[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-cheminformatics":3,"mdc--kunk18-key":50,"related-repo-aws-labs-cheminformatics":1139,"related-org-aws-labs-cheminformatics":1231},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":45,"sourceUrl":48,"mdContent":49},"cheminformatics","calculate molecular properties with RDKit","Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include \"RDKit\", \"molecular descriptors\", \"Lipinski\", \"rule of five\", \"Veber\", \"PAINS\", \"pan-assay interference\", \"Morgan fingerprint\", \"Tanimoto\", \"fingerprint similarity\", \"matched molecular pair\", \"MMP\", \"mmpdb\", \"ADMET\", \"druglikeness\", \"SMILES\", \"cheminformatics\", \"compound filtering\", \"chemical similarity\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20,23],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"Data Analysis","data-analysis",{"name":21,"slug":22,"type":16},"Bioinformatics","bioinformatics",{"name":24,"slug":25,"type":16},"Chemistry","chemistry",4,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills","2026-07-12T08:37:28.334619",null,0,[32,33,34,35,36,37,38,39,40,41,42,43,44],"agent-skills","agentcore","ai-agents","amazon-quick-desktop","claims-processing","drug-discovery","genomics","healthcare-ai","kiro","life-sciences","medical-imaging","risk-adjustment","strands-agents",{"repoUrl":27,"stars":26,"forks":30,"topics":46,"description":47},[32,33,34,35,36,37,38,39,40,41,42,43,44],"Agent skills for healthcare and life sciences: genomics, imaging, claims, drug discovery, and more. Works with Amazon Quick, Kiro, Amazon AgentCore, AWS Strands SDK, Claude Code, Codex, and any Agent Skills-compatible platform.","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fcheminformatics","---\nname: cheminformatics\ndescription: Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include \"RDKit\", \"molecular descriptors\", \"Lipinski\", \"rule of five\", \"Veber\", \"PAINS\", \"pan-assay interference\", \"Morgan fingerprint\", \"Tanimoto\", \"fingerprint similarity\", \"matched molecular pair\", \"MMP\", \"mmpdb\", \"ADMET\", \"druglikeness\", \"SMILES\", \"cheminformatics\", \"compound filtering\", \"chemical similarity\".\nusage: Invoke when computing molecular properties, filtering compound libraries, calculating fingerprint similarity, or running matched molecular pair analysis with RDKit.\nversion: 1.0.0\nvalidated_against:\n  date: 2025-01-15\n  packages: {rdkit: \"2024.03\", mmpdb: \"3.1\"}\ntags: [skill, category:pipeline, cheminformatics, drug-discovery, rdkit, hcls]\n---\n\n# Cheminformatics (RDKit) — Pipeline Skill (Thin Scaffold)\n\n## Overview\n\nAdds fingerprint selection logic, filter cascade ordering, and version-specific gotchas for RDKit workflows. The agent already knows RDKit syntax — this skill prevents parameter mismatches and deprecated API usage.\n\n## Usage\n\n- Activate when filtering compound libraries (Lipinski\u002FVeber\u002FPAINS)\n- Activate for fingerprint similarity search or clustering\n- Activate for matched molecular pair (MMP) analysis with mmpdb\n\n## Core Concepts\n\n**Filter cascade order:** Lipinski → Veber → PAINS → similarity (cheapest first, most expensive last).\n\n**Fingerprint API:** Use `rdFingerprintGenerator` module exclusively (since RDKit 2024.03). The `AllChem.GetMorganFingerprintAsBitVect()` path is deprecated and will be removed.\n\n**SMILES validation:** Always parse with `sanitize=False` then explicit `SanitizeMol()` in try\u002Fexcept. Default `MolFromSmiles` silently returns None on partial failures.\n\n## Decision Logic\n\n### Fingerprint Selection\n\n| Goal | Fingerprint | Parameters | Tanimoto threshold |\n|------|-------------|------------|-------------------|\n| General similarity | Morgan (ECFP4) | radius=2, fpSize=2048 | ≥ 0.7 |\n| High-specificity matching | Morgan (ECFP6) | radius=3, fpSize=4096 | ≥ 0.6 |\n| Substructure screening | MACCS 166 keys | — | ≥ 0.8 |\n| Pharmacophore similarity | FCFP | radius=2, `GetMorganFeatureAtomInvGen()` | ≥ 0.6 |\n| Large-scale clustering | Morgan | radius=2, fpSize=1024 | Speed over precision |\n\n### Filter Thresholds\n\n| Filter | Rule | Threshold | Notes |\n|--------|------|-----------|-------|\n| Lipinski MW | ≤ 500 Da | Allow ≤1 violation total | Not binary pass\u002Ffail |\n| Lipinski LogP | ≤ 5 | — | — |\n| Lipinski HBD | ≤ 5 | — | — |\n| Lipinski HBA | ≤ 10 | — | — |\n| Veber TPSA | ≤ 140 Ų | Hard cutoff | — |\n| Veber RotBonds | ≤ 10 | Hard cutoff | — |\n| PAINS | A+B+C catalogs | HTS triage only | Don't apply to advanced compounds |\n\n### MMP Analysis Decision\n\n| Scenario | Tool | Key parameter |\n|----------|------|---------------|\n| SAR from compound pairs | mmpdb fragment → index → transform | `--min-pairs 3` |\n| Property prediction | mmpdb predict | Requires indexed DB with property data |\n| Core identification | `rdFMCS.FindMCS()` | `ringMatchesRingOnly=True, completeRingsOnly=True` |\n| Large libraries (>10K) | mmpdb CLI | `--max-variable-size 10` to limit fragmentation |\n\n## Critical Parameters\n\n| Parameter | Value | When to change |\n|-----------|-------|----------------|\n| Morgan radius | 2 (ECFP4) | 3 for higher specificity |\n| fpSize | 2048 | 1024 for speed; 4096 for precision |\n| includeChirality | False | True for stereo-sensitive applications |\n| Lipinski max_violations | 1 | 0 for strict; exempt biologics entirely |\n| mmpdb --min-pairs | 3 | Lower for sparse datasets |\n| mmpdb --max-variable-size | 10 | Increase for macrocycle transformations |\n| PAINS catalogs | A+B+C (all three) | Never