[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XFGEXH90YD3TSF6YPTPX2Q":3,"skill-same:01M6XFGEXH90YD3TSF6YPTPX2Q":99},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6XFGEXH90YD3TSF6YPTPX2Q","denovo-design",null,"De novo molecule generation for drug discovery. Scaffold-based analog enumeration, fragment growing\u002Flinking, structure-based design, multi-objective optimization, and drug-likeness filtering.","fadrienne\u002FMyGitHub","fadrienne","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197874571?v=4","01M6X64V8VWCRSMFZ4EPS2BWXG","Francesca Adrienne","01M6X64VD5MW4F9PHDWQKS7ZAF",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"denovo design","design","de","multi-objective","Structure-Based Design","likeness","objective","linking","for","fragment","multi","drug discovery","synthetic","generation","structure","filtering","discovery","enumeration","Optimization","scaffold","2026-11-10 10:12:30",false,"---\nname: denovo-design\ndescription: De novo molecule generation for drug discovery. Scaffold-based analog enumeration, fragment growing\u002Flinking, structure-based design, multi-objective optimization, and drug-likeness filtering.\ncategory: chemistry\nlicense: MIT\nmetadata:\n    skill-author: Synthetic Sciences\n---\n\n# De Novo Molecule Design\n\n## Overview\n\nDe novo design is the computational generation of novel molecular structures with desired properties, without starting from known active compounds. This skill provides a complete toolkit for generating drug candidates through multiple complementary strategies: scaffold-based analog enumeration, fragment-based design, structure-based design (SBDD), multi-objective optimization, and drug-likeness filtering.\n\nAll generation strategies produce molecules with computed physicochemical properties and similarity metrics, enabling rapid prioritization. The scripts are designed for CPU-first execution using RDKit as the core cheminformatics engine, with optional GPU acceleration noted where applicable.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n\n- **Explore chemical space** around a known lead compound by generating analogs with R-group enumeration, bioisosteric replacements, or random mutations\n- **Design molecules from fragments** by growing, linking, or merging fragment hits from screening campaigns\n- **Generate molecules for a protein target** using pocket shape complementarity or pharmacophore constraints\n- **Optimize a set of hits** against multiple objectives (QED, LogP, synthetic accessibility, molecular weight) through iterative refinement\n- **Filter compound libraries** for drug-likeness using Lipinski, Veber, PAINS, Brenk alerts, lead-like, fragment-like, or beyond Rule of Five criteria\n- **Enumerate focused libraries** for virtual screening or synthesis planning\n\n## Installation\n\n```bash\npip install rdkit-pypi datamol numpy pandas\n```\n\nOptional (for enhanced fragment design and structure-based approaches):\n\n```bash\npip install scipy\n```\n\nFor structure-based design with PDB parsing:\n\n```bash\npip install biopython\n```\n\n## Choosing the Right Strategy\n\n| Scenario | Script | Strategy |\n|----------|--------|----------|\n| Have a lead compound, want analogs | `generate_analogs.py` | R-group, bioisostere, mutate |\n| Have fragment screening hits | `generate_fragments.py` | grow, link, merge |\n| Have a protein structure \u002F pocket | `generate_sbdd.py` | shape, pharmacophore |\n| Have hits, need property optimization | `optimize.py` | multi-objective iterative |\n| Have a library, need filtering | `filter.py` | lipinski, veber, pains, etc. |\n\n## Core Workflows\n\n### 1. Analog Generation\n\nGenerate structural analogs of a lead compound using three complementary strategies.\n\n```bash\n# Generate 50 analogs using all strategies\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --num 50 --strategy all\n\n# Only bioisosteric replacements\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --strategy bioisostere\n\n# Only R-group enumeration\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --strategy rgroup\n```\n\nStrategies:\n- **R-group enumeration**: Identifies aromatic and sp3 carbon positions, enumerates common substituents (methyl, ethyl, halides, CF3, OMe, NH2, OH, CN, etc.)\n- **Bioisosteric replacement**: Swaps functional groups using a curated dictionary (COOH to tetrazole, phenyl to thienyl, amide to sulfonamide, ester to oxadiazole, etc.)\n- **Random mutation**: Fragment-based random modifications to the molecular graph\n\nOutput CSV includes: id, smiles, mw, logp, qed, tanimoto_to_parent, strategy.\n\n### 2. Fragment-Based Design\n\nBuild drug-like molecules from fragment hits.