Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
300 skills
OpenAIOfficial
A docs-first workflow for building, scaffolding, and troubleshooting ChatGPT Apps SDK applications.
OpenAIOfficial
A framework for building durable, composable CLI tools that Codex can execute from any repository.
OpenAIOfficial
A utility for discovering and installing additional skills into the Codex environment from curated or external repositories.
OpenAIOfficial
A framework for transforming vague user intentions into concrete, measurable, and verifiable agent objectives.
Pawel Huryn· Community
A redirection skill that informs users and agents about the migration of the code-review skill to the ai-shipping plugin.
Pawel Huryn· Community
A redirection skill that guides users to the current location of the intended-vs-implemented tool within the AI Shipping Kit.
Pawel Huryn· Community
A redirection skill that informs users and agents about the migration of the shipping-artifacts tool to the ai-shipping plugin.
GoogleOfficial
A routing skill that dynamically fetches and executes relevant Google platform guidance from a remote catalog.
GoogleOfficial
Manage, discover, and scaffold agent skills within the Gemini Enterprise Agent Platform.
GoogleOfficial
The primary entrypoint for setting up and navigating the Google Agents CLI development lifecycle.
Hugging FaceOfficial
Automates the creation and deployment of Gradio demos for Hugging Face LoRA models.
Julien Thibeaut (ibelick)· Community
A routing agent for selecting and loading the most relevant UI-focused skills for your development tasks.
Trail of BitsOfficial
Injects entropy into decision-making for vague or casual user prompts using a 12-house Zodiac Tarot spread.
Trail of BitsOfficial
An autonomous improvement loop that iteratively refines Claude Code skills until they pass quality reviews.
Trail of BitsOfficial
Automates the generation and maintenance of Claude Code skills based on the Trail of Bits Testing Handbook.
Trail of BitsOfficial
Drafts and formats copy-paste-ready /goal commands for Claude Code and Codex to ensure precise, verifiable long-running agent tasks.
OpenAIOfficial
Load or manage Product Design's saved user context. Use when the user asks to set up Product Design, get started, onboard, save product or design sources, see what Product Design remembers, update saved context, or remember Product Design preferences. Examples include product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, and general product/design notes.
OpenAIOfficial
A mandatory protocol for agents to identify and invoke relevant skills before performing any task or responding to user input.
OpenAIOfficial
AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
OpenAIOfficial
Evaluate a local Codex skill in engineer-friendly terms. Use when the user says "evaluate this skill", "give me an analysis of the game dev skill", "audit this skill", "why did this score that way", "what should I fix first", or asks for a skill-specific report before benchmarking it.
OpenAIOfficial
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).
OpenAIOfficial
Router for all Remotion skills
OpenAIOfficial
Planning skill for AI-powered conversational agents. Qualifies the developer's use case across outcome sophistication, entry point, and customer profile to recommend the right Twilio Conversations architecture and implementation skills. Handles both high-level requests ("build me a voice AI assistant") and specific ones ("integrate ConversationRelay with my OpenAI backend").
OpenAIOfficial
Turn plugin-eval findings into a concrete rewrite brief for a Codex skill. Use when the user already evaluated a skill and now wants Codex to improve it, especially after asking what to fix first.