use partial sets |\n\n## Common Mistakes\n\n- **Wrong:** `AllChem.GetMorganFingerprintAsBitVect()` → **Right:** `rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=2048).GetFingerprint(mol)` → **Why:** AllChem FP functions deprecated since RDKit 2024.03, will be removed\n\n- **Wrong:** Default `MolFromSmiles(smi)` without error handling → **Right:** `MolFromSmiles(smi, sanitize=False)` + `SanitizeMol()` in try\u002Fexcept → **Why:** Default silently returns None; explicit sanitize catches partial failures\n\n- **Wrong:** Lipinski as hard binary filter → **Right:** Allow ≤1 violation → **Why:** Many approved drugs violate one rule; binary filtering rejects valid candidates\n\n- **Wrong:** PAINS on clinical candidates → **Right:** PAINS only for HTS library triage → **Why:** Designed for screening artifacts; flags valid advanced compounds\n\n- **Wrong:** Morgan radius=1 → **Right:** radius=2 minimum (ECFP4) → **Why:** Radius 1 loses structural information; too many false-positive similarities\n\n- **Wrong:** Comparing FPs with different radius or nBits → **Right:** Identical parameters for both FPs → **Why:** Tanimoto only meaningful in same parameter space\n\n- **Wrong:** Ignoring stereochemistry for chiral compounds → **Right:** `includeChirality=True` in generator → **Why:** Default treats enantiomers as identical\n\n- **Wrong:** Fixed 0.7 threshold for all FP types → **Right:** Validate threshold per fingerprint type and chemical series → **Why:** 0.7 convention is ECFP4-specific; other types need different cutoffs\n\n- **Wrong:** Raw SMILES into mmpdb → **Right:** Pre-canonicalize with `MolToSmiles(MolFromSmiles(smi))` → **Why:** mmpdb expects canonical SMILES; non-canonical causes fragmentation errors\n\n- **Wrong:** Confusing LogP with LogD → **Right:** Use LogD at pH 7.4 for ionizable compounds; RDKit computes LogP only → **Why:** LogP overestimates lipophilicity for ionizable molecules at physiological pH\n\n## Response Format\n\n- Lead with the command or code the user needs — explain after\n- Structure as: confirm inputs → working code → key parameters explained → gotchas\n- One complete working example per task; do not show every alternative\n- Keep code comments minimal and functional\n- Target: 50-100 lines of code with brief surrounding explanation\n",{"data":51,"body":64},{"name":4,"description":6,"usage":52,"version":53,"validated_against":54,"tags":59},"Invoke when computing molecular properties, filtering compound libraries, calculating fingerprint similarity, or running matched molecular pair analysis with RDKit.","1.0.0",{"date":55,"packages":56},"2025-01-15",{"rdkit":57,"mmpdb":58},"2024.03","3.1",[60,61,4,37,62,63],"skill","category:pipeline","rdkit","hcls",{"type":65,"children":66},"root",[67,76,83,89,95,115,121,132,159,193,199,206,364,370,552,558,675,681,834,840,1105,1111],{"type":68,"tag":69,"props":70,"children":72},"element","h1",{"id":71},"cheminformatics-rdkit-pipeline-skill-thin-scaffold",[73],{"type":74,"value":75},"text","Cheminformatics (RDKit) — Pipeline Skill (Thin Scaffold)",{"type":68,"tag":77,"props":78,"children":80},"h2",{"id":79},"overview",[81],{"type":74,"value":82},"Overview",{"type":68,"tag":84,"props":85,"children":86},"p",{},[87],{"type":74,"value":88},"Adds fingerprint selection logic, filter cascade ordering, and version-specific gotchas for RDKit workflows. The agent already knows RDKit syntax — this skill prevents parameter mismatches and deprecated API usage.",{"type":68,"tag":77,"props":90,"children":92},{"id":91},"usage",[93],{"type":74,"value":94},"Usage",{"type":68,"tag":96,"props":97,"children":98},"ul",{},[99,105,110],{"type":68,"tag":100,"props":101,"children":102},"li",{},[103],{"type":74,"value":104},"Activate when filtering compound libraries (Lipinski\u002FVeber\u002FPAINS)",{"type":68,"tag":100,"props":106,"children":107},{},[108],{"type":74,"value":109},"Activate for fingerprint similarity search or clustering",{"type":68,"tag":100,"props":111,"children":112},{},[113],{"type":74,"value":114},"Activate for matched molecular pair (MMP) analysis with mmpdb",{"type":68,"tag":77,"props":116,"children":118},{"id":117},"core-concepts",[119],{"type":74,"value":120},"Core Concepts",{"type":68,"tag":84,"props":122,"children":123},{},[124,130],{"type":68,"tag":125,"props":126,"children":127},"strong",{},[128],{"type":74,"value":129},"Filter cascade order:",{"type":74,"value":131}," Lipinski → Veber → PAINS → similarity (cheapest first, most expensive last).",{"type":68,"tag":84,"props":133,"children":134},{},[135,140,142,149,151,157],{"type":68,"tag":125,"props":136,"children":137},{},[138],{"type":74,"value":139},"Fingerprint API:",{"type":74,"value":141}," Use ",{"type":68,"tag":143,"props":144,"children":146},"code",{"className":145},[],[147],{"type":74,"value":148},"rdFingerprintGenerator",{"type":74,"value":150}," module exclusively (since RDKit 2024.03). The ",{"type":68,"tag":143,"props":152,"children":154},{"className":153},[],[155],{"type":74,"value":156},"AllChem.GetMorganFingerprintAsBitVect()",{"type":74,"value":158}," path is deprecated and will be removed.",{"type":68,"tag":84,"props":160,"children":161},{},[162,167,169,175,177,183,185,191],{"type":68,"tag":125,"props":163,"children":164},{},[165],{"type":74,"value":166},"SMILES validation:",{"type":74,"value":168}," Always parse with ",{"type":68,"tag":143,"props":170,"children":172},{"className":171},[],[173],{"type":74,"value":174},"sanitize=False",{"type":74,"value":176}," then explicit ",{"type":68,"tag":143,"props":178,"children":180},{"className":179},[],[181],{"type":74,"value":182},"SanitizeMol()",{"type":74,"value":184}," in try\u002Fexcept. Default ",{"type":68,"tag":143,"props":186,"children":188},{"className":187},[],[189],{"type":74,"value":190},"MolFromSmiles",{"type":74,"value":192}," silently returns None on partial failures.",{"type":68,"tag":77,"props":194,"children":196},{"id":195},"decision-logic",[197],{"type":74,"value":198},"Decision Logic",{"type":68,"tag":200,"props":201,"children":203},"h3",{"id":202},"fingerprint-selection",[204],{"type":74,"value":205},"Fingerprint Selection",{"type":68,"tag":207,"props":208,"children":209},"table",{},[210,239],{"type":68,"tag":211,"props":212,"children":213},"thead",{},[214],{"type":68,"tag":215,"props":216,"children":217},"tr",{},[218,224,229,234],{"type":68,"tag":219,"props":220,"children":221},"th",{},[222],{"type":74,"value":223},"Goal",{"type":68,"tag":219,"props":225,"children":226},{},[227],{"type":74,"value":228},"Fingerprint",{"type":68,"tag":219,"props":230,"children":231},{},[232],{"type":74,"value":233},"Parameters",{"type":68,"tag":219,"props":235,"children":236},{},[237],{"type":74,"value":238},"Tanimoto threshold",{"type":68,"tag":240,"props":241,"children":242},"tbody",{},[243,267,290,313,341],{"type":68,"tag":215,"props":244,"children":245},{},[246,252,257,262],{"type":68,"tag":247,"props":248,"children":249},"td",{},[250],{"type":74,"value":251},"General similarity",{"type":68,"tag":247,"props":253,"children":254},{},[255],{"type":74,"value":256},"Morgan (ECFP4)",{"type":68,"tag":247,"props":258,"children":259},{},[260],{"type":74,"value":261},"radius=2, fpSize=2048",{"type":68,"tag":247,"props":263,"children":264},{},[265],{"type":74,"value":266},"≥ 0.7",{"type":68,"tag":215,"props":268,"children":269},{},[270,275,280,285],{"type":68,"tag":247,"props":271,"children":272},{},[273],{"type":74,"value":274},"High-specificity matching",{"type":68,"tag":247,"props":276,"children":277},{},[278],{"type":74,"value":279},"Morgan (ECFP6)",{"type":68,"tag":247,"props":281,"children":282},{},[283],{"type":74,"value":284},"radius=3, fpSize=4096",{"type":68,"tag":247,"props":286,"children":287},{},[288],{"type":74,"value":289},"≥ 0.6",{"type":68,"tag":215,"props":291,"children":292},{},[293,298,303,308],{"type":68,"tag":247,"props":294,"children":295},{},[296],{"type":74,"value":297},"Substructure screening",{"type":68,"tag":247,"props":299,"children":300},{},[301],{"type":74,"value":302},"MACCS 166 keys",{"type":68,"tag":247,"props":304,"children":305},{},[306],{"type":74,"value":307},"—",{"type":68,"tag":247,"props":309,"children":310},{},[311],{"type":74,"value":312},"≥ 0.8",{"type":68,"tag":215,"props":314,"children":315},{},[316,321,326,337],{"type":68,"tag":247,"props":317,"children":318},{},[319],{"type":74,"value":320},"Pharmacophore similarity",{"type":68,"tag":247,"props":322,"children":323},{},[324],{"type":74,"value":325},"FCFP",{"type":68,"tag":247,"props":327,"children":328},{},[329,331],{"type":74,"value":330},"radius=2, ",{"type":68,"tag":143,"props":332,"children":334},{"className":333},[],[335],{"type":74,"value":336},"GetMorganFeatureAtomInvGen()",{"type":68,"tag":247,"props":338,"children":339},{},[340],{"type":74,"value":289},{"type":68,"tag":215,"props":342,"children":343},{},[344,349,354,359],{"type":68,"tag":247,"props":345,"children":346},{},[347],{"type":74,"value":348},"Large-scale clustering",{"type":68,"tag":247,"props":350,"children":351},{},[352],{"type":74,"value":353},"Morgan",{"type":68,"tag":247,"props":355,"children":356},{},[357],{"type":74,"value":358},"radius=2, fpSize=1024",{"type":68,"tag":247,"props":360,"children":361},{},[362],{"type":74,"value":363},"Speed over precision",{"type":68,"tag":200,"props":365,"children":367},{"id":366},"filter-thresholds",[368],{"type":74,"value":369},"Filter Thresholds",{"type":68,"tag":207,"props":371,"children":372},{},[373,399],{"type":68,"tag":211,"props":374,"children":375},{},[376],{"type":68,"tag":215,"props":377,"children":378},{},[379,384,389,394],{"type":68,"tag":219,"props":380,"children":381},{},[382],{"type":74,"value":383},"Filter",{"type":68,"tag":219,"props":385,"children":386},{},[387],{"type":74,"value":388},"Rule",{"type":68,"tag":219,"props":390,"children":391},{},[392],{"type":74,"value":393},"Threshold",{"type":68,"tag":219,"props":395,"children":396},{},[397],{"type":74,"value":398},"Notes",{"type":68,"tag":240,"props":400,"children":401},{},[402,425,446,466,487,509,529],{"type":68,"tag":215,"props":403,"children":404},{},[405,410,415,420],{"type":68,"tag":247,"props":406,"children":407},{},[408],{"type":74,"value":409},"Lipinski MW",{"type":68,"tag":247,"props":411,"children":412},{},[413],{"type":74,"value":414},"≤ 500 Da",{"type":68,"tag":247,"props":416,"children":417},{},[418],{"type":74,"value":419},"Allow ≤1 violation total",{"type":68,"tag":247,"props":421,"children":422},{},[423],{"type":74,"value":424},"Not binary pass\u002Ffail",{"type":68,"tag":215,"props":426,"children":427},{},[428,433,438,442],{"type":68,"tag":247,"props":429,"children":430},{},[431],{"type":74,"value":432},"Lipinski LogP",{"type":68,"tag":247,"props":434,"children":435},{},[436],{"type":74,"value":437},"≤ 5",{"type":68,"tag":247,"props":439,"children":440},{},[441],{"type":74,"value":307},{"type":68,"tag":247,"props":443,"children":444},{},[445],{"type":74,"value":307},{"type":68,"tag":215,"props":447,"children":448},{},[449,454,458,462],{"type":68,"tag":247,"props":450,"children":451},{},[452],{"type":74,"value":453},"Lipinski