[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XFHYA74RYR8BVATR8DANGC":3,"skill-same:01M6XFHYA74RYR8BVATR8DANGC":86},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6XFHYA74RYR8BVATR8DANGC","molecular-optimization",null,"Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).","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\u002Fmolecular-optimization\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"molecular optimization","Optimization","molecular","numpy","molecular-design","lead-optimization","ADMET","evaluate","with","synthetic","paper","design","analyze","loop","verify","discovery","rdkit","pypi","pandas","generate","2026-11-10 10:12:30",false,"---\nname: molecular-optimization\ndescription: Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).\ncategory: chemistry\nlicense: MIT\nmetadata:\n    skill-author: Synthetic Sciences\nversion: 1.0.0\ntags: [drug-discovery, lead-optimization, molecular-design, ADMET]\ndependencies: [\"rdkit-pypi\", \"numpy\", \"pandas\"]\n---\n\n# Molecular Optimization\n\n## Overview\n\nLead optimization is the bottleneck of drug discovery — modifying a hit compound to improve potency, selectivity, and ADMET properties without breaking what already works. LLMs frequently generate invalid SMILES or propose modifications that don't appear in the actual structure.\n\nThis skill implements an iterative optimization protocol based on three peer-reviewed approaches:\n- **MT-Mol** (Kim et al., 2025): Multi-agent tool-based reasoning with verification — SOTA on 17\u002F23 PMO benchmark tasks\n- **DrugR** (Liu et al., 2026): Explicit liability reasoning before generation — 18× improvement over blind generation\n- **MultiMol** (Yu et al., 2025): Generate-then-rank with scaffold preservation — 82.3% multi-objective success rate\n\nThe core loop: **Analyze → Identify Liabilities → Generate Candidates → Verify → Evaluate & Rank → Iterate**.\n\n## When to Use This Skill\n\n- **Lead optimization**: Improve ADMET properties of a hit while preserving potency\n- **Scaffold hopping**: Find new scaffolds that maintain key pharmacophoric features\n- **Property-driven design**: Generate analogs targeting specific property improvements (lower LogP, reduce hERG, improve solubility)\n- **Multi-objective optimization**: Balance multiple properties simultaneously\n\n**Do NOT use this skill for:**\n- De novo design from scratch (use `denovo-design` instead)\n- Simple property prediction without optimization (use `admet-prediction`)\n- Docking or binding affinity estimation (use `molecular-docking`, `binding-affinity`)\n\n### Related Skills\n- **admet-prediction**: Compute ADMET properties (this skill uses it internally)\n- **admet-reasoning**: Interpretable ADMET analysis with mechanistic explanations\n- **smiles-validation**: Strict SMILES parsing and structural verification\n- **rdkit**: Core molecular operations\n- **medchem**: Medicinal chemistry filters and transformations\n\n## Installation\n\n### Required dependencies\n\n```bash\npip install rdkit-pypi numpy pandas\n```\n\n### Optional dependencies\n\n```bash\npip install PyTDC datamol\n```\n\n- **PyTDC**: Access to TDC ADMET predictors for enhanced property scoring\n- **datamol**: Convenient molecular manipulation utilities\n\n## Core Workflows\n\n### 1. Single-Molecule Optimization\n\nOptimize one molecule for improved properties:\n\n```bash\npython scripts\u002Foptimize.py \\\n    --smiles \"c1ccc(NC(=O)c2ccccc2Cl)cc1\" \\\n    --targets \"LogP\u003C3,hERG\u003C0.3,QED>0.5\" \\\n    --max-iterations 3 \\\n    --candidates 8 \\\n    --output results.json\n```\n\n### 2. Batch Optimization\n\nOptimize a CSV of molecules:\n\n```bash\npython scripts\u002Foptimize.py \\\n    --input leads.csv \\\n    --smiles-col SMILES \\\n    --targets \"LogP\u003C3,hERG\u003C0.3\" \\\n    --output optimized.csv\n```\n\n### 3. Verification Only\n\nVerify a proposed SMILES matches a claimed modification:\n\n```bash\npython scripts\u002Fverify_smiles.py \\\n    --original \"c1ccccc1\" \\\n    --proposed \"c1ccc(O)cc1\" \\\n    --claimed-modification \"Added hydroxyl group at para position\"\n```\n\n### 4. Candidate Comparison\n\nCompare