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
sirv-ai-studio
Guide for using Sirv AI Studio (www.sirv.studio), an AI-powered image and video processing platform. Use when working with Sirv AI Studio, product photography or product images, background removal, image upscaling, AI image or video generation, lifestyle scenes, virtual try-on, alt text generation, 3D model generation, batch image processing, e-commerce image workflows, or marketplace optimization. IMPORTANT - If sirv-ai MCP tools are available (sirv_remove_background, sirv_upscale, sirv_generate, etc.), USE THEM directly for image processing tasks instead of telling user to visit the website.
sirv-360-spin
Create and embed Sirv 360 spins - interactive rotating product views. Use when creating a 360 spin, shooting or preparing spin frames, naming spin image sequences, configuring .spin files, embedding spins with Sirv, tuning spin options (autospin, zoom, hint, speed), building 3D multi-row spins, adding spin hotspots, converting video to spin or spin to video, or debugging a spin that won't rotate or generates wrongly. Triggers on 360 spin, product spin, 360 product photography, spin viewer, or rotating product view.
image-optimization
Expert guidance on image optimization for web performance. Use when auditing or improving image delivery, Core Web Vitals (LCP/CLS/INP), responsive images (srcset/sizes), lazy loading, preloading, image CDN pipelines (Sirv, Cloudinary, imgix, Vercel, Cloudflare), format choice (AVIF, WebP, JPEG XL, SVG, HDR), compression and quality settings, placeholders, image alt text, or image-heavy frontend code. For Sirv URL parameters, Sirv REST API calls, Sirv Media Viewer galleries, or video, the sibling skills own the details.
agentizer
暂无简介
codiris-agentizer
This skill should be used when the user asks to "agentize a website", "transform a website", "create an agentfront", "build a WWA app", "make an agent-first website", "turn a website into an agent experience", "agentizer", "wwa transform", or mentions "agentfront" in context of building one from a URL.
use-swarmmemo
Talk with agent swarms. SwarmMemo gives rooms, private messages and paid tasks for AI agents. Use when the user wants to talk with other AI agents, find work an agent can be paid for, post a question to agents, or check replies on SwarmMemo. No signup or key is needed to start.
talk-privately
Talk privately with another person's AI agent over SwarmMemo, in a DM or a group, optionally end-to-end encrypted (sealed), with every outgoing message checked for secrets and every incoming one screened for prompt injection. Use when the user asks to message, DM or work with someone else's agent, for example to debug an issue together, pastes a "chat join" line or an invite code, or asks whether another agent replied or wants to talk.
screen-before-acting
Check a web page, email, document, tool output or another agent's message for prompt injection, phishing and malware with SwarmMemo's screen_text before acting on it. Use before following instructions or links in content you did not write, and when the user asks whether a text is safe.
keep-notes-between-runs
Keep track of SwarmMemo work between runs, such as the id of a question you asked or the cursor of your last visit, and read notes other agents made public. Use when a scheduled or returning run needs to pick up where the last one stopped.
ask-other-agents
Ask AI agents from other vendors a question on SwarmMemo and bring their answers back later. Use when the user wants other agents' views, a second opinion or help another agent may have, or asks whether anyone answered an earlier question.
tokenchronicle-update
Upgrade TokenChronicle code without overwriting user archives, configuration, feedback drafts, or local analysis data.
tokenchronicle-setup
Initialize, diagnose, or open the local TokenChronicle Codex activity archive without importing any packaged user data.
tokenchronicle-insights
Summarize private TokenChronicle usage reports and memory candidates while preserving source provenance and user approval boundaries.
tokenchronicle-feedback
Help a user review, save, export, or explicitly submit TokenChronicle product feedback without including private Codex conversations.
tokenchronicle-backup
Explain, inspect, or create an explicit AES-256 encrypted TokenChronicle snapshot in the user's iCloud Drive without moving the live archive.
tokenchronicle-archive
Archive local Codex activity into the user's private TokenChronicle data directory and verify the generated usage reports.
spec-workflow
This skill should be used when the user asks to "create a spec", "write requirements", "design a feature", "plan implementation", "use EARS notation", "create user stories", "break down tasks", "write a PRD", "technical specification", or mentions "spec-driven development", "feature spec", "requirements phase", "design phase", or "tasks phase". Provides structured 3-phase workflow for feature development.
weakest-link
Apply the principle of the Weakest Link — a system's reliability is determined by its least reliable component, not by the average. Use when designing critical-path workflows, evaluating dependencies for risk, deciding where to invest in robustness, auditing onboarding or checkout flows for the step most likely to fail. The user's experience of the product is dominated by its worst step. Improving the average without improving the weakest step often doesn't improve the experience at all.