HBD",{"type":68,"tag":247,"props":455,"children":456},{},[457],{"type":74,"value":437},{"type":68,"tag":247,"props":459,"children":460},{},[461],{"type":74,"value":307},{"type":68,"tag":247,"props":463,"children":464},{},[465],{"type":74,"value":307},{"type":68,"tag":215,"props":467,"children":468},{},[469,474,479,483],{"type":68,"tag":247,"props":470,"children":471},{},[472],{"type":74,"value":473},"Lipinski HBA",{"type":68,"tag":247,"props":475,"children":476},{},[477],{"type":74,"value":478},"≤ 10",{"type":68,"tag":247,"props":480,"children":481},{},[482],{"type":74,"value":307},{"type":68,"tag":247,"props":484,"children":485},{},[486],{"type":74,"value":307},{"type":68,"tag":215,"props":488,"children":489},{},[490,495,500,505],{"type":68,"tag":247,"props":491,"children":492},{},[493],{"type":74,"value":494},"Veber TPSA",{"type":68,"tag":247,"props":496,"children":497},{},[498],{"type":74,"value":499},"≤ 140 Ų",{"type":68,"tag":247,"props":501,"children":502},{},[503],{"type":74,"value":504},"Hard cutoff",{"type":68,"tag":247,"props":506,"children":507},{},[508],{"type":74,"value":307},{"type":68,"tag":215,"props":510,"children":511},{},[512,517,521,525],{"type":68,"tag":247,"props":513,"children":514},{},[515],{"type":74,"value":516},"Veber RotBonds",{"type":68,"tag":247,"props":518,"children":519},{},[520],{"type":74,"value":478},{"type":68,"tag":247,"props":522,"children":523},{},[524],{"type":74,"value":504},{"type":68,"tag":247,"props":526,"children":527},{},[528],{"type":74,"value":307},{"type":68,"tag":215,"props":530,"children":531},{},[532,537,542,547],{"type":68,"tag":247,"props":533,"children":534},{},[535],{"type":74,"value":536},"PAINS",{"type":68,"tag":247,"props":538,"children":539},{},[540],{"type":74,"value":541},"A+B+C catalogs",{"type":68,"tag":247,"props":543,"children":544},{},[545],{"type":74,"value":546},"HTS triage only",{"type":68,"tag":247,"props":548,"children":549},{},[550],{"type":74,"value":551},"Don't apply to advanced compounds",{"type":68,"tag":200,"props":553,"children":555},{"id":554},"mmp-analysis-decision",[556],{"type":74,"value":557},"MMP Analysis Decision",{"type":68,"tag":207,"props":559,"children":560},{},[561,582],{"type":68,"tag":211,"props":562,"children":563},{},[564],{"type":68,"tag":215,"props":565,"children":566},{},[567,572,577],{"type":68,"tag":219,"props":568,"children":569},{},[570],{"type":74,"value":571},"Scenario",{"type":68,"tag":219,"props":573,"children":574},{},[575],{"type":74,"value":576},"Tool",{"type":68,"tag":219,"props":578,"children":579},{},[580],{"type":74,"value":581},"Key parameter",{"type":68,"tag":240,"props":583,"children":584},{},[585,607,625,651],{"type":68,"tag":215,"props":586,"children":587},{},[588,593,598],{"type":68,"tag":247,"props":589,"children":590},{},[591],{"type":74,"value":592},"SAR from compound pairs",{"type":68,"tag":247,"props":594,"children":595},{},[596],{"type":74,"value":597},"mmpdb fragment → index → transform",{"type":68,"tag":247,"props":599,"children":600},{},[601],{"type":68,"tag":143,"props":602,"children":604},{"className":603},[],[605],{"type":74,"value":606},"--min-pairs 3",{"type":68,"tag":215,"props":608,"children":609},{},[610,615,620],{"type":68,"tag":247,"props":611,"children":612},{},[613],{"type":74,"value":614},"Property prediction",{"type":68,"tag":247,"props":616,"children":617},{},[618],{"type":74,"value":619},"mmpdb predict",{"type":68,"tag":247,"props":621,"children":622},{},[623],{"type":74,"value":624},"Requires indexed DB with property data",{"type":68,"tag":215,"props":626,"children":627},{},[628,633,642],{"type":68,"tag":247,"props":629,"children":630},{},[631],{"type":74,"value":632},"Core identification",{"type":68,"tag":247,"props":634,"children":635},{},[636],{"type":68,"tag":143,"props":637,"children":639},{"className":638},[],[640],{"type":74,"value":641},"rdFMCS.FindMCS()",{"type":68,"tag":247,"props":643,"children":644},{},[645],{"type":68,"tag":143,"props":646,"children":648},{"className":647},[],[649],{"type":74,"value":650},"ringMatchesRingOnly=True, completeRingsOnly=True",{"type":68,"tag":215,"props":652,"children":653},{},[654,659,664],{"type":68,"tag":247,"props":655,"children":656},{},[657],{"type":74,"value":658},"Large libraries (>10K)",{"type":68,"tag":247,"props":660,"children":661},{},[662],{"type":74,"value":663},"mmpdb CLI",{"type":68,"tag":247,"props":665,"children":666},{},[667,673],{"type":68,"tag":143,"props":668,"children":670},{"className":669},[],[671],{"type":74,"value":672},"--max-variable-size 10",{"type":74,"value":674}," to limit fragmentation",{"type":68,"tag":77,"props":676,"children":678},{"id":677},"critical-parameters",[679],{"type":74,"value":680},"Critical Parameters",{"type":68,"tag":207,"props":682,"children":683},{},[684,705],{"type":68,"tag":211,"props":685,"children":686},{},[687],{"type":68,"tag":215,"props":688,"children":689},{},[690,695,700],{"type":68,"tag":219,"props":691,"children":692},{},[693],{"type":74,"value":694},"Parameter",{"type":68,"tag":219,"props":696,"children":697},{},[698],{"type":74,"value":699},"Value",{"type":68,"tag":219,"props":701,"children":702},{},[703],{"type":74,"value":704},"When to change",{"type":68,"tag":240,"props":706,"children":707},{},[708,726,744,762,780,798,816],{"type":68,"tag":215,"props":709,"children":710},{},[711,716,721],{"type":68,"tag":247,"props":712,"children":713},{},[714],{"type":74,"value":715},"Morgan radius",{"type":68,"tag":247,"props":717,"children":718},{},[719],{"type":74,"value":720},"2 (ECFP4)",{"type":68,"tag":247,"props":722,"children":723},{},[724],{"type":74,"value":725},"3 