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 Rust LintsCanonical [workspace.lints] and clippy.toml configuration for AI-resilient Rust. Use when reviewing or modifying the workspace Cargo.toml lint section, adding a new crate, or auditing why a class of LLM-generated bug went undetected by clippy. Use when this capability is needed.
-
tomevault-io Bundle LgtmQuery observability backends (Loki logs, Prometheus/Mimir metrics, Tempo traces) to investigate production issues, debug errors, check service health, and analyze system behavior. Use this skill whenever the user asks about logs, metrics, traces, error rates, latency, or debugging anything in production — even if they don't say "lgtm" or "observability" explicitly. Use when this capability is needed.
-
tomevault-io Bundle NarsilUse narsil-mcp code intelligence tools effectively. Use when searching code, finding symbols, analyzing call graphs, scanning for security vulnerabilities, exploring dependencies, or performing static analysis on indexed repositories. Use when this capability is needed.
-
tomevault-io Bundle Agent BuilderUse when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices for building specialized AI assistants.
-
tomevault-io Bundle Prisma CLIPrisma CLI commands reference covering all available commands, options, and usage patterns. Use when running Prisma CLI commands, setting up projects, generating client, running migrations, managing databases, or starting Prisma's MCP server. Triggers on "prisma init", "prisma generate", "prisma migrate", "prisma db", "prisma studio", "prisma mcp". Use when this capability is needed.
-
tomevault-io Bundle Ax RunnersUse when modifying agent runner implementations — pi-session (pi-coding-agent), claude-code (Agent SDK), LLM transport selection, MCP tool wiring, or stream handling in src/agent/runners/
-
tomevault-io Bundle EdgemailUse this API when an agent needs to inspect a temporary inbox on `smtp.idont.date` over HTTP.
-
tomevault-io Bundle Tune Temperature PolicyUse when changing any field in `pkg/temperature/Config` (`DecayRate`, `AccessBoost`, `ColdThreshold`, `NotifyThreshold`, `TickInterval`) or modifying `decayFactor` / `Score` / cold-node notification logic — symptoms include "tune the decay rate", "make notifications less noisy", "change the cold cutoff", "adjust the temperature window", "raise/lower the boost". Prevents silent docs drift in `skills/remind/SKILL.md` (mental-model numerics) and `skills/memorize/references/lifecycle.md` (summarization workflow triggered by the notification).
-
tomevault-io Bundle Capcap Agent ToolsUse this skill whenever an agent needs to autonomously edit a user-provided image, capture screenshots, enumerate windows, annotate images, or produce visual evidence using capcap's headless `capcap agent` commands. Trigger for requests about editing an attached image, agent screenshots, headless screenshot workflows, visual bug reports, marking UI pixels, drawing arrows/boxes/text on screenshots, or creating final result images without human GUI interaction.
-
tomevault-io Bundle Groq APIGroq API syntax — Whisper transcription, audio processing, and prompt-based jargon guidance. Use when calling Groq endpoints or transcribing audio. Use when this capability is needed.
-
tomevault-io Bundle Evalyn CalibrateUse when LLM judges need calibration, evaluation metrics seem misaligned with expectations, or annotation and judge tuning is needed
-
tomevault-io Bundle BugfixforeverState-of-the-art procedure for fixing bugs in software projects. Use this skill when a bug has been detected or declared by the user, agent, or another skill (not during early-stage work in progress). Enforces a disciplined test-driven approach - understand, reproduce experimentally, write failing tests, fix the code, and clean up. Use when this capability is needed.
-
tomevault-io Bundle MagiMulti-perspective deliberation agent (Logos/Pathos/Sophia) for architecture arbitration, trade-off resolution, Go/No-Go verdicts, and strategic decisions. Does not write code. Don't use for architecture design (Atlas), requirement gathering (Accord), code comparison (Arena), or implementation (Builder). Use when this capability is needed.
-
tomevault-io Bundle ReelTerminal recording and CLI demo video generation. Declarative CLI demo GIF/video creation using VHS, terminalizer, and asciinema. Use when terminal session recording, CLI demos, or README GIF generation is needed. Use when this capability is needed.
-
tomevault-io Bundle Agent BrowserBrowser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps. Use when this capability is needed.
-
tomevault-io Bundle MlscpParse and generate MLSCP (Micro LLM Swarm Communication Protocol) commands. Use when communicating with other agents efficiently, parsing compressed commands, or generating token-efficient instructions. Reduces token usage by 70-80% compared to natural language. Use when this capability is needed.
-
tomevault-io Bundle SnitchmdConverts any web page URL to LLM-ready Markdown via a headless browser. Bypasses passive anti-bot fingerprinting and JavaScript rendering, then strips navigation, footers, scripts, and cookie banners. Triggered by URLs that need the actual readable page content.
-
tomevault-io Bundle Lm DelugePython library for LLM API requests with unified interface across providers (OpenAI, Anthropic, Google, etc.). Use when writing code that calls LLMs, creates tools/agents, batch processes prompts, or needs rate limiting. Triggers on lm-deluge, lm_deluge, LLMClient, or multi-provider LLM code tasks. Use when this capability is needed.
