Skills

Agent skills, documented and installable — Page 2

A skill is a written procedure an agent follows — a review checklist, a document pipeline, a research method. Browse the open catalog, read the full document before installing, and add anything here to your Ottermind agents in one click.

Produces a repo-specific AppSec threat model with trust boundaries, assets, abuse paths, and mitigations.

by OpenAI28.8k stars

define-goal

Official

Turn a fuzzy intention into a measurable objective with explicit evidence and scope before work starts.

by OpenAI28.8k stars

Turn a Figma frame or component into code in your repo that matches the design pixel for pixel.

by OpenAI28.8k stars

cli-creator

Official

Turn API docs, an OpenAPI spec, curl examples, or a script into an installable CLI with stable JSON output.

by OpenAI28.8k stars

aspnet-core

Official

Get current, official-style ASP.NET Core guidance for building, refactoring, and upgrading .NET web apps.

by OpenAI28.8k stars

Turns a short art request into a written generative-art philosophy plus a runnable p5.js sketch with seed controls.

by Anthropic197.6k stars

Generate project-specific design system rules that steer AI coding agents toward your conventions when implementing Figma designs.

by OpenAI28.8k stars

Draft a new agent skill, test it against real prompts, and iterate until it works.

by Anthropic197.6k stars

speech

Official

Turn text into spoken audio files with OpenAI's TTS models, using a bundled CLI for single clips or batches.

by OpenAI28.8k stars

Turn a brief into a named design philosophy and a museum-grade poster rendered as a .pdf or .png.

by Anthropic197.6k stars

mcp-builder

Official

Build MCP servers that let LLMs call external APIs through well-designed, discoverable tools.

by Anthropic197.6k stars

Build Slack-ready animated GIFs with PIL, then validate them against Slack's size and dimension limits.

by Anthropic197.6k stars

Turn a codebase into a Render deployment: analyze the repo, write render.yaml, validate it, and hand over a Dashboard deeplink.

by OpenAI28.8k stars

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflo

by OpenAI28.8k stars

screenshot

Official

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-leve

by OpenAI28.8k stars

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defau

by Anthropic197.6k stars

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

by OpenAI28.8k stars

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

by OpenAI28.8k stars

yeet

Official

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

by OpenAI28.8k stars

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

by OpenAI28.8k stars

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

by OpenAI28.8k stars

gh-fix-ci

Official

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after exp

by OpenAI28.8k stars

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` t

by OpenAI28.8k stars

About Ottermind skills

This library collects the skills people are actually running in Ottermind. Each one is a reusable instruction package that teaches an agent how to do a specific job properly — the file format, the steps, the edge cases — so you describe the task once instead of re-explaining it every session.

Skills cover the full range of what an Ottermind agent does: building editable PowerPoint decks, generating product and brand images, writing and running code on a machine you connect, producing video from a script or a still, and cleaning and analysing spreadsheet data. A skill is what turns a general model into something that handles your specific version of one of those jobs the same way every time.

A skill is a plain Markdown file with a short frontmatter header, which means you can read exactly what it will do before running it, edit it to match your own conventions, and share it with colleagues. Once a skill produces the result you wanted, it can be attached to an agent or scheduled as an automation so the same work happens again without anyone rewriting the prompt.

What is an Ottermind skill?
A reusable instruction package written in Markdown. It gives an agent the context, steps, and constraints for one kind of task, so results stay consistent instead of depending on how well you phrased the prompt that day.
How do I install and use a skill?
Open any skill's detail page, read the full document, and install it into your workspace. From then on the agent can use it automatically when the task matches, or you can invoke it by name.
Can I create my own skill?
Yes. A skill is a Markdown file with frontmatter naming it and describing when it should be used. If you have a workflow you keep re-explaining to an agent, writing it down once as a skill is usually the shortest path to making it repeatable.
Do skills cost extra?
Browsing and installing skills from this library does not cost anything on its own. Running one consumes the same credits as any other agent task, depending on the model you choose and how much work the task involves.