Install once. Invoke anywhere.

Reusable agent skills for every repository.

Browse curated skills with install commands, trigger phrases, and quality signals so your agents ship faster with less guesswork.

26k+

Indexed skills

180+

Topics & tags

12M+

Weekly install events

Top 1%

Rising skills surfaced

Skills library

Filter by topic, language, and quality signals—then open any skill for install steps and repository context.

Official Only

26355 skills

Ctrl+K
implement

Execute implementation plans in-place with verification loops. Implements chunks sequentially, runs quality gates, auto-fixes failures. Use after $plan or with inline tasks. Triggers: implement, build, code, execute plan.

project-status-report
Python

Generate comprehensive project health and status reports for rapid developer onboarding. Use when starting sessions, checking project health mid-work, or needing overview of git status, open work items, and suggested next actions.

web-artifacts-builder
Python

현대적인 프런트엔드 웹 기술(React, Tailwind CSS, shadcn/ui)을 사용하여 정교한 다중 컴포넌트 claude.ai용 HTML artifact를 제작하기 위한 툴킷입니다. 상태 관리, 라우팅 또는 shadcn/ui 컴포넌트가 필요한 복잡한 artifact에 사용하세요. 단순한 단일 파일 HTML/JSX artifact용이 아닙니다.

deployment-automation
Python

Automate deployment to Vercel platform. Manages deployment configuration, environment setup, and CI/CD integration.

docs-review
Rust

Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.

semantic-compressor
Javascript

带质量保证循环的agent/skill压缩。5阶段迭代流程确保理解保留。 触发词: semantic-compressor, compress skill, optimize agent, reduce tokens, benchmark

prd
Shell

Write a PRD from a Linear ticket and upload it

prompt-engineer
Shell

This skill should be used when the user asks to "create a prompt", "optimize a prompt", "improve this prompt", "engineer a prompt", "prompt engineering best practices", "make this prompt better", "recommend a model", "which model should I use", "best model for", "GPT vs Claude", "Opus vs Sonnet", "Haiku vs Sonnet", "analyze prompt quality", "fix my prompt", "prompt for Claude", "prompt for GPT", or needs help with prompt engineering techniques, model selection, or prompt optimization for any LLM (Claude Opus/Sonnet/Haiku 4.5, GPT 5.1/Codex, Gemini Pro 3.0).

gcp-developer
Shell

GCP access for developers - BigQuery data analysis, GCS viewing, GKE info (GCP开发者访问:BigQuery、GCS、GKE)

invoice-organizer
Ai

This skill automatically reads invoices and receipts, extracts key data, renames files consistently, and sorts them into organized, tax-ready folders.

AutomationDataProductivityPython+2
translation
Jupyter Notebook

Translate text between languages while preserving meaning and context

prompt-engineer
Ai

This skill helps you craft and optimize prompts for LLMs, improving agent performance and system prompts with proven techniques.

AutomationProductivityResearchWriting+1
release-notes
Automation

This skill generates comprehensive release notes and changelogs for Confluence from Jira, Git and PR data to streamline release documentation.

ContentDocsProductRelease+2
vani-spa-setup
Typescript

Create a minimal Vani SPA root with explicit updates

error-patterns

Error recognition and diagnosis patterns for infrastructure troubleshooting. Use when identifying, categorizing, or resolving errors across platforms.

process-execution

Execute and manage processes inside browser VM environments

databases-architecture
Python

Master database design (SQL, NoSQL), system architecture, API design (REST, GraphQL), and building scalable systems. Learn PostgreSQL, MongoDB, system design patterns, and enterprise architectures.

writing-plugins
Lua

Use when creating, editing, or reviewing OpenCode plugins. Covers plugin structure, event hooks, TypeScript typing, custom tools, dependency management, and common patterns like notifications and compaction hooks.

integrated-reasoning
Python

Meta-orchestration guide for choosing optimal reasoning patterns. Analyzes problem characteristics and recommends which cognitive methodology to use - tree-of-thoughts (find best), breadth-of-thought (explore all), self-reflecting-chain (sequential logic), or direct analysis. Use when facing complex problems and unsure which reasoning approach fits best.

php
Typescript

Modern PHP programming patterns

python-odoo-cursor-rules

Guidelines for Python and Odoo enterprise application development with ORM, XML views, and module architecture best practices.

FAQ

Frequently Asked Questions

Common questions about agent skills, how they work, and how to use this directory.

An agent skill is a packaged unit of behavior, including prompts, tool wiring, and documentation, that you can install into a compatible AI agent or IDE to give it a new capability. Instead of re-explaining a task every time, you install a skill once and the agent can invoke it whenever it is relevant. This directory lists skills you can use with clients like Claude Code, Codex, and other compatible agents.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational