foryourhealth111-pixel/Vibe-Skills

这个仓库里有 258 个技能，GitHub 星标 ★ 3,314。

• skill-creatorGuide for creating effective skills. This skill should be used when users want t
• skill-installerInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub rep
• adaptyvCloud laboratory platform for automated protein testing and validation. Use when
• aeonThis skill should be used for time series machine learning tasks including class
• algorithmic-artCreating algorithmic art using p5.js with seeded randomness and interactive para
• alpha-vantageAccess real-time and historical stock market data, forex rates, cryptocurrency p
• architecture-patternsImplement proven backend architecture patterns including Clean Architecture, Hex
• astropyComprehensive Python library for astronomy and astrophysics. This skill should b
• autonomous-builderFull-stack software development agent for design, implementation, testing, and d
• bio-database-evidenceUnified biological database evidence owner. Use for gene annotation, variant cli
• biopythonPrimary retained Python toolkit for molecular biology sequence work. Preferred f
• brainstormingYou MUST use this before any creative work - creating features, building compone
• cancel-ralphCodex-compatible cancel command for Ralph loop state, preserving the original co
• chembl-databaseQuery ChEMBL bioactive molecules and drug discovery data. Search compounds by st
• citation-managementComprehensive citation management for academic research. Resolve bibliographic i
• claude-skillsClaude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a
• clinical-decision-supportGenerate professional clinical decision support (CDS) documents for pharmaceutic
• clinical-reportsWrite comprehensive clinical reports including case reports (CARE guidelines), d
• clinicaltrials-databaseQuery ClinicalTrials.gov via API v2. Search trials by condition, drug, location,
• clinpgx-databaseAccess ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug in
• code-reviewerDefault code-quality route for broad code review, PR review, maintainability, co
• coding-tutorPersonalized coding tutorials that build on your existing knowledge and use your
• commit-with-reflectionGit提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、
• comprehensive-research-agentEnsure thorough validation, error recovery, and transparent reasoning in researc
• content-research-writerAssists in writing high-quality content by conducting research, adding citations
• context-fundamentalsThis skill should be used when the user asks to "understand context", "explain c
• context-hunterDiscover codebase patterns, conventions, and unwritten rules before making chang
• create-planCreate a concise plan. Use when a user explicitly asks for a plan related to a c
• creating-data-visualizations|
• cs-foundationsMaster discrete mathematics, logic, formal proofs, and computational thinking. B
• daskParallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataF
• data-artistCreate beautiful data visualizations with mathematical elegance, color theory, a
• data-quality-frameworksImplement data quality validation with Great Expectations, dbt tests, and data c
• data-storytellingTransform data into compelling narratives using visualization, context, and pers
• datacommons-clientWork with Data Commons, a platform providing programmatic access to public stati
• datavisComprehensive data visualization toolkit for creating beautiful, mathematically
• denarioMultiagent AI system for scientific research assistance that automates research
• designing-experimentsDesign experiments and quasi-experiments before analysis. Use when choosing stud
• deslopRemove AI-generated code slop from a branch: unnecessary comments, redundant def
• detecting-data-anomalies|
• detecting-performance-regressions|
• dialecticMinimal compatibility wrapper for vibe Dialectic Mode (multi-perspective design
• digital-brainThis skill should be used when the user asks to "write a post", "check my voice"
• dnanexus-integrationDNAnexus cloud genomics platform. Build apps/applets, manage data (upload/downlo
• docUse when the task involves reading, creating, or editing `.docx` documents, espe
• docs-reviewReview documentation changes for compliance with the Metabase writing style guid
• docs-writeWrite documentation following Metabase's conversational, clear, and user-focused
• docxDocument toolkit (.docx). Create/edit documents, tracked changes, comments, form
• pdfPDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill fo
• pptxPresentation toolkit (.pptx). Create/edit slides, layouts, content, speaker note
• document-skillsUmbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the mo
• documentation-lookupUse when the user needs current library, framework, or API documentation and ver
• docxComprehensive document creation, editing, and analysis with support for tracked
• docx-comment-replyReply to comments (批注) in Word .docx/.doc files: extract comment context, draft
• edgartoolsPython library for accessing, analyzing, and extracting data from SEC EDGAR fili
• embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. U
