmolecular-descriptors - Featurize products\n- chemoinformatics\u002Fadmet-prediction - Filter enumerated products\n- chemoinformatics\u002Fretrosynthesis - Reverse direction (target -> starting materials)\n- chemoinformatics\u002Fgenerative-design - Generative alternatives to template enumeration\n- chemoinformatics\u002Fqsar-modeling - Validate Free-Wilson predictions\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\u002Freaction-enumeration\u002FSKILL.md","RDKit","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-reaction-enumeration","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-reaction-enumeration",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-reaction-enumeration",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-reaction-enumeration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-reaction-enumeration\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002Fenumerate_reactions.py","SCRIPT","脚本",6012,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-reaction-enumeration\u002Fexamples\u002Fenumerate_reactions.py",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"usage-guide.md","REFERENCE","参考文档",2200,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-reaction-enumeration\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",[],[]]