multiple candidates against a reference:\n\n```bash\npython scripts\u002Fcompare_candidates.py \\\n    --reference \"c1ccc(NC(=O)c2ccccc2Cl)cc1\" \\\n    --candidates candidates.csv \\\n    --output comparison.html\n```\n\n## Script Reference\n\n| Script | Purpose | Key Outputs |\n|--------|---------|-------------|\n| `optimize.py` | Full iterative optimization loop | `results.json` with ranked candidates, descriptor deltas, reasoning |\n| `verify_smiles.py` | Validate SMILES and check claimed modifications | Pass\u002Ffail report with structural analysis |\n| `compare_candidates.py` | Side-by-side descriptor comparison | Comparison table (CSV\u002FHTML) with liability flags |\n\n## Optimization Protocol Detail\n\n### Step 1: ANALYZE\nCompute molecular descriptors: MW, LogP, TPSA, HBA, HBD, RotBonds, QED, aromatic rings, Murcko scaffold. Flag properties outside ADMET target thresholds.\n\n### Step 2: IDENTIFY LIABILITIES\nRank flagged properties by severity (hERG > DILI > CYP > solubility). For each, identify the structural feature causing the liability and propose a specific modification.\n\n### Step 3: GENERATE CANDIDATES\nApply proposed modifications via:\n- Bioisosteric replacement (e.g., phenyl → pyridine, amide → sulfonamide)\n- Functional group addition\u002Fremoval\n- Ring system modification\n- Chain length adjustment\n\nGenerate 4-8 candidates per iteration.\n\n### Step 4: VERIFY\nFor each candidate:\n1. `Chem.MolFromSmiles()` — discard if None\n2. Scaffold preservation: Murcko scaffold match\n3. Tanimoto similarity (ECFP4): flag if \u003C 0.4\n4. Structural verification: confirm claimed modification exists\n\n### Step 5: EVALUATE & RANK\nRecompute descriptors, build comparison table, score by net liability improvement (+1 per fix, -0.5 per new liability).\n\n### Step 6: ITERATE\nIf no improvement after 3 iterations, return best found with honest assessment.\n\n## ADMET Target Thresholds\n\n| Property | Target | Severity |\n|----------|--------|----------|\n| hERG inhibition | \u003C 0.3 | Critical |\n| DILI | \u003C 0.5 | Critical |\n| CYP inhibition | \u003C 0.5 | High |\n| LogP | 1.0 – 3.0 | Medium |\n| TPSA | 20 – 130 | Medium |\n| MW | 150 – 500 | Medium |\n| QED | > 0.5 | Low |\n| Solubility (LogS) | > -4.0 | Medium |\n","# Molecular Optimization\n\n## Overview\n\nLead optimization is the bottleneck of drug discovery — modifying a hit compound to improve potency, selectivity, and ADMET properties without breaking what already works. LLMs frequently generate invalid SMILES or propose modifications that don't appear in the actual structure.\n\nThis skill implements an iterative optimization protocol based on three peer-reviewed approaches:\n- **MT-Mol** (Kim et al., 2025): Multi-agent tool-based reasoning with verification — SOTA on 17\u002F23 PMO benchmark tasks\n- **DrugR** (Liu et al., 2026): Explicit liability reasoning before generation — 18× improvement over blind generation\n- **MultiMol** (Yu et al., 2025): Generate-then-rank with scaffold preservation — 82.3% multi-objective success rate\n\nThe core loop: **Analyze → Identify Liabilities → Generate Candidates → Verify → Evaluate & Rank → Iterate**.\n\n## When to Use This Skill\n\n- **Lead optimization**: Improve ADMET properties of a hit while preserving potency\n- **Scaffold hopping**: Find new scaffolds that maintain key pharmacophoric features\n- **Property-driven design**: Generate analogs targeting specific property improvements (lower LogP, reduce hERG, improve solubility)\n- **Multi-objective optimization**: Balance multiple properties simultaneously\n\n**Do NOT use this skill for:**\n- De novo design from scratch (use `denovo-design` instead)\n- Simple property prediction without optimization (use `admet-prediction`)\n- Docking or binding affinity estimation (use `molecular-docking`, `binding-affinity`)\n\n### Related Skills\n- **admet-prediction**: Compute ADMET properties (this skill uses it internally)\n- **admet-reasoning**: Interpretable ADMET analysis with mechanistic explanations\n- **smiles-validation**: Strict SMILES parsing and structural verification\n- **rdkit**: Core molecular operations\n- **medchem**: Medicinal