• ena-databaseAccess European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw
• Error ResolverLegacy error-resolution reference archive retained for migration. Do not route u
• etetoolkitPhylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary ev
• evals-contextProvides context about the Roo Code evals system structure in this monorepo. Use
• evaluating-code-modelsEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benc
• evaluating-llms-harnessEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQ
• evaluating-machine-learning-models|
• explaining-machine-learning-models|
• exploratory-data-analysisPerform comprehensive exploratory data analysis on scientific data files across
• fda-databaseQuery openFDA API for drugs, devices, adverse events, recalls, regulatory submis
• figma-implement-designTranslate Figma nodes into production-ready code with 1:1 visual fidelity using
• file-organizerIntelligently organizes your files and folders across your computer by understan
• flashrag-evidenceLocal evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/
• fluidsimFramework for computational fluid dynamics simulations using Python. Use when ru
• fred-economic-dataQuery FRED (Federal Reserve Economic Data) API for 800,000+ economic time series
• G2 Legend ExpertExpert skill for G2 legend development - provides comprehensive knowledge about
• generate-imageGenerate or edit images using AI models (FLUX, Nano Banana 2). Use for general-p
• generating-test-reports|
• geo-databaseAccess NCBI GEO for gene expression/genomics data. Search/download microarray an
• geomasterComprehensive geospatial science skill covering remote sensing, GIS, spatial ana
• geopandasPython library for working with geospatial vector data including shapefiles, Geo
• get-available-resourcesThis skill should be used at the start of any computationally intensive scientif
• gh-address-commentsHelp address review/issue comments on the open GitHub PR for the current branch
• gh-fix-ciUse when a user asks to debug or fix failing GitHub PR checks that run in GitHub
• gradient-methodsProblem-solving strategies for gradient methods in optimization
• gtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindi
• hedgefundmonitorQuery the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fu
• histolabLightweight WSI tile extraction and preprocessing. Use for basic slide processin
• hive-mind-advancedAdvanced Hive Mind collective intelligence system for queen-led multi-agent coor
• hypothesis-generationStructured hypothesis formulation from observations. Use when you have experimen
• hypothesis-testing|
• imagegenUse when the user asks to generate or edit images via the OpenAI Image API (for
• imaging-data-commonsQuery and download public cancer imaging data from NCI Imaging Data Commons usin
• infographicsCreate professional infographics using Nano Banana Pro AI with smart iterative r
• iso-13485-certificationComprehensive toolkit for preparing ISO 13485 certification documentation for me
• jupyter-notebookUse when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`)
• knowledge-stewardAI工作经验知识库管理。适用于用户明确要求'保存到Obsidian'、'记录这个'、'save this insight'、'memo this'、'captu
• lamindbThis skill should be used when working with LaminDB, an open-source data framewo
• latchbio-integrationLatch platform for bioinformatics workflows. Build pipelines with Latch SDK, @wo
• latex-postersUse when creating or revising LaTeX research posters with beamerposter, tikzpost
• latex-submission-pipelineUse when building a LaTeX manuscript submission pipeline with templates, latexmk
• literature-reviewConduct comprehensive, systematic literature reviews using multiple academic dat
• local-vco-rolesCodex-local role pack for dialectic multi-agent reviews, designed to be compatib
• LQF_Machine_Learning_Expert_Guide|
• manuscript-as-codeTreat manuscripts as software: version control, reproducible builds, figure pipe
• markdown-mermaid-writing>
• market-research-reportsGenerate comprehensive market research reports and industry/competitive analysis
• markitdownConvert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX,
• matchmsSpectral similarity and compound identification for metabolomics. Use for compar
• mathUnified math capabilities - computation, solving, and explanation. I route to th
• math-model-selectorRoutes problems to appropriate mathematical frameworks using expert heuristics
• math-toolsDeterministic mathematical computation using SymPy. Use for ANY math operation r
• mathematical-logic-expertExpert in formal logic, model theory, computability, and foundations of mathemat
• matlabMATLAB and GNU Octave numerical computing for matrix operations, data analysis,
• matplotlibFoundational plotting library. Create line plots, scatter, bar, histograms, heat
• MCP IntegrationThis skill should be used when the user asks to "add MCP server", "integrate MCP
• medchemMedicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS
• metabolomics-workbench-databaseAccess NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolit
• metric-calculator|
• ml-data-leakage-guardDetects and prevents data leakage in machine learning and mathematical modeling.
