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 Ssrf服务端请求伪造漏洞检测与利用。当目标存在 URL 参数、远程文件加载、Webhook、PDF 生成、URL 预览功能时使用。 Use when this capability is needed.
- tomevault-io Bundle Agent Exec
Execute a skill on a running aide agent instance. Use when the user wants to run a command or skill on an existing agent. Use when this capability is needed.
- tomevault-io Bundle Agent List
List running aide agent instances and their status. Use when the user asks about running agents, agent status, or wants to see what agents are active. Use when this capability is needed.
- tomevault-io Bundle Another Android
Control Android devices from AI agents using the Another MCP server. Use when asked to interact with, test, automate, or take screenshots of an Android device. Provides tools for touch input, text entry, button presses, screenshots, app launching, shell commands, and swipe gestures. Use when this capability is needed.
- tomevault-io Bundle Ctop
Inspect, monitor, and control running AI coding agent sessions across terminals via the `ctop` CLI. Use when the user asks "what agents are running", "what sessions do I have", "what is my master agent doing", "is my context about to compact", "how much have I spent", "kill the stuck session", "clean up ghost sessions", "what's idle", or anything that requires visibility across Claude Code / Codex / OpenCode sessions. Works on macOS, Linux, Windows. No network calls — reads local process state and session files. Use when this capability is needed.
- tomevault-io Bundle Structure
Extracts work items as Beads and bundles them into Convoys for Gastown multi-agent execution.
- tomevault-io Bundle Dsql
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL. Use when this capability is needed.
- tomevault-io Bundle Speak
Automatically announces plans, issues, and summaries out loud using TTS. Use this skill PROACTIVELY after completing major tasks like finalizing a plan, resolving an issue, or generating a summary. Each project gets a unique voice so users can identify which project is speaking from another room. Providers fallback in order (google, openai, elevenlabs, say) on rate limits. Use when this capability is needed.
- tomevault-io Bundle Team Lead
Agent Teams orchestrator for parallel Phase 4 workflows. Coordinates multiple Claude Code Agent Teams teammates for parallel story development, document review, and story creation. Make sure to use this skill whenever the user wants to run multiple stories in parallel, coordinate team development, delegate work across agents, or manage parallel implementation — even if they just say "let's work on multiple stories at once" or "can we parallelize this?" Also use for team coordination, work distribution, and managing concurrent development tasks. Use when this capability is needed.
- tomevault-io Bundle Mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation. Use when this capability is needed.
- tomevault-io Bundle Ame
Use when the user invokes /ame, says "ask me exhaustively", "interview me about this", "help me think through what I want to build", "ask me questions about my idea", or wants to clarify requirements before planning or coding. Runs a structured adaptive interview across all software quality dimensions in a single compiled message, writes a compressed spec to .ame/spec.md, and prepares context for /ema. REQUIRES agent/agentic mode with file-write capability (VS Code Agent mode, Google Antigravity, or Claude Code).
- tomevault-io Bundle Ema
Use when the user invokes /ema, says "enclose my analysis", "generate a plan", "create an implementation plan", "plan this out", "build a plan from the spec", or wants to turn a completed /ame spec into a structured, chunked execution plan. Reads .ame/spec.md, analyses layer dependencies, generates .ame/plan.md, and offers to execute each chunk on confirmation. REQUIRES agent/agentic mode with file-write capability (VS Code Agent mode, Google Antigravity, or Claude Code). Run /ame first.
- tomevault-io Bundle Linejs
Helps a coding agent build LINE bots / clients with the `@evex/linejs` library — JSR package, Deno-first, runs on Node/Bun too. Use when the user asks to write LINE bots, automate LINE accounts, work with LINE Thrift APIs, or wrap the AI "Agent I" feature. Use when this capability is needed.
- tomevault-io Bundle Sm
sm agent Use when this capability is needed.
- tomevault-io Bundle Hosizoraru Keios Keios
KeiOS MCP Skill
- tomevault-io Bundle Wiki
Work with team wiki (Confluence) - read/write documentation, create pages, maintain project docs. Use when user asks about team documentation, wiki pages, or needs to document something for the team. Requires Confluence MCP server. Use when this capability is needed.
- tomevault-io Bundle Xtuner Sync Supported Models
Synchronize xtuner's supported model documentation (docs/en/pretrain_sft/advanced_tutorial/model.md and docs/zh_cn/pretrain_sft/advanced_tutorial/model.md) with the actual Config classes defined under xtuner/v1/model/. Use when (1) new TransformerConfig, MoEConfig, or BaseComposeConfig subclasses are added, removed, or renamed in xtuner/v1/model/, (2) existing model configs change their inheritance hierarchy, scale, or HuggingFace counterpart, or (3) a code review or user request points out that model.md is out of sync with the codebase. Use when this capability is needed.
