[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DARVB7XNWZ13WEB69SPYYD":3,"skill-same:01M6DARVB7XNWZ13WEB69SPYYD":120},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6DARVB7XNWZ13WEB69SPYYD","tooluniverse-image-analysis",null,"Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ\u002FCellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV\u002FTSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area\u002Fcircularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"tooluniverse image analysis","analysis","image","use","tests","confidence intervals","ANOVA","statistics","culture","datasets","ready","power","effect","regression","statistical analysis","data","analyzing","Optimization","csv","test","2026-11-10 10:12:30",false,"---\nname: tooluniverse-image-analysis\ndescription: Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ\u002FCellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV\u002FTSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area\u002Fcircularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.\n---\n\n# Microscopy Image Analysis and Quantitative Imaging Data\n\nProduction-ready skill for analyzing microscopy-derived measurement data using pandas, numpy, scipy, statsmodels, and scikit-image.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory.\n\n---\n\n## When to Use\n\n- Microscopy measurement data (area, circularity, intensity, cell counts) in CSV\u002FTSV\n- Colony morphometry, cell counting statistics, fluorescence quantification\n- Statistical comparisons (t-test, ANOVA, Dunnett's, Mann-Whitney, Cohen's d, power analysis)\n- Regression models (polynomial, spline) for dose-response or ratio data\n- Imaging software output (ImageJ, CellProfiler, QuPath)\n\n**NOT for**: Phylogenetics, RNA-seq DEG, single-cell scRNA-seq, statistics without imaging context.\n\n---\n\n## Core Principles\n\n1. **Data-first** - Load and inspect all CSV\u002FTSV before analysis\n2. **Question-driven** - Parse the exact statistic requested\n3. **Statistical rigor** - Effect sizes, multiple comparison corrections, model selection\n4. **Imaging-aware** - Understand ImageJ\u002FCellProfiler columns (Area, Circularity, Round, Intensity)\n5. **Precision** - Match expected answer format (integer, range, decimal places)\n\n---\n\n## Required Packages\n\n```python\nimport pandas as pd, numpy as np\nfrom scipy import stats\nfrom scipy.interpolate import BSpline, make_interp_spline\nimport statsmodels.api as sm\nfrom statsmodels.formula.api import ols\nfrom statsmodels.stats.power import TTestIndPower\nfrom patsy import dmatrix, bs, cr\n# Optional: skimage, cv2, tifffile\n```\n\n---\n\n## Workflow Decision Tree\n\n```\nPRE-QUANTIFIED DATA (CSV\u002FTSV) → Load → Parse question → Statistical analysis\nRAW IMAGES (TIFF, PNG) → Load → Segment → Measure → Analyze (see references\u002F)\n\nStatistical comparison:\n  Two groups → t-test or Mann-Whitney\n  Multiple groups vs control → Dunnett's test\n  Two factors → Two-way ANOVA\n  Effect size → Cohen's d + power analysis\n\nRegression:\n  Dose-response → Polynomial (quadratic\u002Fcubic)\n  Ratio optimization → Natural spline\n  Model comparison → R-squared, F-stat, AIC\u002FBIC\n```\n\n---\n\n## Analysis Workflow\n\n### Phase 0: Question Parsing and Data Discovery\n\n```python\nimport os, glob, pandas as pd\ncsv_files = glob.glob(os.path.join(\".\", '**', '*.csv'), recursive=True)\ndf = pd.read_csv(csv_files[0])\nprint(f\"Shape: {df.shape}, Columns: {list(df.columns)}\")\n```\n\nCommon columns: Area, Circularity, Round, Genotype\u002FStrain, Ratio, NeuN\u002FDAPI\u002FGFP.\n\n### Phase 1-3: Grouped Stats → Statistical Testing → Regression\n\nSee **references\u002Fstatistical_analysis.md** for complete implementations of grouped_summary, Dunnett's, Cohen's d, power analysis, polynomial\u002Fspline regression.\n\n---\n\n## Common BixBench Patterns\n\n| Pattern | Example Question | Workflow |\n|---------|-----------------|----------|\n| Colony Morphometry (bix-18) | \"Mean circularity of genotype with largest area?\" | Group by Genotype → max mean Area → report Circularity |\n| Cell Counting (bix-19) | \"Cohen's d for NeuN counts?\" | Filter → split by Condition → pooled SD → Cohen's d |\n| Multi-Group (bix-41) | \"How many ratios equivalent to control?\" | Dunnett's for Area AND Circularity → count non-significant in BOTH |\n| Regression (bix-54) | \"Peak frequency from natural spline?\" | Ratio→frequency → spline(df=4) → grid search peak → CI |\n\n---\n\n## Raw Image Processing\n\n```python\nfrom scripts.segment_cells import count_cells_in_image\nresult = count_cells_in_image(image_path=\"cells.tif\", channel=0, min_area=50)\n```\n\nSegmentation: Nuclei → Otsu+watershed; Colonies → Otsu; Phase contrast → adaptive threshold.\nSee **references\u002Fsegmentation.md**, **references\u002Fcell_counting.md**, **references\u002Fimage_processing.md**.