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.
-
tomevault-io Bundle LifelinesComplete survival analysis library in Python. Handles right-censored data, Kaplan-Meier curves, and Cox regression. Standard for clinical trial analysis and epidemiology. Use when this capability is needed.
- tomevault-io Bundle Daily Calibration Report
Automated daily health check of all model components for early warning of degradation and drift. Use when setting up daily reports, debugging performance issues, or reviewing model health after deployment. Covers PnL attribution, calibration metrics, signal decay, regime analysis, and alerting. Use when this capability is needed.
- tomevault-io Bundle Ida Agent Bridge
Use when writing ida-domain scripts, querying .i64 databases, or analyzing binaries. Provides short-connection REPL commands (disasm, xrefs, hexdump, pseudocode, rename) and arbitrary Python script execution piped via nc, with real-time file sync on rename/comment/patch.
- tomevault-io Bundle Adapter Antigravity
Use this skill when the user wants to enforce a WARD.md security policy inside Google Antigravity via its hook system. Triggers on requests to "secure my Antigravity agent", "block agy from doing X", "install WARD hooks in Antigravity", "make Antigravity respect my policy file", or any work involving the `weave-antigravity` command or the `agy` CLI. Also useful when reviewing a user's `~/.gemini/antigravity-cli/settings.json` for hook configuration, or when a user reports that an Antigravity agent is doing things they want stopped.
- tomevault-io Bundle X Search
AI-powered X/Twitter search agent for real-time trends, news, and social media insights. Costs 0.05 USDC per request on Base network. Use when this capability is needed.
- tomevault-io Bundle Pubmed Database
直接访问PubMed REST API。高级布尔/MeSH查询、E-utilities API、批量处理、引文管理。对于Python工作流，建议使用biopython (Bio.Entrez)。此技能适用于直接HTTP/REST操作或自定义API实现。 Use when this capability is needed.
- tomevault-io Bundle Fabric Tmdl
TMDL (Tabular Model Definition Language) authoring rules for Fabric and Power BI semantic models. Use when editing .tmdl files, adding measures or columns to a semantic model, defining relationships or calculation groups, working in a PBIP definition/ folder, configuring Direct Lake partitions, or debugging TMDL validation errors. Covers syntax (tabs not spaces, /// descriptions, single-quoting names), DAX measure patterns, row-level security roles, calendar groups, and common gotchas. Use when this capability is needed.
- tomevault-io Bundle Weather Check
Check current weather and forecast via a simple CLI script. Use when the user asks for current conditions, temperature, wind, or a quick forecast. Defaults to Torrejón de Ardoz and metric units. Use when this capability is needed.
- tomevault-io Bundle Computer Use Agent
AI-powered desktop automation using screenshots and vision-guided actions to control any desktop application Use when this capability is needed.
- tomevault-io Bundle Implement With Feedback
Execute a plan document into code through a disciplined, git-centric workflow — plan's phases refined into reviewable sprints up front, clean checkout, properly named branch, continuous WIP tracking, small meaningful commits. Use when a plan doc exists and the user is ready to build it. LOCAL-ONLY — never pushes during the implementation loop. Use when this capability is needed.
- tomevault-io Bundle Github MCP With Retry
Try reconnecting Github MCP until connection succeeds. Use when using Github MCP tools. Use when this capability is needed.
- tomevault-io Bundle Read Through Codebase
Create a comprehensive understanding of the codebase overview and functionality by reading through the codebase. Use when `docs/ai/*` does not exist. Use when this capability is needed.
- tomevault-io Bundle Chapter Planner Agent
将故事 canon 转成可执行的分章大纲。用于规划每一章的任务、场景顺序、信息揭示、冲突推进和节奏控制。 Use when this capability is needed.
- tomevault-io Bundle Glm CLI Runtime
Use when a Claude Code agent (especially the `glm-rescue` agent) needs to invoke the `glm-companion` CLI to delegate work to z.ai's GLM-5.1. Covers subcommand contracts, exit codes, env variable overrides, foreground vs background semantics, and the canonical failure-recovery sequence.
- tomevault-io Bundle Grepai MCP Tools
Reference for all GrepAI MCP tools. Use this skill to understand available MCP tools and their parameters. Use when this capability is needed.
- tomevault-io Bundle Test Execution
Run unit and integration tests, generate coverage reports, and view results. Use to validate code changes before committing or merging. Use when this capability is needed.
- tomevault-io Bundle Cursor Agent Supervisor
Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project Use when this capability is needed.
- tomevault-io Bundle Formax Approval UI Workflow
Use when adding or changing any Approval prompt/presenter.
