A Neon skill with Postgres 14 to 18 guidance: schema design, indexes, query tuning, migrations and common pitfalls.
Skills for AI agents
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. This section collects skills for Claude Code, Cursor, Codex and other agents, each with an install command, an access level and a plain description of who needs it and when.
Match with Foxx AI
Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.
Found: 3123
Needs a VPN
A skill that makes Claude a conductor: it hands tasks to Codex workers in git branches and verifies each before merge.
A skill that lays out WeChat articles: Markdown goes into a local preview page and copies out as ready rich text.
27 WordPress security skills: an agent checks nonces and capabilities, escapes output and reviews plugins with checklists.
A skill for Claude Code and Codex: the agent writes animation scenes, a browser player shows them, export to MP4 and Lottie.
1C Database Queries for Agents
1c-llm-requests
A tiny 1C extension with an HTTP service plus a skill, so an agent writes 1C queries itself and gets database data as TSV
Agile V skills add a reviewable chain to agent work: approved requirements, independent tests and a human release decision.
Skill instead of WebFetch reads a page and returns only the blocks that answer the question, verbatim with heading paths.
jeo-skills is a skill catalog with a router that searches, previews and installs only your picks into Claude Code and Codex.
The vf-rtl skill drives Claude Code through four RTL design stages: from spec and code to simulation and Yosys synthesis.
Six OpenClaw skills: four-source search, page extraction to Markdown, GitHub repository analysis and dependency checks.
A workspace for talking-head video editing: an agent cuts flubs, adds subtitles, cards and sound while you refine in a browser.
Investiture adds eight Claude Code skills to a project: project doctrine, architecture enforcement and a repository audit.
sofagent audits changes made by an AI agent against rules and leaves a log and a snapshot for rollback.
A framework for working with coding agents: a root AGENTS.md, 18 mcaf skills and tests as the decision makers.
A Remotion video starter: ten styles and two skills let an agent make a motion video from a repository link.
A skill that takes an agent from an idea to a working TypeScript extension for Voz, so Mac dictation becomes commands or notes.
Skill configures OpenTelemetry: collectors, sampling, security and telemetry from AI agents, without flooding the context.
Skill edits video from a form brief: cuts, logo, on-screen inserts, zoom and music, all running locally.
19 skills for UI, code and copy: the agent decides from project evidence and verifies results rather than making a template.
jp-essay writes essays in Claude Code the slow way: question, sources, draft, recall from memory and script checks.
A technical documentation skill: SRS, PRD, SDD and OpenAPI from templates, reverse generation from code and quality audit.
A Codex skill for fiction: grounded viewpoint, dialogue with consequences and revision that keeps the author voice.
Official
Ten SpriteCook skills teach an agent to make pixel art and game graphics, animate sprites and export them to Godot
Frequently asked questions
What is a skill for an AI agent?
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. The agent picks it up and solves the task by the defined scenario.
How do I install a skill?
Each card has an install command for a specific agent: Claude Code, Cursor, Codex and others. Usually you copy a folder into the skills directory or install it through a plugin manager.
How is a skill different from an MCP server?
A skill gives the agent knowledge and a sequence of actions, an MCP server gives access to external data and tools over a protocol. They are often used together.