- tomevault-io Bundle Itechmeat LLM Code Bun
Bun
- tomevault-io Bundle Cortex Config
Interactively create a Cortex YAML config for multi-agent orchestration. Supports all three modes — workflow (DAG), mesh, and gossip. Use when this capability is needed.
- tomevault-io Bundle Mulch Record From Evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed `ml record` invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them. Use when this capability is needed.
- tomevault-io Bundle Python Regression Statistics
Expert guidance for regression analysis, statistical modeling, and outlier detection in Python using statsmodels, scikit-learn, scipy, and PyOD - includes model diagnostics, assumption checking, robust methods, and comprehensive outlier detection strategies Use when this capability is needed.
- tomevault-io Bundle Jat Start
Begin working on a JAT task. Registers agent identity, selects a task, searches memory, detects conflicts, declares files, emits IDE signals, and starts work. Use this at the beginning of every JAT session. Use when this capability is needed.
- tomevault-io Bundle Christopher Manning
Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab). Use this skill whenever you are discussing natural language processing, LLM architecture, AI research strategy, cognitive science, or the evolution of machine learning. Trigger this skill for questions about AGI timelines, academic vs. industry research trade-offs, linguistic structure in neural networks, modularity in AI design, or evaluating true intelligence versus mere memorization. Channel his pragmatic focus on domain science, adaptability, and competing on ideas rather than raw compute. Use when this capability is needed.
- tomevault-io Bundle Clawdhub
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI. Use when this capability is needed.
- tomevault-io Bundle Keiji AI Biodsa Biodsa
BioDSA Agent Execution Skill
- tomevault-io Bundle Typescript Magician
Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing `any` types, strict typing, type errors, `infer`, `extends`, conditional types, mapped types, template literal types, branded/opaque types, or utility types like `Partial`, `Record`, `ReturnType`, and `Awaited`. Use when this capability is needed.
- tomevault-io Bundle Claude Add
Add a single project-local Claude Code automation — sub-agent, skill, or hook — into .claude/. Use when the user runs /adam:claude-add, /claude-add, or asks to "add a sub-agent that...", "add a skill for X", "add a hook that runs Y on file write", "wire ruff into claude-code", "give me a code-reviewer agent for this project", or "create a new agent/skill/hook for the project". Distinct from /adam:setup (which suggests a batch); this adds exactly ONE artifact at a time, prompting for missing details via AskUserQuestion. Use when this capability is needed.
- tomevault-io Bundle Git Workflow
Git and GitHub workflow. Use for status, diffs, commits, syncing with remote, recovery, PRs, issues, and GitHub Actions. Use when this capability is needed.
- tomevault-io Bundle Vibepm
When a user wants to build an app using an AI coding agent (like Cursor, Windsurf, OpenClaw) but only has a vague idea, use this skill to transform their raw idea into a rock-solid technical architecture spec, database schema, and step-by-step implementation plan (Vibecoding Prep). Use when this capability is needed.
- tomevault-io Bundle Bhxch Jlens Jlens MCP En
JLens MCP Expert Navigation Guide (V1.1.1)
- tomevault-io Bundle Minibook
Connect your agent to a Minibook instance for project collaboration. Use when this capability is needed.
- tomevault-io Bundle Packs Sdk
Use when working with a prompt and set of tools that defines a specific skill this agent provides.
- tomevault-io Bundle Mettle
Use when an AI agent needs to verify its substrate, prove it is not human, or obtain a METTLE credential. Triggers on requests to 'verify yourself', 'prove you're AI', 'get METTLE badge', 'run METTLE', or any inverse Turing test scenario.
- tomevault-io Bundle Investigating Kilroy Runs
To diagnose active, stuck, or failed Kilroy Attractor runs, inspect run artifacts (`manifest.json`, `live.json`, `checkpoint.json`, `final.json`, `progress.ndjson`), resolve run IDs/log roots, identify model/provider routing, and isolate failure causes. Includes CXDB operations for launching/probing CXDB, opening the CXDB UI, and querying run context turns. This skill is useful when investigating run status, debugging retries/failures, explaining model usage, or inspecting CXDB-backed event history. Use when this capability is needed.
- tomevault-io Bundle Release Dbt MCP
Release a new version of dbt-mcp to PyPi Use when this capability is needed.
- tomevault-io Bundle Pywry Orientation
When to reach for PyWry MCP tools (native webview rendering, Plotly, TradingView, AgGrid, chat) instead of writing Flask/Streamlit/Dash/Electron code. Use at the start of any task involving interactive UI, dashboards, charts, or chat widgets driven from Python. 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 ssrf, agent-exec, agent-list. 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.