\n\n```bash\n# Grow a fragment by adding substituents\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1\" --mode grow --output grown.csv --num 50\n\n# Link two fragments\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1,c1ccccc1O\" --mode link --output linked.csv --num 50\n\n# Merge fragment pharmacophores\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1,c1ccccc1O\" --mode merge --output merged.csv --num 50\n```\n\nModes:\n- **Grow**: Adds substituents at attachment points on a single fragment\n- **Link**: Connects two fragments with linkers (alkyl chains, amides, ethers, piperazines, etc.)\n- **Merge**: Combines pharmacophoric features of two fragments into hybrid molecules\n\n### 3. Structure-Based Design (SBDD)\n\nGenerate molecules complementary to a protein binding pocket.\n\n```bash\n# Shape-based design from a PDB file\npython scripts\u002Fgenerate_sbdd.py --protein target.pdb --pocket-residues \"ASP189,SER195,HIS57\" --method shape --output sbdd_hits.csv --num 100\n\n# Pharmacophore-based design\npython scripts\u002Fgenerate_sbdd.py --protein target.pdb --pocket-residues auto --method pharmacophore --output sbdd_hits.csv --num 100\n```\n\nMethods:\n- **Shape-based** (CPU): Generates molecules complementing the pocket shape using fragment assembly\n- **Pharmacophore** (CPU): Defines pharmacophore features from pocket residues and generates matching molecules\n\nNote: For production SBDD, consider GPU-accelerated methods like DiffSBDD or Pocket2Mol. This script provides a CPU-based starting point.\n\n### 4. Multi-Objective Optimization\n\nIteratively optimize a set of compounds against multiple property objectives.\n\n```bash\n# Optimize for QED and LogP with constraints\npython scripts\u002Foptimize.py --input hits.csv --objectives qed,logp,sa --constraints \"mw\u003C500,logp\u003C5,qed>0.5\" --output optimized.csv --num-iterations 3\n```\n\nThe optimizer runs iterative cycles: generate analogs, compute properties, filter by constraints, rank by multi-objective score, select top compounds for the next round.\n\n### 5. Drug-Likeness Filtering\n\nApply standard medicinal chemistry filters to compound libraries.\n\n```bash\n# Apply Lipinski and PAINS filters\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters lipinski,pains\n\n# Apply all available filters\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters lipinski,veber,qed,pains,brenk,leadlike,fragmentlike,bro5\n\n# Custom thresholds\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters qed,pains --qed-threshold 0.6 --sa-threshold 5.0\n```\n\nAvailable filters:\n- **Lipinski Ro5**: MW \u003C= 500, LogP \u003C= 5, HBD \u003C= 5, HBA \u003C= 10\n- **Veber**: RotBonds \u003C= 10, TPSA \u003C= 140\n- **QED**: Quantitative drug-likeness score above threshold\n- **PAINS**: Pan-assay interference compounds (RDKit FilterCatalog)\n- **Brenk**: Structural alerts for reactive\u002Ftoxic groups\n- **Lead-like**: MW 200-350, LogP -1 to 3\n- **Fragment-like (Ro3)**: MW \u003C= 300, LogP \u003C= 3, HBD \u003C= 3, HBA \u003C= 3\n- **bRo5**: Beyond Rule of Five for natural product-like space (MW 500-1000, LogP -2 to 10)\n- **SA score**: Synthetic accessibility (1 = easy, 10 = hard)\n\n## Tips\n\n- **Start broad, then narrow**: Use `generate_analogs.py` with `--strategy all` first, then filter with `filter.py`, then optimize survivors with `optimize.py`.\n- **Fragment merging is powerful**: If you have multiple fragment hits from an FBDD campaign, merging can produce leads that retain key interactions from both fragments.\n- **Combine SBDD with filtering**: Structure-based hits often need medicinal chemistry optimization. Pipe SBDD output through `filter.py` and `optimize.py`.\n- **Check synthetic accessibility**: Always include SA score in your analysis. A beautiful molecule is useless if it cannot be synthesized. Use `--sa-threshold 5.0` or lower for practical compounds.\n- **Deduplicate early**: All generation scripts deduplicate by canonical SMILES, but if you combine outputs from multiple runs, deduplicate again before downstream analysis.\n- **Property distributions matter**: Look at the property distribution summaries printed by each script. Bimodal distributions or outliers can indicate issues with the generation strategy.\n","# De Novo Molecule Design\n\n## Overview\n\nDe novo design is the computational generation of novel molecular structures with desired properties, without starting from known active compounds. This skill provides a complete toolkit for generating drug candidates through multiple complementary strategies: scaffold-based analog enumeration, fragment-based design, structure-based design (SBDD), multi-objective optimization, and drug-likeness filtering.