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 Blocklet PrCreate standardized Pull Requests for blocklet projects. Performs lint checks, unit tests, version updates, and creates PRs following PR templates. Use `/blocklet-pr` or say "help me submit a PR", "create pull request" to trigger. Use when this capability is needed.
- tomevault-io Bundle Wan Flf Video
Build WAN 2.2 First-Last-Frame video workflows — native dual hi-lo (required), and WanVideoWrapper VACE approaches Use when this capability is needed.
- tomevault-io Bundle Ship Safe Red Team
Run a multi-agent red team scan — 16 specialized security agents scan for 80+ attack classes including injection, auth bypass, SSRF, supply chain, Supabase RLS, MCP security, agentic AI, RAG poisoning, PII compliance, and more. Use when the user wants a deep security analysis beyond just secrets. Use when this capability is needed.
- tomevault-io Bundle Pytest Writer
专业的pytest测试用例编写助手，用于创建、编写和优化Python测试用例。当需要编写测试文件、创建测试代码、重构优化测试、调试失败测试、使用fixtures、参数化测试、断言技巧、测试覆盖率分析时使用此技能。 Use when this capability is needed.
- tomevault-io Bundle Gpt Researcher
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API, customizing research workflows, adding new retrievers, integrating MCP data sources, or troubleshooting research pipelines. Use when this capability is needed.
- tomevault-io Bundle Perigon Agent
Pointers for Copilot/agents to apply Perigon conventions Use when this capability is needed.
- tomevault-io Bundle Managing Agents
Configure and update AGENTS.md context file for AI agents. Use when setting up agent context or modifying agent instructions. Use when this capability is needed.
- tomevault-io Bundle With Custom Agent
Use when testing custom agent validation
- tomevault-io Bundle Bearbinary Jarvy Agent Doc Writer
Agent Doc Writer
- tomevault-io Bundle Benbjohnson Litestream Litestream
Litestream Agent Skill
- tomevault-io Bundle Ego Check
Run the ego agent to produce a process health assessment (coherent/strained/drifting) and forward-look for the next session. Use when this capability is needed.
- tomevault-io Bundle Atlas MCP
ATLAS MCP Server — Claude Code & Codex Integration — Use this skill when the user needs ATLAS capabilities exposed to Claude Code or Use when this capability is needed.
- tomevault-io Bundle Revalidation
Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when the user asks for agent revalidation, skill revalidation, config revalidation, or to check that AGENTS.md and .codex/skills match the codebase. Use when this capability is needed.
- tomevault-io Bundle Plan Export
Export a detailed phased implementation plan for a GitHub issue to a file, reading all applicable rules from .cursor/rules before planning Use when this capability is needed.
- tomevault-io Bundle Project Intake
Build a fast, accurate mental model of the eo-processor repo and the user’s task. Use when starting work, when requirements are unclear, or before making multi-file changes (Rust+PyO3+Python packaging/tests/docs). Use when this capability is needed.
- tomevault-io Bundle Project Spawn
Spawn a new Claude Code or Codex session in a project directory with context handoff. This skill should be used when discussion shifts to a different project/repo and the user wants to work on it in a dedicated session. Creates a handoff document with relevant context from the current conversation, then launches a new tmux session ready to continue. Use when this capability is needed.
- tomevault-io Bundle Prax Verification Loop
在提交、交付或大型改动后运行 Prax 风格的验证闭环。 Use when this capability is needed.
- tomevault-io Bundle Axiom IOS Ml
Use when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing speech-to-text. Covers CoreML conversion, MLTensor, model compression (quantization/palettization/pruning), stateful models, KV-cache, multi-function models, async prediction, SpeechAnalyzer, SpeechTranscriber.
- tomevault-io Bundle Add Parallel
Legacy MCP-based integration notes for Parallel AI. The Codex version of NanoClaw uses IPC actions instead of MCP. Use when this capability is needed.
- tomevault-io Bundle 3dsmax MCP
Tool choices, workflows, and MAXScript pitfalls for controlling 3ds Max via MCP. Use when this capability is needed.
