28,367 skills sorted by stars.
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my...
Create or update a workspace skill: its description, structure, instructions, and supporting files.
A fake skill for testing
Inspect Skill Manager's locally installed Claude Code, Codex, Muse, or Grok skills before non-trivial work, report the s...
Agent SDK task integration patterns for Business Central. Triggers on: Agent Task Builder, Agent Task Message Builder, P...
Build, configure, and integrate Business Central agents using the AI Development Toolkit and Agent SDK. Triggers on Agen...
Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they...
Split a skill into scriptable and judgment work, proposing a script interface and a simplified SKILL.md.
Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new s...
Design, build, evaluate, score and improve reusable skills through discovery, architecture and minimal evidence-based ed...
Advanced prompt engineering skill for pi-mono ecosystem.
Audit a SKILL.md (15 checks).
Create or update project-specific skills in this repo. Use when asked to make new skills, modularize workflows, or build...
创建、设计、修改、重构和验证 AgentDock Skill 时使用；负责 Agent Skills 兼容的 SKILL.md、可移植核心、引用、辅助脚本、测试、安全边界和本地真实验证。
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conver...
The official Skill Base CLI client. Use the `skb` (Skill Base CLI) command to search, install (single skill or collectio...
Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port m...
Call help() or help("page.click") to print signatures and uncommon options
Designs and builds a new Claude Code skill folder from a blank page in your own house style, surveying existing skills f...
Scaffold a new SKILL.md.
Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design...
Prismstack 的品質審查 meta-skill。三個 mode： - design：規劃階段 7 問快速判斷（候選 skill 該不該建） - review：完成後 15 維度 + 6 雷區掃描（skill 品質夠不夠） - pac...
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pag...
系统性清理本地 skills — 识别无用/低使用率 skill，分类禁用或删除
Find installed skills that share a name, shadow each other or overlap so much in description that the wrong one gets pic...
DAG-based multi-skill orchestration with dependency resolution.
Generates a new Betty Framework Skill directory and manifest. Use when you need to bootstrap a new skill in the Betty Fr...
Use this skill when the user asks to create a new skill, custom command, or wants to know how skills work in Claude Code...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...
Create new Claude Code skills
Create new skills, improve existing skills, and test skill quality. Use when the user wants to build a skill from scratc...
Creates and updates skills per agentskills.io spec.
AesopIDE with Antigravity-inspired UI"
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integr...
Create, edit, and evaluate agent skills iteratively.
Create production-grade agent skills aligned with the 2026 AgentSkills.io spec and Anthropic best practices (2026). Also...
Collection of Claude Code/Antigravity skills I find useful.
Create new Cebian skills, edit or improve existing ones, scaffold multi-file skill packages, and validate them against t...
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Creates new Claude Code Skills following project patterns with trigger-rich descriptions and progressive disclosure. Use...
Create new Synapse skills from conversation. Describe what you want the skill to do and I'll generate it.
Fix for skill-creator's `aggregate_benchmark.py` silently producing an empty benchmark (0% pass rate, 0.00 delta, "0 ± 0...
Создаёт новые Claude Code Skills в текущем проекте. Используй когда пользователь просит: - Создать новый навык или скилл...
Audits, creates and improves Agent Skills (folders with a SKILL.md) against Anthropic's skill authoring best practices,...
Creates production-grade, reusable skills that extend Claude's capabilities.This skill should be used when users want to...
Use when the user wants to register, inspect, manually run, or remove scheduled Claude skills with Telegram push notific...
Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into...