\n\nAll generation strategies produce molecules with computed physicochemical properties and similarity metrics, enabling rapid prioritization. The scripts are designed for CPU-first execution using RDKit as the core cheminformatics engine, with optional GPU acceleration noted where applicable.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n\n- **Explore chemical space** around a known lead compound by generating analogs with R-group enumeration, bioisosteric replacements, or random mutations\n- **Design molecules from fragments** by growing, linking, or merging fragment hits from screening campaigns\n- **Generate molecules for a protein target** using pocket shape complementarity or pharmacophore constraints\n- **Optimize a set of hits** against multiple objectives (QED, LogP, synthetic accessibility, molecular weight) through iterative refinement\n- **Filter compound libraries** for drug-likeness using Lipinski, Veber, PAINS, Brenk alerts, lead-like, fragment-like, or beyond Rule of Five criteria\n- **Enumerate focused libraries** for virtual screening or synthesis planning\n\n## Installation\n\n```bash\npip install rdkit-pypi datamol numpy pandas\n```\n\nOptional (for enhanced fragment design and structure-based approaches):\n\n```bash\npip install scipy\n```\n\nFor structure-based design with PDB parsing:\n\n```bash\npip install biopython\n```\n\n## Choosing the Right Strategy\n\n| Scenario | Script | Strategy |\n|----------|--------|----------|\n| Have a lead compound, want analogs | `generate_analogs.py` | R-group, bioisostere, mutate |\n| Have fragment screening hits | `generate_fragments.py` | grow, link, merge |\n| Have a protein structure \u002F pocket | `generate_sbdd.py` | shape, pharmacophore |\n| Have hits, need property optimization | `optimize.py` | multi-objective iterative |\n| Have a library, need filtering | `filter.py` | lipinski, veber, pains, etc. |\n\n## Core Workflows\n\n### 1. Analog Generation\n\nGenerate structural analogs of a lead compound using three complementary strategies.\n\n```bash\n# Generate 50 analogs using all strategies\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --num 50 --strategy all\n\n# Only bioisosteric replacements\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --strategy bioisostere\n\n# Only R-group enumeration\npython scripts\u002Fgenerate_analogs.py --smiles \"c1ccc(NC(=O)c2ccccc2)cc1\" --output analogs.csv --strategy rgroup\n```\n\nStrategies:\n- **R-group enumeration**: Identifies aromatic and sp3 carbon positions, enumerates common substituents (methyl, ethyl, halides, CF3, OMe, NH2, OH, CN, etc.)\n- **Bioisosteric replacement**: Swaps functional groups using a curated dictionary (COOH to tetrazole, phenyl to thienyl, amide to sulfonamide, ester to oxadiazole, etc.)\n- **Random mutation**: Fragment-based random modifications to the molecular graph\n\nOutput CSV includes: id, smiles, mw, logp, qed, tanimoto_to_parent, strategy.\n\n### 2. Fragment-Based Design\n\nBuild drug-like molecules from fragment hits.\n\n```bash\n# Grow a fragment by adding substituents\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1\" --mode grow --output grown.csv --num 50\n\n# Link two fragments\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1,c1ccccc1O\" --mode link --output linked.csv --num 50\n\n# Merge fragment pharmacophores\npython scripts\u002Fgenerate_fragments.py --fragments \"c1cc[nH]c1,c1ccccc1O\" --mode merge --output merged.csv --num 50\n```\n\nModes:\n- **Grow**: Adds substituents at attachment points on a single fragment\n- **Link**: Connects two fragments with linkers (alkyl chains, amides, ethers, piperazines, etc.)\n- **Merge**: Combines pharmacophoric features of two fragments into hybrid molecules\n\n### 3. Structure-Based Design (SBDD)\n\nGenerate molecules complementary to a protein binding pocket.\n\n```bash\n# Shape-based design from a PDB file\npython scripts\u002Fgenerate_sbdd.py --protein target.pdb --pocket-residues \"ASP189,SER195,HIS57\" --method shape --output sbdd_hits.csv --num 100\n\n# Pharmacophore-based design\npython scripts\u002Fgenerate_sbdd.py --protein target.pdb --pocket-residues auto --method pharmacophore --output sbdd_hits.csv --num 100\n```\n\nMethods:\n- **Shape-based** (CPU): Generates molecules complementing the pocket shape using fragment assembly\n- **Pharmacophore** (CPU): Defines pharmacophore features from pocket residues and generates matching molecules\n\nNote: For production SBDD, consider GPU-accelerated methods like DiffSBDD or Pocket2Mol. This script provides a CPU-based starting point.