chemistry filters and transformations\n\n## Installation\n\n### Required dependencies\n\n```bash\npip install rdkit-pypi numpy pandas\n```\n\n### Optional dependencies\n\n```bash\npip install PyTDC datamol\n```\n\n- **PyTDC**: Access to TDC ADMET predictors for enhanced property scoring\n- **datamol**: Convenient molecular manipulation utilities\n\n## Core Workflows\n\n### 1. Single-Molecule Optimization\n\nOptimize one molecule for improved properties:\n\n```bash\npython scripts\u002Foptimize.py \\\n    --smiles \"c1ccc(NC(=O)c2ccccc2Cl)cc1\" \\\n    --targets \"LogP\u003C3,hERG\u003C0.3,QED>0.5\" \\\n    --max-iterations 3 \\\n    --candidates 8 \\\n    --output results.json\n```\n\n### 2. Batch Optimization\n\nOptimize a CSV of molecules:\n\n```bash\npython scripts\u002Foptimize.py \\\n    --input leads.csv \\\n    --smiles-col SMILES \\\n    --targets \"LogP\u003C3,hERG\u003C0.3\" \\\n    --output optimized.csv\n```\n\n### 3. Verification Only\n\nVerify a proposed SMILES matches a claimed modification:\n\n```bash\npython scripts\u002Fverify_smiles.py \\\n    --original \"c1ccccc1\" \\\n    --proposed \"c1ccc(O)cc1\" \\\n    --claimed-modification \"Added hydroxyl group at para position\"\n```\n\n### 4. Candidate Comparison\n\nCompare multiple candidates against a reference:\n\n```bash\npython scripts\u002Fcompare_candidates.py \\\n    --reference \"c1ccc(NC(=O)c2ccccc2Cl)cc1\" \\\n    --candidates candidates.csv \\\n    --output comparison.html\n```\n\n## Script Reference\n\n| Script | Purpose | Key Outputs |\n|--------|---------|-------------|\n| `optimize.py` | Full iterative optimization loop | `results.json` with ranked candidates, descriptor deltas, reasoning |\n| `verify_smiles.py` | Validate SMILES and check claimed modifications | Pass\u002Ffail report with structural analysis |\n| `compare_candidates.py` | Side-by-side descriptor comparison | Comparison table (CSV\u002FHTML) with liability flags |\n\n## Optimization Protocol Detail\n\n### Step 1: ANALYZE\nCompute molecular descriptors: MW, LogP, TPSA, HBA, HBD, RotBonds, QED, aromatic rings, Murcko scaffold. Flag properties outside ADMET target thresholds.\n\n### Step 2: IDENTIFY LIABILITIES\nRank flagged properties by severity (hERG > DILI > CYP > solubility). For each, identify the structural feature causing the liability and propose a specific modification.\n\n### Step 3: GENERATE CANDIDATES\nApply proposed modifications via:\n- Bioisosteric replacement (e.g., phenyl → pyridine, amide → sulfonamide)\n- Functional group addition\u002Fremoval\n- Ring system modification\n- Chain length adjustment\n\nGenerate 4-8 candidates per iteration.\n\n### Step 4: VERIFY\nFor each candidate:\n1. `Chem.MolFromSmiles()` — discard if None\n2. Scaffold preservation: Murcko scaffold match\n3. Tanimoto similarity (ECFP4): flag if \u003C 0.4\n4. Structural verification: confirm claimed modification exists\n\n### Step 5: EVALUATE & RANK\nRecompute descriptors, build comparison table, score by net liability improvement (+1 per fix, -0.5 per new liability).\n\n### Step 6: ITERATE\nIf no improvement after 3 iterations, return best found with honest assessment.\n\n## ADMET Target Thresholds\n\n| Property | Target | Severity |\n|----------|--------|----------|\n| hERG inhibition | \u003C 0.3 | Critical |\n| DILI | \u003C 0.5 | Critical |\n| CYP inhibition | \u003C 0.5 | High |\n| LogP | 1.0 – 3.0 | Medium |\n| TPSA | 20 – 130 | Medium |\n| MW | 150 – 500 | Medium |\n| QED | > 0.5 | Low |\n| Solubility (LogS) | > -4.0 | Medium |\n",{"name":5,"tags":44,"license":15,"version":46,"category":47,"metadata":48,"description":7,"dependencies":50},[45,24,23,25],"drug-discovery","1.0.0","chemistry",{"skill-author":49},"Synthetic Sciences",[51,22,37],"rdkit-pypi","main","4aa39efd1cdab0b4657ecee16c92a92011a5b10f","openscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fmolecular-optimization","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub","https:\u002F\u002Fgithub.com\u002Ffadrienne","2026-10-28 00:43:09",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add fadrienne\u002FMyGitHub --skill molecular-optimization",{"tool":64,"command":65},"bunx","bunx skills add