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 Foundry Reference Spec AuditAudit a Solidity reference implementation against a protocol whitepaper or public specification. Use when Codex needs to decide whether reference-model behavior, math, edge cases, or unsupported surfaces match the spec before creating or trusting Foundry differential tests. Use when this capability is needed.
- tomevault-io Bundle Devops Agent
Infrastructure, deployment, and operations automation Use when this capability is needed.
- tomevault-io Bundle Writer Agent
Long-form content creation with research and editing Use when this capability is needed.
- tomevault-io Bundle Qtype Architect
Expert assistant for designing and building AI applications using QType's declarative YAML specification language. Helps users architect flows from concept to implementation, validates QType code, generates visualizations, and recommends best practices. Use when users want to build chatbots, RAG systems, agents, data pipelines, or any AI application with QType. Use when the user mentions building AI apps, RAG pipelines, or YAML-based agent orchestration. Use when this capability is needed.
- tomevault-io Bundle Chalkak Ocr Models Release
Release and sync the `chalkak-ocr-models` AUR package by bumping `aur/chalkak-ocr-models/PKGBUILD` and `.SRCINFO`, refreshing checksums against the GitHub asset `ocr-models-vN`, and pushing packaging-only metadata to AUR. Use when publishing OCR model files to AUR, updating model package version/checksum, or fixing `chalkak-ocr-models` AUR metadata. Use when this capability is needed.
- tomevault-io Bundle Agent Context Management
Manages AI agent context window usage - truncation rules, clear truncation markers, and tools for chunked reading or search. Use when building or modifying agent context, system prompts, user messages, or tools that inject large content into the LLM.
- tomevault-io Bundle Ragnarok Quickstart
Use when working with ragnarok CLI commands (generate, validate, convert), prompt modes (chatqa, ragnarok_v4, etc.), dataset-backed or file-backed generation, TREC RAG output formats, or introspection (doctor, describe, schema). Covers all entry points, flags, and generation workflows.
- tomevault-io Bundle Castorini Rank LLM Rank LLM
rank_llm Quickstart
- tomevault-io Bundle Signboard MCP
Use this skill when working with Signboard boards through the local MCP server (listing views/lists/cards, reading cards, and safely creating/updating/moving cards, boards, or board settings).
- tomevault-io Bundle Coreml
Use when deploying custom ML models on-device, converting PyTorch models, compressing models, implementing LLM inference, or optimizing CoreML performance. Covers model conversion, compression, stateful models, KV-cache, multi-function models, MLTensor.
- tomevault-io Bundle MCP Tools Guide
Use when needing to analyze a Rails codebase programmatically — inspecting models, schemas, routes, or controllers. Also applies when looking up library documentation or tracing method definitions across files. Covers Rails MCP Server tools, Context7 documentation queries, and Ruby LSP code intelligence.
- tomevault-io Bundle Fetching Github Issues
Fetches GitHub issues for the current repository and formats them as markdown for LLM consumption. Use when the user asks to implement or read a GitHub issue. Use when this capability is needed.
- tomevault-io Bundle Lightjj
Interacts with a running lightjj instance (browser-based Jujutsu/jj viewer) via the `lightjj api` CLI. Reads diffs, posts inline review comments, posts doc-mode suggestions, and steers the user's view. Use when the user has lightjj running and wants the agent to review changes, annotate diffs, or comment on markdown docs. Use when this capability is needed.
- tomevault-io Bundle Cl MCP
Test a Common Lisp product from multiple perspectives using parallel agents with cl-mcp tools. Each agent adopts a different role (user, security, maintainability, etc.) to find issues that single-perspective testing misses. Use for pre-release validation or quality audits. Use when this capability is needed.
- tomevault-io Bundle Openlore Analyze Codebase
Run a full static analysis of a project using openlore and summarise the results — architecture, call graph, top refactoring issues, and duplicate code. No LLM required. Use when this capability is needed.
- tomevault-io Bundle Session Info
This skill should be used when the user asks "what's my session ID?", "show my inbox topic", "get session info", "what session am I in?", "my agent ID", or needs to retrieve current hive session details for messaging coordination or debugging. Use when this capability is needed.
- tomevault-io Bundle N8n Node Configuration
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are required for each operation, how displayOptions control field visibility, and when to use patchNodeField for surgical edits vs full node updates. Use when this capability is needed.
- tomevault-io Bundle Clawith
Use this skill when a user wants to add a new tool or integration (e.g., GitHub, Brave Search, Notion, etc.) that isn't currently available but can be imported from the MCP registry or via a direct URL.
- tomevault-io Bundle Precision Architect
Convert the user's initial request into a fully-specified, unambiguous, execution-ready prompt through structured interaction. Use when this capability is needed.
- tomevault-io Bundle Dowdiness Crdt Agent Memory
Agent Memory
- tomevault-io Bundle Mixseek Skills
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core. Use when this capability is needed.
- tomevault-io Bundle Pm Dashboard Dev
Development patterns for PM Dashboard plugin including MCP tools, FastAPI endpoints, database operations, WebSocket broadcasting, and testing requirements. Use when working on src/task_manager/, adding features, or modifying the plugin codebase. Use when this capability is needed.
- tomevault-io Bundle Cerebras Inference
Use this to write code to call an LLM using LiteLLM and OpenRouter with the Cerebras inference provider
- tomevault-io Bundle Add Skill
Create or improve agent skills. Load when creating SKILL.md files, writing skill descriptions, or structuring skill content for OpenCode or Claude. Use when this capability is needed.
- tomevault-io Bundle New Agent
You MUST use the new-agent skill when asked to add a implement a agent in lanes. Use when this capability is needed.
- tomevault-io Bundle Twitter Agent
Twitter, tweet, timeline, mentions, X, social media, feed, engagement, replies, drafts, scoring (project) Use when this capability is needed.
- tomevault-io Bundle Fluidcad
Workflow and best practices for designing parts in FluidCAD through its MCP server. Use this skill whenever the user wants to model, design, or modify any part in FluidCAD, whenever they mention FluidCAD, a `.fluid.js` file, or ask for CAD/parametric modeling work that involves sketches, extrudes, cuts, fillets, patterns, repeats, faces, edges, or shape filters. Trigger this even if the user does not explicitly say "FluidCAD" — any time the FluidCAD MCP tools (`mcp__fluidcad__*`) are available and the task involves 3D part design, follow this skill. Use when this capability is needed.
- tomevault-io Bundle Spm4kmp
Use when working with the **spmForKmp** Agent Skill is a assistant designed to help you integrate and manage Swift Package Manager (SPM) dependencies in your Kotlin Multiplatform (KMP) projects using the `spmForKmp` plugin.
- tomevault-io Bundle Prompt Analysis
Analyze AI prompting patterns and acceptance rates Use when this capability is needed.
- tomevault-io Bundle Gologo13 Agent Skills Deslop
Remove AI code slop
- tomevault-io Bundle Graysurf Agent Kit Gh Fix CI
GitHub CI Auto Fix
- tomevault-io Bundle Aw Sync
Sync the AgentWeave project context — regenerate all agent context files (CLAUDE.md, AGENTS.md, GEMINI.md) from the source at .agentweave/ai_context.md. Run this after editing ai_context.md to make sure all agents see updated context. Use when this capability is needed.
- tomevault-io Bundle Hainrixz Cyber Neo Cyber Neo
Cyber Neo — Cybersecurity Analysis Agent
- tomevault-io Bundle Daiso CLI
Use this when a user wants to search Daiso/다이소, compare product price candidates, nearby restaurants/cafes/음식점/카페, convenience stores/편의점, marts, Olive Young/올리브영, Megabox/메가박스, Lotte Cinema/롯데시네마, or CGV data through the Daiso project. Prefer the daiso CLI for direct execution, use the MCP endpoint when the host app supports remote MCP, and choose commands for products, stores, inventory/재고, compare, places, movies, showtimes, seats, health checks, and raw JSON output.
- tomevault-io Bundle Inbound CLI
Use the Inbound CLI to manage mailbox profiles, list and read emails, and keep an agent's default mailbox context between sessions. Use when this capability is needed.
- tomevault-io Bundle Inference Gateway Skills Adl
ADL (Agent Definition Language) Expert
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 foundry-reference-spec-audit, devops-agent, writer-agent. 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.