- tomevault-io Bundle Idea Plugin Dev
Develop IntelliJ IDEA plugins with two templates, standard plugins and AI-integrated plugins. Use when creating new IntelliJ IDEA plugins, setting up plugin projects, implementing actions, settings pages, or integrating with IntelliAI Engine. Supports both simple plugins without AI dependencies and advanced plugins with AI provider selection and prompt template management. Use when this capability is needed.
- tomevault-io Bundle 0xlayerghost Solidity Agent Kit Git Workflow
Git Collaboration Standards
- tomevault-io Bundle Platform Friend Messaging System
Friends management, real-time messaging, WebSocket integration, and privacy controls. Use when this capability is needed.
- tomevault-io Bundle Blender Archetype Library
Apply reusable blender scene archetypes (wobble, flow, hard, bullet) with controlled layer behavior. Use when designing or refactoring LedFX blender scenes and masks for readable yet high-impact DJ visuals. Use when this capability is needed.
- tomevault-io Bundle Agent Definition Auditor
Audit and score an agent-definition markdown such as `AGENTS.md`, `CLAUDE.md`, `SKILL.md`, `SOUL.md`, `.cursorrules`, or a system prompt using a cold-reader rubric for clarity, consistency, context independence, and operating-model fit. Use when the user asks to review, score, critique, or audit an agent instruction file. Not for evaluating agent outputs, code quality, or rewriting the file itself. Use when this capability is needed.
Audited - tomevault-io Bundle Opus Prompting
Writing assistant that identifies artifact type (CLAUDE.md, skill, command, agent prompt) Use when this capability is needed.
- tomevault-io Bundle Repo Guidance Sync
Keep repository documentation, AGENTS.md, and contributor/test guidance aligned with code, design, and product changes. Use when Codex changes or reviews behavior that affects user-facing docs, developer runbooks, architecture notes, CLI/API references, setup instructions, design-system guidance, operational commands, E2E assumptions, or agent instructions; when a user asks to update docs after implementation; or when stale repo guidance could mislead future contributors. Use when this capability is needed.
- tomevault-io Bundle AI Orchestration Langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing Use when this capability is needed.
- tomevault-io Bundle Gologo13 Agent Skills Refactor Code
Refactor Code
- tomevault-io Bundle Device Screenshot
This skill should be used when capturing screenshots from connected devices during development. Use this when users request to capture device screens, take screenshots, analyze device UI, or inspect layout issues on iOS Simulator, physical iOS devices, or Android devices. Typical triggers include "capture screen", "take a screenshot of the device", "show me what's on the device", or "analyze the current screen". Use when this capability is needed.
- tomevault-io Bundle Plan Implement Dual Review
当用户提供项目计划文件并希望按计划落地代码时使用。该技能用于主agent编排两个subagent：subagent1读取计划并在新分支实现代码、随后依据 .ai_docs/rules/code_rules.md 自审并直接修复；subagent2再依据 .ai_docs/rules/code_review_structure_rules.md 做结构性审查并上报问题；主agent最终仅向用户汇报第三步的结构性问题。 Use when this capability is needed.
- tomevault-io Bundle Update Provider Models
Updates models and related metadata (context window, vision, tools, tags) for each LLM Router provider. Prefers provider APIs where available (e.g. OpenRouter), uses web search for official docs when no API exists. Writes to router.toml and reminds to sync config to DB. Use when the user asks to update provider models, refresh model lists, sync model information from OpenAI/Claude/Gemini/OpenRouter, or when asked to update 各 provider 的模型 / 同步模型列表 / 用搜索更新模型信息. Use when this capability is needed.
- tomevault-io Bundle Ml Integration Patterns
Machine learning integration patterns for rRNA-Phylo covering three use cases - rRNA sequence classification (supervised learning with sklearn/PyTorch), multi-tree consensus (ensemble methods), and generative tree synthesis (GNNs/transformers). Includes feature engineering, model training, hyperparameter tuning, model serving, versioning, and evaluation metrics for bioinformatics ML workflows. Use when this capability is needed.
- tomevault-io Bundle Romanmesicek Agent Skills Academic Research
Academic Research Skill
- tomevault-io Bundle Fastapi Model
Generate a SQLAlchemy model with matching Pydantic v2 schemas for FastAPI. Includes relationships, indexes, and the correct from_attributes configuration. Use when this capability is needed.
- tomevault-io Bundle Agent Arch System Design
Agent skill for arch-system-design - invoke with $agent-arch-system-design Use when this capability is needed.
- tomevault-io Bundle Agent Gossip Coordinator
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator Use when this capability is needed.
- tomevault-io Bundle Agent Memory Coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator Use when this capability is needed.
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 lifelines, daily-calibration-report, ida-agent-bridge. 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.