\n\n---\n\n## R-to-Python Equivalents\n\n- R Dunnett (`multcomp::glht`) → `scipy.stats.dunnett()` (scipy >= 1.10)\n- R natural spline (`ns(x, df=4)`) → `patsy.cr(x, knots=...)` with explicit quantile knots\n- R `t.test()` → `scipy.stats.ttest_ind()`\n- R `aov()` → `statsmodels.formula.api.ols()` + `sm.stats.anova_lm()`\n\n## Answer Formatting\n\n- \"to the nearest thousand\": `int(round(val, -3))`\n- Cohen's d: 3 decimal places\n- Sample sizes: integer (ceiling)\n- Ratios: string \"5:1\"\n\n---\n\n## Evidence Grading\n\n| Grade | Criteria |\n|-------|----------|\n| **Strong** | p \u003C 0.001, d > 0.8, N >= 30\u002Fgroup |\n| **Moderate** | p \u003C 0.05, 0.5 \u003C= d \u003C 0.8 |\n| **Weak** | p \u003C 0.05, d \u003C 0.5 or low N |\n| **Insufficient** | p >= 0.05 or N \u003C 5\u002Fgroup |\n\nCircularity near 1.0 = round\u002Fhealthy; \u003C 0.5 = irregular. Post-hoc power \u003C 0.80 = underpowered.\n\n---\n\n## References\n\nScripts: `segment_cells.py`, `measure_fluorescence.py`, `batch_process.py`, `colony_morphometry.py`, `statistical_comparison.py`\nDocs: `statistical_analysis.md`, `cell_counting.md`, `segmentation.md`, `fluorescence_analysis.md`, `image_processing.md`\n","# Microscopy Image Analysis and Quantitative Imaging Data\n\nProduction-ready skill for analyzing microscopy-derived measurement data using pandas, numpy, scipy, statsmodels, and scikit-image.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory.\n\n---\n\n## When to Use\n\n- Microscopy measurement data (area, circularity, intensity, cell counts) in CSV\u002FTSV\n- Colony morphometry, cell counting statistics, fluorescence quantification\n- Statistical comparisons (t-test, ANOVA, Dunnett's, Mann-Whitney, Cohen's d, power analysis)\n- Regression models (polynomial, spline) for dose-response or ratio data\n- Imaging software output (ImageJ, CellProfiler, QuPath)\n\n**NOT for**: Phylogenetics, RNA-seq DEG, single-cell scRNA-seq, statistics without imaging context.\n\n---\n\n## Core Principles\n\n1. **Data-first** - Load and inspect all CSV\u002FTSV before analysis\n2. **Question-driven** - Parse the exact statistic requested\n3. **Statistical rigor** - Effect sizes, multiple comparison corrections, model selection\n4. **Imaging-aware** - Understand ImageJ\u002FCellProfiler columns (Area, Circularity, Round, Intensity)\n5. **Precision** - Match expected answer format (integer, range, decimal places)\n\n---\n\n## Required Packages\n\n```python\nimport pandas as pd, numpy as np\nfrom scipy import stats\nfrom scipy.interpolate import BSpline, make_interp_spline\nimport statsmodels.api as sm\nfrom statsmodels.formula.api import ols\nfrom statsmodels.stats.power import TTestIndPower\nfrom patsy import dmatrix, bs, cr\n# Optional: skimage, cv2, tifffile\n```\n\n---\n\n## Workflow Decision Tree\n\n```\nPRE-QUANTIFIED DATA (CSV\u002FTSV) → Load → Parse question → Statistical analysis\nRAW IMAGES (TIFF, PNG) → Load → Segment → Measure → Analyze (see references\u002F)\n\nStatistical comparison:\n  Two groups → t-test or Mann-Whitney\n  Multiple groups vs control → Dunnett's test\n  Two factors → Two-way ANOVA\n  Effect size → Cohen's d + power analysis\n\nRegression:\n  Dose-response → Polynomial (quadratic\u002Fcubic)\n  Ratio optimization → Natural spline\n  Model comparison → R-squared, F-stat, AIC\u002FBIC\n```\n\n---\n\n## Analysis Workflow\n\n### Phase 0: Question Parsing and Data Discovery\n\n```python\nimport os, glob, pandas as pd\ncsv_files = glob.glob(os.path.join(\".\", '**', '*.csv'), recursive=True)\ndf = pd.read_csv(csv_files[0])\nprint(f\"Shape: {df.shape}, Columns: {list(df.columns)}\")\n```\n\nCommon columns: Area, Circularity, Round, Genotype\u002FStrain, Ratio, NeuN\u002FDAPI\u002FGFP.\n\n### Phase 1-3: Grouped Stats → Statistical Testing → Regression\n\nSee **references\u002Fstatistical_analysis.md** for complete implementations of grouped_summary, Dunnett's, Cohen's d, power analysis, polynomial\u002Fspline regression.\n\n---\n\n## Common BixBench Patterns\n\n| Pattern | Example Question | Workflow |\n|---------|-----------------|----------|\n| Colony Morphometry (bix-18) | \"Mean circularity of genotype with largest area?\" | Group by Genotype → max mean Area → report Circularity |\n| Cell Counting (bix-19) | \"Cohen's d for NeuN counts?\" | Filter → split by Condition → pooled SD → Cohen's d |\n| Multi-Group (bix-41) | \"How many ratios equivalent to control?\" | Dunnett's for Area AND Circularity → count non-significant in BOTH |\n| Regression (bix-54) | \"Peak frequency from natural spline?\" | Ratio→frequency → spline(df=4) → grid search peak → CI |\n\n---\n\n## Raw Image Processing\n\n```python\nfrom scripts.segment_cells import count_cells_in_image\nresult = count_cells_in_image(image_path=\"cells.tif\", channel=0, min_area=50)\n```\n\nSegmentation: Nuclei → Otsu+watershed; Colonies → Otsu; Phase contrast → adaptive threshold.\nSee **references\u002Fsegmentation.md**, **references\u002Fcell_counting.md**, **references\u002Fimage_processing.md**.