• ml-pipeline-workflowBuild end-to-end MLOps pipelines from data preparation through model training, v
• netlify-deployDeploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when t
• networkxComprehensive toolkit for creating, analyzing, and visualizing complex networks
• neurokit2Comprehensive biosignal processing toolkit for analyzing physiological data incl
• neuropixels-analysisNeuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess,
• node-zombie-guardianUse when diagnosing stale or orphaned Node.js processes launched by VCO, auditin
• nowait-reasoning-optimizerImplements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use wh
• omero-integrationMicroscopy data management platform. Access images via Python, retrieve datasets
• openai-docsUse when the user asks how to build with OpenAI products or APIs and needs up-to
• openai-knowledgeCompatibility alias for OpenAI platform documentation guidance. Delegate to the
• openalex-databaseQuery and analyze scholarly literature using the OpenAlex database. This skill s
• paper-2-webUse when converting academic papers into dissemination assets such as Paper2Web
• pathmlComputational pathology toolkit for analyzing whole-slide images (WSI) and multi
• pdfUse when tasks involve reading, creating, or reviewing PDF files where rendering
• peer-reviewStructured manuscript/grant review with checklist-based evaluation. Use when wri
• performance-testingBenchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stre
• performing-causal-analysisEstimate causal effects from existing data. Use when fitting or interpreting DiD
• perplexity-searchPerform AI-powered web searches with real-time information using Perplexity mode
• planning-with-filesImplements Manus-style file-based planning for complex tasks. Creates task_plan.
• playwrightUse when the task requires automating a real browser from the terminal (navigati
• plotlyInteractive scientific and statistical data visualization library for Python. Us
• polarsFast in-memory DataFrame library for datasets that fit in RAM. Use when pandas i
• pptx-postersCreate research posters using HTML/CSS that can be exported to PDF or PPTX. Use
• preprocessing-data-with-automated-pipelines|
• prompt-lookupActivates when the user asks about AI prompts, needs prompt templates, wants to
• property-based-testing|
• propositional-logicProblem-solving strategies for propositional logic in mathematical logic
• providing-performance-optimization-advice|
• prowler-docs>
• pubmed-databaseDirect REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API
• pufferlibThis skill should be used when working with reinforcement learning tasks includi
• pydeseq2Differential gene expression analysis (Python DESeq2). Identify DE genes from bu
• pydicomPython library for working with DICOM (Digital Imaging and Communications in Med
• pyhealthComprehensive healthcare AI toolkit for developing, testing, and deploying machi
• pymatgenMaterials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, ban
• pymc-bayesian-modelingBayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational
• pymc-bayesian-modelingCompatibility alias for the descriptive PyMC skill name. Delegate to the canonic
• pymooMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts
• pyopenmsPython interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS
• pytorch-lightningDeep learning framework (PyTorch Lightning). Organize PyTorch code into Lightnin
• pyzoteroInteract with Zotero reference management libraries using the pyzotero Python cl
• ralph-loopCodex-compatible Ralph loop runner with dual engines (compat local state loop +
• rdkitCore cheminformatics toolkit for SMILES/SDF/InChI parsing, descriptors (MW, LogP
• receiving-code-reviewReview-feedback handling route for CodeRabbit, GitHub, PR, or human reviewer com
• report-generator高级报告生成专家，支持多格式输出、数据可视化和交互式报告生成。
• requesting-code-reviewPrepare and request a code review after implementation or before merge by assemb
• research-grantsWrite competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC.