-
tomevault-io Bundle Reference CatalogMaintain and validate SD.Next model reference catalogs in data/reference*.json, including schema consistency, deduplication, link checks, and thumbnail alignment. Use when this capability is needed.
-
tomevault-io Bundle BuckleSet up or extend a "Hub-and-Spoke" agent documentation system in a repository — AGENTS.md as a table of contents pointing to spoke files (docs, agent instructions, runbooks, anything). Use this skill whenever the user wants to create or update AGENTS.md, add or restructure agent rules, migrate inline rules out of CLAUDE.md / .cursorrules into a shared hub, write a doc or runbook that agents should follow, or reconcile tool-specific files (CLAUDE.md, .cursorrules, .windsurfrules, .clinerules, .github/copilot-instructions.md, GEMINI.md) so they don't drift. Trigger this even when the user does not say "hub-and-spoke" — phrases like "rules for agents in this repo", "make Claude follow X in the API folder", "I'm starting to use Cursor too", or "give me a workflow for scaffolding a route" all qualify. Use when this capability is needed.
-
tomevault-io Bundle Scienceworld Ambiguous Action ResolutionUse when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. This skill resolves the disambiguation by selecting the lowest available number (typically 0) to proceed, ensuring task progression when multiple identical object instances exist and the system cannot automatically determine which instance to act upon.
-
tomevault-io Bundle Process Github IssueExtract ZK circuit bugs from a GitHub issue or pull request and add them to the zkbugs dataset. Creates branch, scaffolds directories, fills configs, finds similar bugs. Use when this capability is needed.
-
tomevault-io Bundle Bedframe Your Skill NameReplace with a description of what this skill does and when an agent should use it. Use when this capability is needed.
-
tomevault-io Skill AgentmailAPI-first email platform designed for AI agents. Create and manage dedicated email inboxes, send and receive emails programmatically, and handle email-based workflows with webhooks and real-time events. Use when you need to set up agent email identity, send emails from agents, handle incoming email workflows, or replace traditional email providers like Gmail with agent-friendly infrastructure. Use when this capability is needed.
-
tomevault-io Skill AgentyardThis skill enables agents to collaborate on AgentYard (agentyard.dev) - the world's first agent-only codebase. Use this skill when an agent wants to build, contribute, or collaborate on the AgentYard repository. Provides registration workflow, secure token storage, and GitHub operations (branches, PRs, issues, discussions). Triggers on "agentyard", "agent-only codebase", "collaborate with other agents", or requests to build on a shared agent repository. Use when this capability is needed.
Audited -
tomevault-io Bundle Search Suitable Public APISearch the curated Agenvoy public API list for an API that fits the current user need or skill context, then chain into the `api-tool-add` skill to register it under `~/.config/agenvoy/tools/api/`. Triggers when the agent lacks a tool for a data lookup (weather, currency, geocoding, dictionary, etc.), when the user says "找個 API"/"有沒有 XXX 的 API"/"我需要查 XXX 但你沒工具"/"add a public API for this", or when an upstream skill needs an external data source that is not yet wired. Use when this capability is needed.
-
tomevault-io Bundle Petrovc AI Agent Kit NodeNode.js (Backend) Skill
-
tomevault-io Bundle Petrovc AI Agent Kit RustRust Skill
-
tomevault-io Bundle Dev BrowserBrowser automation via MCP tools. ALWAYS use these tools for ANY web task - navigating sites, clicking, typing, filling forms, taking screenshots, or extracting data. This is the ONLY way to control the browser. Use when this capability is needed.
-
tomevault-io Bundle Aptos AgentInteract with Aptos blockchain - check balances, transfer APT, swap tokens, stake, and execute Move view functions. Features game-theoretic decision analysis with Nash equilibrium detection. All transactions require explicit approval. Use when this capability is needed.
-
tomevault-io Bundle AutopoiesisSelf-producing skill system combining ruler enforcement with skill self-evolution. Implements trifurcation-first imperative via nbb sexp invocation for idempotent agent instruction. Use when this capability is needed.
-
tomevault-io Bundle Cost ReportQuery and report on API usage costs across LLM, embedding, and tool providers Use when this capability is needed.
-
tomevault-io Bundle Prompt WriterWrite maximally terse agent prompts from scratch. Use when creating new agent specs, command prompts, or instruction sets. Teaches structure-first composition with compression-by-default patterns. Use when this capability is needed.
-
tomevault-io Bundle Create Pass Through ApproximationModel a library method's taint propagation as a passThrough approximation config. Use for a dropped external method whose propagation is simple copying Use when this capability is needed.
-
tomevault-io Bundle AgentbaseMulti-agent orchestration system for coordinating parallel development work. Use when managing complex multi-workstream development, triaging failures, or coordinating parallel agent work. Use when this capability is needed.
Audited -
tomevault-io Bundle AnvilTerminal UI construction, CLI development, and dev-tool integration (linter/test-runner/build-tool wiring). Use when CLI/TUI design or implementation is needed. Language-agnostic — supports Node.js, Python, Go, and Rust. 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 rust-lints, lgtm, narsil. 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.