AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
majiayu000 Bundle Tcr Repertoire Analysis Agent 2AI-powered T-cell receptor repertoire analysis for cancer diagnosis, immunotherapy response prediction, and therapeutic TCR selection using deep learning and multi-layer ML approaches.
567 - majiayu000 Bundle Threejs 5
Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.
567 - majiayu000 Bundle Repo Applying Maker Checker Fixer 2
Three-stage content quality workflow pattern (Maker creates, Checker validates, Fixer remediates). Use when working with content quality workflows, validation processes, audit reports, or implementing maker/checker/fixer agent roles.
567 - majiayu000 Bundle Image Generation 4
Generate images from text prompts using Ollama.
567 - majiayu000 Bundle Vector Store 2
Transient vector store service for fast similarity search (FAISS)
567 - majiayu000 Bundle Fetcher 3
Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or provides URLs needing retrieval.
567 - majiayu000 Bundle Research 57
Document codebase as-is with thoughts directory for historical context
567 - majiayu000 Bundle The Oracle 3
Use when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or architectural questions requiring multi-source investigation. Combines codebase exploration and web searches, synthesizing findings into actionable answers.
567 - majiayu000 Bundle Commit Review 3
Reviews changed code for issues, DRY opportunities, naming clarity, and test coverage using a sub-agent. Use as the first step before testing.
567 - majiayu000 Bundle Nette Architecture 2
Provides Nette application architecture guidelines. Use when working with presenters, modules, directory structure, Core vs Model decisions, or Nette MVC patterns.
567 - majiayu000 Bundle Orca Architecture 2
This skill should be used when the user asks about "Orca architecture", "knowledge graph design", "MCP server structure", "nugget storage", "telemetry design", "Orca refactoring", or is planning changes to Orca components. Provides decision capture workflows, bounded exploration patterns, and architecture discussion guidance.
567 - majiayu000 Bundle Obsidian 10
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
567 - majiayu000 Bundle Frankx Daily Execution System 2
Helps execute Frank's daily workflow using the FRANKX-SUPERINTELLIGENT-AGENT-SYSTEM, Starlight Intelligence, and productivity methodologies for conscious creation
567 - majiayu000 Bundle Review Sonnet 2
Fast code/plan review for quality, security, and tests. Use for quick reviews before deeper analysis.
567 - majiayu000 Bundle Tribunal 4
The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes {{CMD:tribunal}}. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry. Costs on the order of millions of tokens; proceeds only after the user acknowledges the estimate; never a required gate; nothing filed or sent without explicit authorization.
567 - majiayu000 Bundle Pylabrobot 3
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.
567 - majiayu000 Bundle Autopilot 9
Full autonomous execution from idea to working code
567 - majiayu000 Bundle Validate Agent 2
Validation agent that validates plan tech choices against current best practices
567 - majiayu000 Bundle AI Sdk Core 3
Vercel AI SDK v5 for backend AI (text generation, structured output, tools, agents). Multi-provider. Use for server-side AI or encountering AI_APICallError, AI_NoObjectGeneratedError, streaming failures.
567 - majiayu000 Bundle Prompt Engineering 25
Prompt engineering knowledge base for designing prompts, evaluating them, reviewing AI-facing assets, and improving safety, structure, and reliability.
567 - majiayu000 Bundle Chip Clonal Hematopoiesis Agent 2
AI-powered clonal hematopoiesis of indeterminate potential (CHIP) detection, risk stratification, and cardiovascular/malignancy risk prediction using genomic and clinical data.
567 - majiayu000 Bundle Hemoglobinopathy Analysis Agent 2
AI-powered analysis of hemoglobin disorders including sickle cell disease, thalassemias, and variant hemoglobins using HPLC, electrophoresis, and molecular data.
567 - majiayu000 Bundle Skill Fix Logs 2
[Skill Management] Fix the agent skill based on `logs.txt` file.
567 - majiayu000 Bundle Cosmic Database 2
Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication.
567 - majiayu000 Bundle Agent Ops Install 2
Install AgentOps into a new or existing project. Handles .agent/ setup and .github/ merging.
567 - majiayu000 Bundle Testflight 3
Build and upload visionOS/iOS/macOS apps to TestFlight via App Store Connect API. Handles archive, export, and upload workflow with rsync bug workaround. Use when deploying to TestFlight or App Store Connect.
567 - majiayu000 Bundle Writing Openstudio Model Measures 2
Write OpenStudio ModelMeasures (Ruby scripts that modify .osm files) for building energy models. Use when creating measures, writing measure.rb files, or modifying OpenStudio models programmatically. Targets OpenStudio 3.9 with best practices from NREL documentation.
567 - majiayu000 Bundle Multi LLM 2
Route tasks to optimal LLM provider (Gemini, Codex, Copilot, Claude)
567 - majiayu000 Bundle Normalize 4
Comprehensive text normalization for handling PDF and Unicode encoding issues.
567 - majiayu000 Bundle Web Games 3
Web browser game development principles. Framework selection, WebGPU, optimization, PWA.
567 - majiayu000 Bundle Add Gmail Tool 2
Add Gmail as an MCP tool (read, search, send, label, draft) using OneCLI-managed OAuth. The agent gets Gmail tools in every enabled group; OneCLI injects real tokens at request time so no raw credentials are ever in the container or on disk in usable form.
567 - majiayu000 Bundle 2d Games 2
2D game development principles. Sprites, tilemaps, physics, camera.
567 - majiayu000 Bundle 3d Games 2
3D game development principles. Rendering, shaders, physics, cameras.
567 - majiayu000 Bundle Jira Pm 3
Jira project management and issue tracking integration
567 - majiayu000 Bundle Power Mode 2
Multi-agent orchestration system using Claude Code's native background agents (2.0.64+) for true parallel collaboration. Enables shared context, sync barriers between phases, and coordinator oversight. Use for complex tasks benefiting from parallel execution (epics, large refactors, multi-phase features). Do NOT use for simple tasks or sequential workflows - the coordination overhead isn't justified.
567 - majiayu000 Bundle Rp CLI 3
Repo Prompt CLI - proxy MCP client for AI agents to access Repo Prompt's context engineering tools via bash. Build prompts, search code, manage file selections, chat with AI, and export context without MCP configuration.
567
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include tcr-repertoire-analysis-agent, threejs, repo-applying-maker-checker-fixer. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.