for higher specificity",{"type":68,"tag":215,"props":727,"children":728},{},[729,734,739],{"type":68,"tag":247,"props":730,"children":731},{},[732],{"type":74,"value":733},"fpSize",{"type":68,"tag":247,"props":735,"children":736},{},[737],{"type":74,"value":738},"2048",{"type":68,"tag":247,"props":740,"children":741},{},[742],{"type":74,"value":743},"1024 for speed; 4096 for precision",{"type":68,"tag":215,"props":745,"children":746},{},[747,752,757],{"type":68,"tag":247,"props":748,"children":749},{},[750],{"type":74,"value":751},"includeChirality",{"type":68,"tag":247,"props":753,"children":754},{},[755],{"type":74,"value":756},"False",{"type":68,"tag":247,"props":758,"children":759},{},[760],{"type":74,"value":761},"True for stereo-sensitive applications",{"type":68,"tag":215,"props":763,"children":764},{},[765,770,775],{"type":68,"tag":247,"props":766,"children":767},{},[768],{"type":74,"value":769},"Lipinski max_violations",{"type":68,"tag":247,"props":771,"children":772},{},[773],{"type":74,"value":774},"1",{"type":68,"tag":247,"props":776,"children":777},{},[778],{"type":74,"value":779},"0 for strict; exempt biologics entirely",{"type":68,"tag":215,"props":781,"children":782},{},[783,788,793],{"type":68,"tag":247,"props":784,"children":785},{},[786],{"type":74,"value":787},"mmpdb --min-pairs",{"type":68,"tag":247,"props":789,"children":790},{},[791],{"type":74,"value":792},"3",{"type":68,"tag":247,"props":794,"children":795},{},[796],{"type":74,"value":797},"Lower for sparse datasets",{"type":68,"tag":215,"props":799,"children":800},{},[801,806,811],{"type":68,"tag":247,"props":802,"children":803},{},[804],{"type":74,"value":805},"mmpdb --max-variable-size",{"type":68,"tag":247,"props":807,"children":808},{},[809],{"type":74,"value":810},"10",{"type":68,"tag":247,"props":812,"children":813},{},[814],{"type":74,"value":815},"Increase for macrocycle transformations",{"type":68,"tag":215,"props":817,"children":818},{},[819,824,829],{"type":68,"tag":247,"props":820,"children":821},{},[822],{"type":74,"value":823},"PAINS catalogs",{"type":68,"tag":247,"props":825,"children":826},{},[827],{"type":74,"value":828},"A+B+C (all three)",{"type":68,"tag":247,"props":830,"children":831},{},[832],{"type":74,"value":833},"Never use partial sets",{"type":68,"tag":77,"props":835,"children":837},{"id":836},"common-mistakes",[838],{"type":74,"value":839},"Common Mistakes",{"type":68,"tag":96,"props":841,"children":842},{},[843,880,923,944,965,986,1007,1035,1056,1084],{"type":68,"tag":100,"props":844,"children":845},{},[846,851,853,858,860,865,866,872,873,878],{"type":68,"tag":125,"props":847,"children":848},{},[849],{"type":74,"value":850},"Wrong:",{"type":74,"value":852}," ",{"type":68,"tag":143,"props":854,"children":856},{"className":855},[],[857],{"type":74,"value":156},{"type":74,"value":859}," → ",{"type":68,"tag":125,"props":861,"children":862},{},[863],{"type":74,"value":864},"Right:",{"type":74,"value":852},{"type":68,"tag":143,"props":867,"children":869},{"className":868},[],[870],{"type":74,"value":871},"rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=2048).GetFingerprint(mol)",{"type":74,"value":859},{"type":68,"tag":125,"props":874,"children":875},{},[876],{"type":74,"value":877},"Why:",{"type":74,"value":879}," AllChem FP functions deprecated since RDKit 2024.03, will be removed",{"type":68,"tag":100,"props":881,"children":882},{},[883,887,889,895,897,901,902,908,910,915,917,921],{"type":68,"tag":125,"props":884,"children":885},{},[886],{"type":74,"value":850},{"type":74,"value":888}," Default ",{"type":68,"tag":143,"props":890,"children":892},{"className":891},[],[893],{"type":74,"value":894},"MolFromSmiles(smi)",{"type":74,"value":896}," without error handling → ",{"type":68,"tag":125,"props":898,"children":899},{},[900],{"type":74,"value":864},{"type":74,"value":852},{"type":68,"tag":143,"props":903,"children":905},{"className":904},[],[906],{"type":74,"value":907},"MolFromSmiles(smi, sanitize=False)",{"type":74,"value":909}," + ",{"type":68,"tag":143,"props":911,"children":913},{"className":912},[],[914],{"type":74,"value":182},{"type":74,"value":916}," in try\u002Fexcept → ",{"type":68,"tag":125,"props":918,"children":919},{},[920],{"type":74,"value":877},{"type":74,"value":922}," Default silently returns None; explicit sanitize catches partial failures",{"type":68,"tag":100,"props":924,"children":925},{},[926,930,932,936,938,942],{"type":68,"tag":125,"props":927,"children":928},{},[929],{"type":74,"value":850},{"type":74,"value":931}," Lipinski as hard binary filter → ",{"type":68,"tag":125,"props":933,"children":934},{},[935],{"type":74,"value":864},{"type":74,"value":937}," Allow ≤1 violation → ",{"type":68,"tag":125,"props":939,"children":940},{},[941],{"type":74,"value":877},{"type":74,"value":943}," Many approved drugs violate one rule; binary filtering rejects valid candidates",{"type":68,"tag":100,"props":945,"children":946},{},[947,951,953,957,959,963],{"type":68,"tag":125,"props":948,"children":949},{},[950],{"type":74,"value":850},{"type":74,"value":952}," PAINS on clinical candidates → ",{"type":68,"tag":125,"props":954,"children":955},{},[956],{"type":74,"value":864},{"type":74,"value":958}," PAINS only for HTS library triage → ",{"type":68,"tag":125,"props":960,"children":961},{},[962],{"type":74,"value":877},{"type":74,"value":964}," Designed for screening artifacts; flags valid advanced compounds",{"type":68,"tag":100,"props":966,"children":967},{},[968,972,974,978,980,984],{"type":68,"tag":125,"props":969,"children":970},{},[971],{"type":74,"value":850},{"type":74,"value":973}," Morgan