• research-lookupLook up current research information using Perplexity's Sonar Pro Search or Sona
• rowanCloud-based quantum chemistry platform with Python API. Preferred for computatio
• scanpySingle-cell RNA-seq and retained scverse workflow owner. Load .h5ad/10X data, ma
• scholar-evaluationSystematically evaluate scholarly work using the ScholarEval framework, providin
• scholarly-publishingUse when planning an end-to-end scholarly publishing workflow, including manuscr
• scientific-brainstormingOpen-ended scientific ideation partner. Use for research gaps, mechanism explora
• scientific-critical-thinkingEvaluate scientific claims and evidence quality. Use for assessing experimental
• scientific-data-preprocessing⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSI
• scientific-reportingWrite research/technical reports with strong structure + figure standards. Suppo
• scientific-schematicsCreate publication-quality scientific diagrams using Nano Banana Pro AI with sma
• scientific-slidesBuild slide decks and presentations for research talks. Use this for making Powe
• scientific-visualizationCreate publication figures with matplotlib/seaborn/plotly. Multi-panel layouts,
• scientific-writingUse when writing or revising scientific manuscript prose: IMRAD sections, abstra
• scikit-bioBiological data toolkit. Sequence analysis, alignments, phylogenetic trees, dive
• scikit-learnMachine learning in Python with scikit-learn. Use when working with supervised l
• scikit-survivalComprehensive toolkit for survival analysis and time-to-event modeling in Python
• scraplingCLI-first web scraping & content extraction with optional MCP server. Use when y
• screenshotUse when the user explicitly asks for a desktop or system screenshot (full scree
• seabornStatistical visualization. Scatter, box, violin, heatmaps, pair plots, regressio
• security-best-practicesPerform language and framework specific security best-practice reviews and sugge
• security-ownership-mapAnalyze git repositories to build a security ownership topology (people-to-file)
• security-reviewerDedicated security-audit route for OWASP-style risks, secret leaks, auth flaws,
• security-threat-modelRepository-grounded threat modeling that enumerates trust boundaries, assets, at
• senior-computer-visionWorld-class computer vision skill for image/video processing, object detection,
• senior-data-scientistWorld-class data science skill for statistical modeling, experimentation, causal
• senior-ml-engineerWorld-class ML engineering skill for productionizing ML models, MLOps, and build
• senior-prompt-engineerWorld-class prompt engineering skill for LLM optimization, prompt patterns, stru
• sentryUse when the user asks to inspect Sentry issues or events, summarize recent prod
• shapModel interpretability and explainability using SHAP (SHapley Additive exPlanati
• similarity-search-patternsImplement efficient similarity search with vector databases. Use when building s
• simpyProcess-based discrete-event simulation framework in Python. Use this skill when
• skill-creatorGuide for creating effective skills. This skill should be used when users want t
• skill-lookupActivates when the user asks about Agent Skills, wants to find reusable AI capab
• skypilot-multi-cloud-orchestrationMulti-cloud orchestration for ML workloads with automatic cost optimization. Use
• slides-as-codeBuild research slides with text-first source (Slidev/Marp/Reveal/Quarto) and rep
• smart-file-writerIntelligent file write error handler: diagnoses permissions, disk space, path le
• sparse-autoencoder-trainingProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SA
• spec-kit-vibe-compatCompatibility router for /speckit.* workflows into /vibe-first Codex execution.
• speckit-analyzePerform cross-artifact consistency analysis across spec.md, plan.md,
• speckit-checklistGenerate custom quality checklists for validating requirements completeness
• speckit-clarifyStructured clarification workflow for underspecified requirements. Use
• speckit-constitutionCreate or update project governing principles and development guidelines.