- tomevault-io Bundle Agent Definition
Guide for creating and configuring AI agents in the DEVS platform. Use this when asked to create new agents, modify agent behavior, or work with agent YAML/JSON files. Use when this capability is needed.
- tomevault-io Bundle Codexview CLI
Read or compress an AI coding agent session log (Codex CLI, AgentWeb codex-team, Claude Code, OpenCode, or GitHub Copilot) into compact plaintext markdown using the `codexview-md` CLI. Keeps conversation text, plaintext reasoning, and subagent summaries (Claude Code `Agent` inline; OpenCode `task` via `--subagent`); drops tool outputs, diffs, encrypted reasoning. Use whenever the user wants to read, summarize, or compress an agent session log; mentions paths like `~/.codex/sessions/.../rollout-*.jsonl`, `~/.claude/projects/<repo>/<sessionId>.jsonl`, `.codex-team/runs/*/events.jsonl`, OpenCode at `~/.local/share/opencode/`, or GitHub Copilot `chatSessions/*.json`; wants a past agent conversation as compressed context for another LLM; or is debugging earlier runs. Also triggers on "summarize this Claude Code session", "export this OpenCode session", "summarize my Copilot session", or any time the user pipes/cats a multi-megabyte agent session file into the conversation. Use when this capability is needed.
- tomevault-io Bundle Cui Java Cdi
CDI and Quarkus development standards for CUI projects, including CDI aspects, container configuration, testing, and native optimization Use when this capability is needed.
- tomevault-io Bundle Cyanheads MCP TS Core MCP TS Core
When to Use
- tomevault-io Bundle Otel Semantic Conventions
OpenTelemetry Semantic Conventions expert. Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions. Covers the attribute registry, naming patterns, attribute placement, and versioning. For span names, span kinds, and span status codes, see the otel-instrumentation skill. Use when this capability is needed.
- tomevault-io Bundle Dbmcco Claude Agent Toolkit Rifts
Rifts (Workgraph Autopilot)
- tomevault-io Bundle Nano Banana
Generate and edit AI images via Google's Gemini image models (Nano Banana / Nano Banana Pro) using a direct REST call to the Generative Language API — no MCP server, no npm install. Ships one bundled Python CLI (`scripts/generate.py`, pure stdlib) that handles generate / edit / continue-edit / history / get against an on-disk session log. Use when the user asks to generate an image, edit a photo, build an infographic or diagram, or iterate on a prior generation. Use when this capability is needed.
- tomevault-io Bundle Ap Status
Summarize current project status from STATUS.md and related files. Use to quickly re-orient and decide the next step. Use when this capability is needed.
- tomevault-io Bundle Exboys Skilllite Agent Browser
Browser Automation with agent-browser
- tomevault-io Bundle Lsp Setup
LSP-enable a Python, TypeScript, or Rust repository for fast-agent development. Use when creating or refreshing agent cards with LSP function tools, configuring ty, typescript-language-server, or rust-analyzer integration, or scoping repo-local code navigation safely. Use when this capability is needed.
- tomevault-io Bundle Flexnetos Ripple Env Inference
AI Inference & Model Serving
- tomevault-io Bundle Agent Creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
- tomevault-io Bundle Eval Review
Review LLM-generated diff classifications for the diffview eval system. Use when the user invokes this skill or pastes yanked case data from evalreview (containing "# Diff Classification Review" header). Evaluates whether classifications accurately help code reviewers, provides pass/fail verdict with detailed critique. Use when this capability is needed.
- tomevault-io Bundle Capacitor
Capacitor cross-platform native runtime. Use for web to native. Use when this capability is needed.
- tomevault-io Bundle Cursor AI
Cursor AI editor with context-aware coding. Use for AI-assisted development. Use when this capability is needed.
- tomevault-io Bundle Hexagonal
Hexagonal architecture ports and adapters. Use for testable systems. 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 blocklet-pr, wan-flf-video, ship-safe-red-team. 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.