fadrienne\u002FMyGitHub --skill molecular-optimization",{"tool":67,"command":68},"pnpm","pnpm dlx skills add fadrienne\u002FMyGitHub --skill molecular-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fmolecular-optimization\u002FSKILL.md",true,[72,78,82],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fcompare_candidates.py","SCRIPT","脚本",5832,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fmolecular-optimization\u002Fscripts\u002Fcompare_candidates.py",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Foptimize.py",13747,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fmolecular-optimization\u002Fscripts\u002Foptimize.py",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fverify_smiles.py",10317,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fmolecular-optimization\u002Fscripts\u002Fverify_smiles.py",[87,117,143,177,204,231],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":39},"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",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[99,100,101,102,103,104,30,105,106,107,108,109,110,111,112,31,113,114,115,116],"power","statistical power","effect","scipy","regression","choose","uv","when","Bash","collection","analysis","calculation","ANOVA","conversion","t-test","chi-square","simulation","sample",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":126,"publishedAt":39},"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",[123],{"categoryNo":124,"categoryName":125,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000008","测试与质量",[109,127,99,128,129,130,106,131,132,133,134,135,136,27,137,138,139,140,141,142],"statistical analysis","academic research","implementing","selection","you","reporting","data","for","tests","use","test","research","results","statsmodels","models","help",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":158,"publishedAt":39},"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",[149,152,153],{"categoryNo":150,"categoryName":151,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":154,"categoryName":155,"taxonomyType":156,"taxonomyTypeDesc":157},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[159,160,161,162,163,164,165,166,167,168,107,169,170,171,172,173,174,175,132,176],"writing","scientific","scientific writing","Citations","deep","deep research","never","papers","journal","false","api","prisma","structure","openrouter","Outlines","core skill","read","features",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":187,"publishedAt":39},"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",[183,186],{"categoryNo":184,"categoryName":185,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[188,160,189,190,191,192,193,194,195,167,106,196,197,198,199,200,201,202,134,203],"visualization","scientific visualization","error","ready","quick","exploration","meta-skill","Meta","safe","plotly","annotations","formatting","Publication","figures","panel","submission",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":216,"publishedAt":39},"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",[210,213],{"categoryNo":211,"categoryName":212,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":214,"categoryName":215,"taxonomyType":156,"taxonomyTypeDesc":157},"01JBSEEDCAT000000000000030","开发工程师",[217,218,138,219,220,221,222,105,223,106,107,109,224,225,226,227,228,229,175,230],"code","research code","which","memory","data-analysis","errors","debugging","common","review","data pipelines","run","scripts","line","write",{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":235,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":244,"publishedAt":39},"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",[238,241,242,243],{"categoryNo":239,"categoryName":240,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":150,"categoryName":151,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":154,"categoryName":155,"taxonomyType":156,"taxonomyTypeDesc":157},[159,245,246,247,248,249,188,250,251,106,107,109,252,253,254,255,256,257,160,175],"markdown mermaid writing","mermaid","markdown","community","diagrams","project","default","team","guides","text","documentation","references","diagram"]