\n\n### 4. Multi-Objective Optimization\n\nIteratively optimize a set of compounds against multiple property objectives.\n\n```bash\n# Optimize for QED and LogP with constraints\npython scripts\u002Foptimize.py --input hits.csv --objectives qed,logp,sa --constraints \"mw\u003C500,logp\u003C5,qed>0.5\" --output optimized.csv --num-iterations 3\n```\n\nThe optimizer runs iterative cycles: generate analogs, compute properties, filter by constraints, rank by multi-objective score, select top compounds for the next round.\n\n### 5. Drug-Likeness Filtering\n\nApply standard medicinal chemistry filters to compound libraries.\n\n```bash\n# Apply Lipinski and PAINS filters\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters lipinski,pains\n\n# Apply all available filters\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters lipinski,veber,qed,pains,brenk,leadlike,fragmentlike,bro5\n\n# Custom thresholds\npython scripts\u002Ffilter.py --input library.csv --output filtered.csv --filters qed,pains --qed-threshold 0.6 --sa-threshold 5.0\n```\n\nAvailable filters:\n- **Lipinski Ro5**: MW \u003C= 500, LogP \u003C= 5, HBD \u003C= 5, HBA \u003C= 10\n- **Veber**: RotBonds \u003C= 10, TPSA \u003C= 140\n- **QED**: Quantitative drug-likeness score above threshold\n- **PAINS**: Pan-assay interference compounds (RDKit FilterCatalog)\n- **Brenk**: Structural alerts for reactive\u002Ftoxic groups\n- **Lead-like**: MW 200-350, LogP -1 to 3\n- **Fragment-like (Ro3)**: MW \u003C= 300, LogP \u003C= 3, HBD \u003C= 3, HBA \u003C= 3\n- **bRo5**: Beyond Rule of Five for natural product-like space (MW 500-1000, LogP -2 to 10)\n- **SA score**: Synthetic accessibility (1 = easy, 10 = hard)\n\n## Tips\n\n- **Start broad, then narrow**: Use `generate_analogs.py` with `--strategy all` first, then filter with `filter.py`, then optimize survivors with `optimize.py`.\n- **Fragment merging is powerful**: If you have multiple fragment hits from an FBDD campaign, merging can produce leads that retain key interactions from both fragments.\n- **Combine SBDD with filtering**: Structure-based hits often need medicinal chemistry optimization. Pipe SBDD output through `filter.py` and `optimize.py`.\n- **Check synthetic accessibility**: Always include SA score in your analysis. A beautiful molecule is useless if it cannot be synthesized. Use `--sa-threshold 5.0` or lower for practical compounds.\n- **Deduplicate early**: All generation scripts deduplicate by canonical SMILES, but if you combine outputs from multiple runs, deduplicate again before downstream analysis.\n- **Property distributions matter**: Look at the property distribution summaries printed by each script. Bimodal distributions or outliers can indicate issues with the generation strategy.\n",{"name":5,"license":15,"category":54,"metadata":55,"description":7},"chemistry",{"skill-author":56},"Synthetic Sciences","main","4aa39efd1cdab0b4657ecee16c92a92011a5b10f","openscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub","https:\u002F\u002Fgithub.com\u002Ffadrienne","2026-10-28 00:43:09",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add fadrienne\u002FMyGitHub --skill denovo-design",{"tool":69,"command":70},"bunx","bunx skills add fadrienne\u002FMyGitHub --skill denovo-design",{"tool":72,"command":73},"pnpm","pnpm dlx skills add fadrienne\u002FMyGitHub --skill denovo-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002FSKILL.md",true,[77,83,87,91,95],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Ffilter.py","SCRIPT","脚本",16220,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002Fscripts\u002Ffilter.py",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fgenerate_analogs.py",20027,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002Fscripts\u002Fgenerate_analogs.py",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fgenerate_fragments.py",21339,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002Fscripts\u002Fgenerate_fragments.py",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fgenerate_sbdd.py",27853,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002Fscripts\u002Fgenerate_sbdd.py",{"path":96,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Foptimize.py",23755,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fdenovo-design\u002Fscripts\u002Foptimize.py",[100,129,155,186,213,240],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":109,"publishedAt":49},"01M7167B28PK20HP7R7ZED2DY0","statistical-power","Sample size calculation, power analysis, and effect size conversion for scientific studies. Use BEFORE data collection (a priori) to determine required N, or after (post-hoc) to compute achieved power. Covers parametric tests (t-test, ANOVA, chi-square, proportions, correlation, regression), simulation-based power for complex\u002Fclustered\u002Fnested designs, and power curves. Use this skill when someone asks 'how many samples do I need', 'what is my power', 'what effect size can I detect', or any variant. Pairs with \u002Fexperimental-design (choose design first, then compute power) and \u002Fstatistical-analysis (analyze data after collection).