\n\n---\n\n## R-to-Python Equivalents\n\n- R Dunnett (`multcomp::glht`) → `scipy.stats.dunnett()` (scipy >= 1.10)\n- R natural spline (`ns(x, df=4)`) → `patsy.cr(x, knots=...)` with explicit quantile knots\n- R `t.test()` → `scipy.stats.ttest_ind()`\n- R `aov()` → `statsmodels.formula.api.ols()` + `sm.stats.anova_lm()`\n\n## Answer Formatting\n\n- \"to the nearest thousand\": `int(round(val, -3))`\n- Cohen's d: 3 decimal places\n- Sample sizes: integer (ceiling)\n- Ratios: string \"5:1\"\n\n---\n\n## Evidence Grading\n\n| Grade | Criteria |\n|-------|----------|\n| **Strong** | p \u003C 0.001, d > 0.8, N >= 30\u002Fgroup |\n| **Moderate** | p \u003C 0.05, 0.5 \u003C= d \u003C 0.8 |\n| **Weak** | p \u003C 0.05, d \u003C 0.5 or low N |\n| **Insufficient** | p >= 0.05 or N \u003C 5\u002Fgroup |\n\nCircularity near 1.0 = round\u002Fhealthy; \u003C 0.5 = irregular. Post-hoc power \u003C 0.80 = underpowered.\n\n---\n\n## References\n\nScripts: `segment_cells.py`, `measure_fluorescence.py`, `batch_process.py`, `colony_morphometry.py`, `statistical_comparison.py`\nDocs: `statistical_analysis.md`, `cell_counting.md`, `segmentation.md`, `fluorescence_analysis.md`, `image_processing.md`\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-image-analysis",{"tool":64,"command":65},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-image-analysis",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-image-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002FSKILL.md",true,[72,78,82,86,90,94,98,104,108,112,116],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcell_counting.md","REFERENCE","参考文档",15226,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Fcell_counting.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Ffluorescence_analysis.md",14692,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Ffluorescence_analysis.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fimage_processing.md",11945,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Fimage_processing.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fsegmentation.md",17995,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Fsegmentation.md",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fstatistical_analysis.md",21938,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Fstatistical_analysis.md",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Ftroubleshooting.md",10058,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Freferences\u002Ftroubleshooting.md",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fbatch_process.py","SCRIPT","脚本",8869,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Fscripts\u002Fbatch_process.py",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fmeasure_fluorescence.py",7217,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Fscripts\u002Fmeasure_fluorescence.py",{"path":109,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fsegment_cells.py",7588,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Fscripts\u002Fsegment_cells.py",{"path":113,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":114,"sourceHtmlUrl":115},"SKILL_OLD.md",41056,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002FSKILL_OLD.md",{"path":117,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":118,"sourceHtmlUrl":119},"test_image_analysis.py",16610,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-image-analysis\u002Ftest_image_analysis.py",[121,142,171,196,210,225],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":47},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[128,129,130,131,132,133,134,135,136,30,137,138,139,140,141],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":151,"publishedAt":47},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[148],{"categoryNo":149,"categoryName":150,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[152,153,154,155,156,157,158,159,160,161,162,163,164,165,30,166,167,168,169,170],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":181,"publishedAt":47},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[177,180],{"categoryNo":178,"categoryName":179,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[182,183,184,185,186,187,188,189,190,191,153,192,193,194,195],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":47},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[198,203,204,205,206,207,208,209],"setup","report","project","installation","project setup","issues","state",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":47},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[216],{"categoryNo":149,"categoryName":150,"taxonomyType":21,"taxonomyTypeDesc":22},[212,218,133,219,37,220,30,221,222,223,224],"start issue","issue","work on issue","user","work","work on","development",{"skillNo":226,"name":203,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":47},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[203,205,168,231,207,232],"files","interactive"]