SkillsAdd

Install skills for AI.
Extend your AI agent.

A local directory of open agent skills — ranked, searchable, and one command away.

How to install Browse ranked skills

Catalog324,895

Summaries320,711

With docs109,090

Ranked9,730

Topics

Agent workflows 125,511 Design & UI 81,335 Testing 28,140 Docs & files 15,373 Databases 8,443 React 7,147 Marketing 6,034 Azure 3,589

Ranked skills

All Official With docs

#

Skill

Source

8W Activity

Installs

dotnet-backend-patterns

wshobson/agents

plan Enter plan mode for .NET projects with architecture awareness. Analyzes tasks through the lens of supported architect…

codewithmukesh/dotnet-claude-kit

mantis-architecture >- Synthesizes raw learnings and codebase analysis into an interlinked Markdown Knowledge Base (KB). Use at the begin…

vectorization Design, implement, optimize, and review SIMD code in .NET. USE FOR: vectorizing scalar loops with TensorPrimitives, V…

ziniao-shared 紫鸟 CLI ?

ziniao-open/skills

mongodb-schema-design Official MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from S…

mongodb/agent-skills

dashboarding Build, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table …

skill-creator Official Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an ex…

giuseppe-trisciuoglio/developer-kit

prototype 构建一次性原型来回答一个设计问题。适用于用户想验证某个 state model 或 logic 是否感觉对，或探索 UI 应该长什么样时。

vinvcn/mattpocock-skills-zh-cn

openapi-spec-generation

wshobson/agents

mantis-calibrate >- Calculates the final risk score based on empirical evidence and architectural impact. Use when findings have been …

clickhouse-best-practices Official MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before…

clickhouse/agent-skills

shadcn-vue Manages shadcn-vue components and projects — adding, searching, fixing, debugging, styling, and composing UI.

unovue/shadcn-vue

claude-security Official The Claude Security menu — pick a job: scan the codebase (the whole repository or a scoped part of it), scan changes …

anthropics/claude-plugins-official

mantis-meta-agent >- Acts as the persistent supervisor, launching and monitoring the automated review campaign. Use when running a long…

vue-pinia-best-practices Pinia stores, state management patterns, store setup, and reactivity with stores.

vuejs-ai/skills

writing-for-agents 为 agent 编写文档。适用于创建或编辑 skills，或修改 AGENTS.md 或 CLAUDE.md 时。

vinvcn/mattpocock-skills-zh-cn

mantis-pipeline-adapter >- Interactively guides the design and implementation of custom deterministic orchestrator harnesses. Use when a user…

zsxq 知识星球 CLI（zsxq-cli）与底层接口完整操作指南，涵盖星球和?

unnoo/zsxq-skill

target-prioritization Prioritize drug targets from a ranked gene list (e.g., scRNA-seq DE output) by orchestrating parallel API queries aga…

agents365-ai/365-skills

mantis-history >- Analyzes the repository's version control system (VCS) history to extract past vulnerabilities, security fixes, an…

baoyu-xhs-images Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1…

jimliu/baoyu-skills

korean-humanizer AI가 쓴 티가 나는 한국어 글을 자연스러운 사람 글로 고친다. 번역체, AI 상투어, 과도한 ?

nomadamas/k-skill

pi-result-handling Internal guidance for presenting Pi helper output back to the user

agents365-ai/365-skills

mantis-reflect >- Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extr…

skill-creator Official Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…

anthropics/claude-plugins-official

qianwen-audio-tts Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceove…

qianwen-ai/qianwen-ai

heygen-com/hyperframes

mantis-structural-index >- Builds a content-addressed semantic-unit index from source code for structural context. Use when a pinned or live …

mantis-reproduce >- Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to writ…

tdd 测试驱动开发。适用于用户想用先写测试的方式构建功能或修复缺陷、提到 “red-green-refactor”，或需要集成测试时。

vinvcn/mattpocock-skills-zh-cn

autopilot Use when the user dictates an app, site, bot, or feature to build end-to-end and expects a finished result without re…

nick-vels/skills

nextjs-performance Expert Next.js performance optimization skill covering Core Web Vitals, image/font optimization, caching strategies, …

giuseppe-trisciuoglio/developer-kit

baoyu-url-to-markdown Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapte…

jimliu/baoyu-skills

pi-prompting Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagno…

agents365-ai/365-skills

managing-amazon-kinesis-data-streams Official Operates Amazon Kinesis Data Streams (KDS). Covers streaming tables and Amazon S3 delivery - serverless, fully manage…

aws/agent-toolkit-for-aws

code-review 从固定点（commit、branch、tag 或 merge-base）开始，按 Standards（代码是否符合本仓库记录的编码标准？）和 Spec（代码是…

vinvcn/mattpocock-skills-zh-cn

pi-cli-runtime Internal helper contract for calling the pi-companion runtime from Claude Code

agents365-ai/365-skills

ziniao-page Use when a request concerns a webpage running inside an already-opened 紫鸟/ZClaw store browser, including navigation…

ziniao-open/skills

vue-testing-best-practices Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright f…

markdown Renders assistant message text as markdown in assistant-ui. Use when wiring MarkdownTextPrimitive or the markdown-tex…

assistant-ui/skills

video-podcast-maker Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary…

agents365-ai/365-skills

voice Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight e…

simota/agent-skills

nestjs-code-review Provides comprehensive code review capability for NestJS applications, analyzing controllers, services, modules, guar…

giuseppe-trisciuoglio/developer-kit

baoyu-compress-image Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "op…

jimliu/baoyu-skills

qianwen-vision Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract infor…

qianwen-ai/qianwen-ai

mantis-chain >- Analyzes individual security findings to identify and construct complex exploit chains. Use after validation stage…

context7-mcp Official This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Act…

upstash/context7

karpathy-guidelines Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…

szkocot/andrej-karpathy-skills