radius=1 → ",{"type":68,"tag":125,"props":975,"children":976},{},[977],{"type":74,"value":864},{"type":74,"value":979}," radius=2 minimum (ECFP4) → ",{"type":68,"tag":125,"props":981,"children":982},{},[983],{"type":74,"value":877},{"type":74,"value":985}," Radius 1 loses structural information; too many false-positive similarities",{"type":68,"tag":100,"props":987,"children":988},{},[989,993,995,999,1001,1005],{"type":68,"tag":125,"props":990,"children":991},{},[992],{"type":74,"value":850},{"type":74,"value":994}," Comparing FPs with different radius or nBits → ",{"type":68,"tag":125,"props":996,"children":997},{},[998],{"type":74,"value":864},{"type":74,"value":1000}," Identical parameters for both FPs → ",{"type":68,"tag":125,"props":1002,"children":1003},{},[1004],{"type":74,"value":877},{"type":74,"value":1006}," Tanimoto only meaningful in same parameter space",{"type":68,"tag":100,"props":1008,"children":1009},{},[1010,1014,1016,1020,1021,1027,1029,1033],{"type":68,"tag":125,"props":1011,"children":1012},{},[1013],{"type":74,"value":850},{"type":74,"value":1015}," Ignoring stereochemistry for chiral compounds → ",{"type":68,"tag":125,"props":1017,"children":1018},{},[1019],{"type":74,"value":864},{"type":74,"value":852},{"type":68,"tag":143,"props":1022,"children":1024},{"className":1023},[],[1025],{"type":74,"value":1026},"includeChirality=True",{"type":74,"value":1028}," in generator → ",{"type":68,"tag":125,"props":1030,"children":1031},{},[1032],{"type":74,"value":877},{"type":74,"value":1034}," Default treats enantiomers as identical",{"type":68,"tag":100,"props":1036,"children":1037},{},[1038,1042,1044,1048,1050,1054],{"type":68,"tag":125,"props":1039,"children":1040},{},[1041],{"type":74,"value":850},{"type":74,"value":1043}," Fixed 0.7 threshold for all FP types → ",{"type":68,"tag":125,"props":1045,"children":1046},{},[1047],{"type":74,"value":864},{"type":74,"value":1049}," Validate threshold per fingerprint type and chemical series → ",{"type":68,"tag":125,"props":1051,"children":1052},{},[1053],{"type":74,"value":877},{"type":74,"value":1055}," 0.7 convention is ECFP4-specific; other types need different cutoffs",{"type":68,"tag":100,"props":1057,"children":1058},{},[1059,1063,1065,1069,1071,1077,1078,1082],{"type":68,"tag":125,"props":1060,"children":1061},{},[1062],{"type":74,"value":850},{"type":74,"value":1064}," Raw SMILES into mmpdb → ",{"type":68,"tag":125,"props":1066,"children":1067},{},[1068],{"type":74,"value":864},{"type":74,"value":1070}," Pre-canonicalize with ",{"type":68,"tag":143,"props":1072,"children":1074},{"className":1073},[],[1075],{"type":74,"value":1076},"MolToSmiles(MolFromSmiles(smi))",{"type":74,"value":859},{"type":68,"tag":125,"props":1079,"children":1080},{},[1081],{"type":74,"value":877},{"type":74,"value":1083}," mmpdb expects canonical SMILES; non-canonical causes fragmentation errors",{"type":68,"tag":100,"props":1085,"children":1086},{},[1087,1091,1093,1097,1099,1103],{"type":68,"tag":125,"props":1088,"children":1089},{},[1090],{"type":74,"value":850},{"type":74,"value":1092}," Confusing LogP with LogD → ",{"type":68,"tag":125,"props":1094,"children":1095},{},[1096],{"type":74,"value":864},{"type":74,"value":1098}," Use LogD at pH 7.4 for ionizable compounds; RDKit computes LogP only → ",{"type":68,"tag":125,"props":1100,"children":1101},{},[1102],{"type":74,"value":877},{"type":74,"value":1104}," LogP overestimates lipophilicity for ionizable molecules at physiological pH",{"type":68,"tag":77,"props":1106,"children":1108},{"id":1107},"response-format",[1109],{"type":74,"value":1110},"Response Format",{"type":68,"tag":96,"props":1112,"children":1113},{},[1114,1119,1124,1129,1134],{"type":68,"tag":100,"props":1115,"children":1116},{},[1117],{"type":74,"value":1118},"Lead with the command or code the user needs — explain after",{"type":68,"tag":100,"props":1120,"children":1121},{},[1122],{"type":74,"value":1123},"Structure as: confirm inputs → working code → key parameters explained → gotchas",{"type":68,"tag":100,"props":1125,"children":1126},{},[1127],{"type":74,"value":1128},"One complete working example per task; do not show every alternative",{"type":68,"tag":100,"props":1130,"children":1131},{},[1132],{"type":74,"value":1133},"Keep code comments minimal and functional",{"type":68,"tag":100,"props":1135,"children":1136},{},[1137],{"type":74,"value":1138},"Target: 50-100 lines of code with brief surrounding explanation",{"items":1140,"total":1230},[1141,1162,1173,1187,1200,1207,1220],{"slug":1142,"name":1142,"fn":1143,"description":1144,"org":1145,"tags":1146,"stars":26,"repoUrl":27,"updatedAt":1161},"aws-genai-ml-architect","design AWS GenAI and ML architectures","Reasoning skill for designing AWS GenAI and ML architectures for healthcare and life sciences workloads. Use when the user asks to choose between SageMaker and Bedrock, design a RAG system over medical literature, architect clinical NLP or medical imaging inference, plan genomics or drug discovery pipelines on AWS, address HIPAA\u002FPHI compliance in ML systems, design MLOps for regulated clinical models, or optimize cost for HCLS ML workloads. Triggers include \"AWS architecture\", \"SageMaker vs Bedrock\", \"HIPAA ML\", \"clinical RAG\", \"medical imaging inference\", \"genomics on AWS\", \"PHI training\", \"MLOps healthcare\", \"Bedrock guardrails\", \"HealthLake\", \"HCLS cloud architecture\", \"BAA compliance\", \"SageMaker endpoint\", \"Bedrock knowledge base\", \"clinical NLP on AWS\", \"FDA SaMD on AWS\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1147,1150,1153,1156,1158],{"name":1148,"slug":1149,"type":16},"Architecture","architecture",{"name":1151,"slug":1152,"type":16},"AWS","aws",{"name":1154,"slug":1155,"type":16},"Healthcare","healthcare",{"name":1157,"slug":41,"type":16},"Life Sciences",{"name":1159,"slug":1160,"type":16},"LLM","llm","2026-07-12T08:38:07.975937",{"slug":1163,"name":1163,"fn":1164,"description":1165,"org":1166,"tags":1167,"stars":26,"repoUrl":27,"updatedAt":1172},"biomarker-discovery","guide biomarker discovery and validation","Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include \"discover a biomarker\", \"validate biomarker\", \"prognostic vs predictive\", \"feature selection\", \"LASSO vs elastic net\", \"nested cross-validation\", \"data leakage\", \"C-index\", \"time-dependent AUC\", \"decision curve analysis\", \"external validation cohort\", \"events per variable\", \"optimism-corrected\", \"multi-omics integration\", \"clinical utility of a biomarker\", \"is this biomarker ready\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1168,1169,1170,1171],{"name":1151,"slug":1152,"type":16},{"name":21,"slug":22,"type":16},{"name":1157,"slug":41,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T08:37:49.295301",{"slug":1174,"name":1174,"fn":1175,"description":1176,"org":1177,"tags":1178,"stars":26,"repoUrl":27,"updatedAt":1186},"cdisc-compliance","reason about CDISC SDTM and ADaM implementation","Reason about CDISC SDTM and ADaM implementation for regulatory submissions. Use when the user asks about SDTM domain mapping, ADaM dataset design, controlled terminology versioning, define.xml completeness, FDA or PMDA submission requirements, query prioritization by clinical impact, SUPPQUAL usage, or CDISC compliance review. Triggers include \"SDTM mapping\", \"ADaM dataset\", \"CDISC compliance\", \"controlled terminology\", \"define.xml\", \"FDA submission data\", \"PMDA submission\", \"SDTM domain\", \"ADSL\", \"ADAE\", \"ADLB\", \"BDS structure\", \"SUPPQUAL\", \"RELREC\", \"value-level metadata\", \"CDISC CT\", \"regulatory submission data standards\", \"eCTD datasets\", \"SDTM 3.3\", \"ADaM 1.1\", \"query prioritization\", \"clinical data review\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1179,1182,1183],{"name":1180,"slug":1181,"type":16},"Clinical Trials","clinical-trials",{"name":1157,"slug":41,"type":16},{"name":1184,"slug":1185,"type":16},"Regulatory Compliance","regulatory-compliance","2026-07-12T08:37:33.35594",{"slug":1188,"name":1188,"fn":1189,"description":1190,"org":1191,"tags":1192,"stars":26,"repoUrl":27,"updatedAt":1199},"cell-type-annotation","annotate single-cell RNA-seq clusters","Generate code to assign cell type labels to single-cell RNA-seq clusters using CellTypist, SingleR, marker-based annotation, or reference label transfer (scANVI\u002Fingest). Triggers on requests to \"annotate cell types\", \"label clusters\", \"run CellTypist\", \"SingleR annotation\", \"marker gene dotplot\", \"transfer labels from reference atlas\", \"cell identity\", \"automated annotation\", \"reference mapping\", \"scANVI label transfer\", \"canonical markers\", \"immune cell types\", \"hierarchical annotation\", \"majority voting CellTypist\", \"over-clustering annotation\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1193,1194,1195,1196],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":1157,"slug":41,"type":16},{"name":1197,"slug":1198,"type":16},"RNA-seq","rna-seq","2026-07-12T08:38:05.443454",{"slug":4,"name":4,"fn":5,"description":6,"org":1201,"tags":1202,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1203,1204,1205,1206],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":1208,"name":1208,"fn":1209,"description":1210,"org":1211,"tags":1212,"stars":26,"repoUrl":27,"updatedAt":1219},"claims-analytics","analyze and parse healthcare claims data","Pipeline skill for healthcare claims data parsing, analysis, and fraud detection. Use when the user asks to parse X12 837 or 835 claim files, manipulate ICD-10 CPT or HCPCS codes, detect billing pattern anomalies, profile providers against specialty peers, identify outlier billing behavior, validate NCCI edits programmatically, detect duplicate claims, run Benford's law analysis on charges, build claims data pipelines, or analyze E&M code distributions. Triggers include \"parse X12 837\", \"parse 835\", \"claims SQL\", \"ICD-10 manipulation\", \"CPT code analysis\", \"provider profiling\", \"billing outlier\", \"NCCI validation code\", \"duplicate claim detection\", \"Benford's law charges\", \"claims ETL\", \"E&M distribution analysis\", \"claims analytics pipeline\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1213,1214,1215,1218],{"name":18,"slug":19,"type":16},{"name":1154,"slug":1155,"type":16},{"name":1216,"slug":1217,"type":16},"Insurance","insurance",{"name":1157,"slug":41,"type":16},"2026-07-12T08:37:34.815088",{"slug":1221,"name":1221,"fn":1222,"description":1223,"org":1224,"tags":1225,"stars":26,"repoUrl":27,"updatedAt":1229},"claims-billing-rules","analyze healthcare claims billing rules","Reasoning skill for healthcare claims billing rules and fraud detection logic. Use when the user asks about CMS billing rules, place of service codes, global surgery periods, modifier usage (25 59 76 77), NCCI edit logic, column 1 column 2 code pairs, mutually exclusive procedures, modifier indicators, fraud waste and abuse patterns, E&M upcoding, unbundling, phantom billing, impossible day detection, coding error versus fraud distinction, FWA investigation methodology, or claims audit logic. Triggers include \"CMS billing rules\", \"NCCI edits\", \"modifier 25\", \"modifier 59\", \"global surgery period\", \"upcoding\", \"unbundling\", \"phantom billing\", \"impossible day\", \"FWA\", \"fraud waste abuse\", \"coding error vs fraud\", \"claims audit\", \"billing compliance\", \"E&M level selection\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1226,1227,1228],{"name":1154,"slug":1155,"type":16},{"name":1216,"slug":1217,"type":16},{"name":1184,"slug":1185,"type":16},"2026-07-12T08:38:28.210856",40,{"items":1232,"total":1408},[1233,1252,1273,1283,1296,1309,1319,1329,1350,1365,1380,1395],{"slug":1234,"name":1234,"fn":1235,"description":1236,"org":1237,"tags":1238,"stars":1249,"repoUrl":1250,"updatedAt":1251},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1239,1240,1243,1246],{"name":1151,"slug":1152,"type":16},{"name":1241,"slug":1242,"type":16},"Debugging","debugging",{"name":1244,"slug":1245,"type":16},"Logs","logs",{"name":1247,"slug":1248,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":1253,"name":1254,"fn":1255,"description":1256,"org":1257,"tags":1258,"stars":1249,"repoUrl":1250,"updatedAt":1272},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1259,1262,1263,1266,1269],{"name":1260,"slug":1261,"type":16},"Aurora","aurora",{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},"Database","database",{"name":1267,"slug":1268,"type":16},"Serverless","serverless",{"name":1270,"slug":1271,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":1274,"name":1275,"fn":1255,"description":1256,"org":1276,"tags":1277,"stars":1249,"repoUrl":1250,"updatedAt":1282},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1278,1279,1280,1281],{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},{"name":1267,"slug":1268,"type":16},{"name":1270,"slug":1271,"type":16},"2026-07-12T08:36:42.694299",{"slug":1284,"name":1285,"fn":1255,"description":1256,"org":1286,"tags":1287,"stars":1249,"repoUrl":1250,"updatedAt":1295},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1288,1289,1290,1293,1294],{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},{"name":1291,"slug":1292,"type":16},"Migration","migration",{"name":1267,"slug":1268,"type":16},{"name":1270,"slug":1271,"type":16},"2026-07-12T08:36:38.584057",{"slug":1297,"name":1298,"fn":1255,"description":1256,"org":1299,"tags":1300,"stars":1249,"repoUrl":1250,"updatedAt":1308},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1301,1302,1303,1306,1307],{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},{"name":1304,"slug":1305,"type":16},"PostgreSQL","postgresql",{"name":1267,"slug":1268,"type":16},{"name":1270,"slug":1271,"type":16},"2026-07-12T08:36:46.530743",{"slug":1310,"name":1311,"fn":1255,"description":1256,"org":1312,"tags":1313,"stars":1249,"repoUrl":1250,"updatedAt":1318},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1314,1315,1316,1317],{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},{"name":1267,"slug":1268,"type":16},{"name":1270,"slug":1271,"type":16},"2026-07-12T08:36:48.104182",{"slug":1320,"name":1320,"fn":1255,"description":1256,"org":1321,"tags":1322,"stars":1249,"repoUrl":1250,"updatedAt":1328},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1323,1324,1325,1326,1327],{"name":1151,"slug":1152,"type":16},{"name":1264,"slug":1265,"type":16},{"name":1291,"slug":1292,"type":16},{"name":1267,"slug":1268,"type":16},{"name":1270,"slug":1271,"type":16},"2026-07-12T08:36:36.374512",{"slug":1330,"name":1330,"fn":1331,"description":1332,"org":1333,"tags":1334,"stars":1347,"repoUrl":1348,"updatedAt":1349},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1335,1338,1341,1344],{"name":1336,"slug":1337,"type":16},"Accounting","accounting",{"name":1339,"slug":1340,"type":16},"Analytics","analytics",{"name":1342,"slug":1343,"type":16},"Cost Optimization","cost-optimization",{"name":1345,"slug":1346,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":1351,"name":1351,"fn":1352,"description":1353,"org":1354,"tags":1355,"stars":1347,"repoUrl":1348,"updatedAt":1364},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1356,1357,1358,1361],{"name":1151,"slug":1152,"type":16},{"name":1345,"slug":1346,"type":16},{"name":1359,"slug":1360,"type":16},"Management","management",{"name":1362,"slug":1363,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":1366,"name":1366,"fn":1367,"description":1368,"org":1369,"tags":1370,"stars":1347,"repoUrl":1348,"updatedAt":1379},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1371,1372,1373,1376],{"name":1339,"slug":1340,"type":16},{"name":1345,"slug":1346,"type":16},{"name":1374,"slug":1375,"type":16},"Financial Statements","financial-statements",{"name":1377,"slug":1378,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":1381,"name":1381,"fn":1382,"description":1383,"org":1384,"tags":1385,"stars":1347,"repoUrl":1348,"updatedAt":1394},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1386,1389,1392],{"name":1387,"slug":1388,"type":16},"Automation","automation",{"name":1390,"slug":1391,"type":16},"Documents","documents",{"name":1393,"slug":1381,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":1396,"name":1396,"fn":1397,"description":1398,"org":1399,"tags":1400,"stars":1347,"repoUrl":1348,"updatedAt":1407},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1401,1402,1403,1404],{"name":1336,"slug":1337,"type":16},{"name":18,"slug":19,"type":16},{"name":1345,"slug":1346,"type":16},{"name":1405,"slug":1406,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150]