• speckit-implementExecute all tasks from the task breakdown to build the feature. Use after
• speckit-planGenerate technical implementation plans from feature specifications.
• speckit-specifyCreate or update feature specifications from natural language descriptions.
• speckit-tasksBreak down implementation plans into actionable task lists. Use after
• speckit-taskstoissuesConvert tasks from tasks.md into GitHub issues. Use after task breakdown
• speechUse when the user asks for text-to-speech narration or voiceover, accessibility
• splitting-datasets|
• spreadsheetUse when tasks involve creating, editing, analyzing, or formatting spreadsheets
• stable-baselines3Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2
• statistical-analysisStatistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regr
• statistics-mathStatistics, probability, linear algebra, and mathematical foundations for data s
• statsmodelsStatistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis
• structured-content-storageEnforces structured, highly documented storage for code and data projects. Use w
• subagent-driven-developmentUse when executing implementation plans with independent tasks in the current se
• submission-checklistStage-based submission checklists for papers/reports: pre-submission, submission
• sympyUse this skill when working with symbolic mathematics in Python. This skill shou
• systematic-debuggingRoot-cause route for actual bugs, failing tests, build errors, crashes, stack tr
• tdd-guideTest-first development route for TDD, writing failing tests first, RED -> GREEN
• tensorboardVisualize training metrics, debug models with histograms, compare experiments, v
• theme-factoryToolkit for styling artifacts with a theme. These artifacts can be slides, docs,
• think-harder4-phase structured analysis wrapper for vibe pre-routing (compatible with claude
• tiledbvcfEfficient storage and retrieval of genomic variant data using TileDB. Scalable V
• timesfm-forecasting>
• torch-geometricGraph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GA
• torchdrugGraph-based drug discovery toolkit. Molecular property prediction (ADMET), prote
• transcribeTranscribe audio files to text with optional diarization and known-speaker hints
• transformer-lens-interpretabilityProvides guidance for mechanistic interpretability research using TransformerLen
• transformersThis skill should be used when working with pre-trained transformer models for n
• treatment-plansGenerate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format
• umap-learnUMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visual
• uniprot-databaseDirect REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping
• unslothExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80%
• usfiscaldataQuery the U.S. Treasury Fiscal Data API for federal financial data including nat
• uspto-databaseAccess USPTO APIs for patent/trademark searches, examination history (PEDS), ass
• ux-researcher-designerUX research and design toolkit for Senior UX Designer/Researcher including data-
• vaexUse this skill for processing and analyzing large tabular datasets (billions of
• venue-templatesUse when preparing manuscripts, conference papers, or academic posters that need
• vercel-deployDeploy applications and websites to Vercel. Use when the user requests deploymen
• verification-before-completionCompletion-evidence route used before claiming work is complete, fixed, passing,
• Verification & Quality AssuranceComprehensive truth scoring, code quality verification, and automatic rollback s
• video-studioUse when the user asks to create or edit videos end-to-end (script→video, auto-c
• visualization-best-practices|
• vscode-release-notes-writerGuidelines for writing and reviewing Insiders and Stable release notes for Visua
• webthinker-deep-researchDeep web research for VCO: multi-hop search+browse+extract with an auditable act
• weights-and-biasesTrack ML experiments with automatic logging, visualize training in real-time, op
• windows-hook-debuggingWindows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.
• writing-docsGuides for writing and editing Remotion documentation. Use when adding docs page
• writing-plansUse when you have a spec or requirements for a multi-step task, before touching
• xanHigh-performance CSV processing with xan CLI for large tabular datasets, streami
• xlsxSpreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze
• yeetUse only when the user explicitly asks to stage, commit, push, and open a GitHub
• zarr-pythonChunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS in
• vibeVibe Code Orchestrator (VCO) is a governed runtime entry that freezes requiremen