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-power\u002FSKILL.md",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[110,111,112,113,114,115,30,116,117,118,119,120,121,122,123,124,125,126,127,128],"power","statistical power","effect","scipy","regression","choose","uv","when","Bash","collection","analysis","calculation","ANOVA","conversion","analyze","t-test","chi-square","simulation","sample",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":49},"01M71677EBCM8EPCE9BZCK8505","statistical-analysis","Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-analysis\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[120,139,110,140,141,142,117,143,144,145,37,146,147,148,149,150,151,152,153,154],"statistical analysis","academic research","implementing","selection","you","reporting","data","tests","use","with","test","research","results","statsmodels","models","help",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":168,"publishedAt":49},"01M71673R93XAHFH81DBNVNG7H","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[161,164,165],{"categoryNo":162,"categoryName":163,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":166,"categoryName":167,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[169,170,171,172,173,174,175,176,177,178,118,179,180,43,181,182,183,184,144,185],"writing","scientific","scientific writing","Citations","deep","deep research","never","papers","journal","false","api","prisma","openrouter","Outlines","core skill","read","features",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":196,"publishedAt":49},"01M7166ZPKXBF4EBPHVTJPQBB1","scientific-visualization","Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib\u002Fseaborn\u002Fplotly with publication styles. For quick exploration use seaborn or plotly directly.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[192,195],{"categoryNo":193,"categoryName":194,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},[197,170,198,199,200,201,202,203,204,177,117,205,206,207,208,209,210,211,37,212],"visualization","scientific visualization","error","ready","quick","exploration","meta-skill","Meta","safe","plotly","annotations","formatting","Publication","figures","panel","submission",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":225,"publishedAt":49},"01M7166VXJWQSSC3RQZP60WBGR","research-code","Debug, profile, review, and restructure Python research and analysis code. Use when analysis scripts crash, produce wrong results, run too slowly, or need a correctness review. Covers: reading tracebacks and diagnosing root causes, hypothesis-driven debugging, reviewing code for common statistical\u002Fnumerical errors, profiling data pipelines, improving reproducibility (seeds, environments, determinism), and structuring analysis scripts for sharing. Distinct from \u002Fexploratory-data-analysis (which understands data) and \u002Fstatistical-analysis (which chooses and runs tests) — this skill focuses on the code itself.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fresearch-code\u002FSKILL.md",[219,222],{"categoryNo":220,"categoryName":221,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":223,"categoryName":224,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[226,227,150,228,229,230,231,116,232,117,118,120,233,234,235,236,237,238,184,239],"code","research code","which","memory","data-analysis","errors","debugging","common","review","data pipelines","run","scripts","line","write",{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":244,"licenseFileUrl":6,"sourceHtmlUrl":245,"categories":246,"keywords":253,"publishedAt":49},"01M7166CF5HSR7SVZYZFWTDX55","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fmarkdown-mermaid-writing\u002FSKILL.md",[247,250,251,252],{"categoryNo":248,"categoryName":249,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":162,"categoryName":163,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":166,"categoryName":167,"taxonomyType":26,"taxonomyTypeDesc":27},[169,254,255,256,257,258,197,259,260,117,118,120,261,262,263,264,265,266,170,184],"markdown mermaid writing","mermaid","markdown","community","diagrams","project","default","team","guides","text","documentation","references","diagram"]