GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
using-lwc
Use when project decisions, code structure, research, incidents, or verified context must survive future coding-agent sessions through LWC memory and graph indexes.
using-agent-skills
Meta-skill for discovering and invoking the right agent skill for the work at hand, applied at session start.
user-thoughts
Persist user decisions and project constraints to mdbase across sessions. Trigger on /user-thoughts or /ustht, or when the user discusses architecture, tech stack, rules, UI/UX, or project memory.
user-management
Manage users, groups, and permissions on Linux systems. Configure sudo and access controls. Use when managing system access.
use-dom
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
usage-based-pricing
Design pricing models that developers understand, accept, and can predict. Trigger phrases: usage-based pricing, API pricing, metered billing, developer pricing, pricing page, cost calculator, pay as you go, pricing transparency, competitive pricing, developer billing
upgrading-expo
Guidelines for upgrading Expo SDK versions and fixing dependency issues
update-swiftui-apis
Scan Apple's SwiftUI documentation for deprecated APIs and update the SwiftUI Expert Skill with modern replacements.
unsloth-finetuning
Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.
unslop
Post-process AI-generated text through the unslop CLI to strip AI writing patterns before publishing
unslop-review
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix.
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly.
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format.
unship
Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.
unified-ai-gateway
Operate and evaluate Unified AI System through nine governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
understand-project-yylo
Inspect the current product architecture, dependencies, and validation loops before planning or implementing a requested change.
ui-update
Update StyleSeed engine in your project — analyzes what's outdated and updates safely
ui-tokens
View, add, or modify design tokens in the StyleSeed design system