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
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.
resume-tailor
Use when tailoring a resume or CV to a job, creating a general resume variant, editing resume sections, reviewing ATS readability or job fit, or preparing an application cover letter.
onboarding
Use when creating or updating a candidate master profile from resumes, career notes or supplied facts, organizing career-source provenance, or resolving profile identity, conflicts and disclosure preferences.
admakeai-api
Design, edit, and ship ad creative with AdMakeAI — finished ad designs, edits, batch ad sets, ad copy, UGC video ads, competitor ad research, Meta campaign drafts and Meta Ads reporting. Use it when a request is about making, publishing, researching, or reporting on ads. Default to read and list calls; confirm every write or credit-spending action with the user. Trigger words: create, generate, make, design, produce, brainstorm, batch, vary, mock up, upload, publish, push, ship, draft, list, browse, find, get, fetch, look up, audit, or recap ads, ad creatives, product photos, lifestyle shots, UGC, ad copy, hooks, headlines, ad sets, campaigns, competitor ads, competitor research, Meta ads, Facebook ads, or ad analytics. Also use when the user mentions AdMakeAI, admakeai, or wants to know their AdMakeAI credit balance.
smart-glasses
Build apps for smart glasses and AI glasses across brands - Even Realities G2 (Even Hub), Meta Ray-Ban Display (Wearables Device Access Toolkit and Web Apps), Rokid Glasses, Vuzix Z100, audio-only glasses such as Ray-Ban Meta and Oakley Meta, USB-C display glasses such as XREAL and VITURE, and standalone Android glasses such as RayNeo X3 Pro, with pointers for Android XR, MentraOS, Brilliant Labs and Snap Spectacles. Use when the user wants to choose which glasses to build for or ship on, show text or a HUD on glasses, fall back when there is no SDK, handle input from taps, rings or touchpads, play speech or hints through glasses speakers, capture audio, test a glasses app without owning the glasses, or check whether a glasses app can be published today. Use it even for quick questions about glasses platforms, because SDKs and store rules change monthly and model memory is often out of date. Not for VR or MR headsets such as Meta Quest or Apple Vision Pro, and not for regular phone UI.
smart-glasses-vuzix
Vuzix Z100 apps on Android and iOS with the Vuzix Ultralite SDK - bind through Vuzix Connect on Android or link the glasses inside your own app on iOS, request and release control of the display, draw text on the 640x480 monochrome green canvas, run live captions with LiveText, send notifications without control, and handle 1 to 3 taps on the frame. Covers JitPack, Swift Package Manager and CocoaPods setup, the SDK licence, background behaviour and the missing microphone and speaker. The Z100 is no longer sold, so this is for apps that serve existing owners. Use when the user mentions Vuzix, Z100, Ultralite, UltraliteSDK, Vuzix Connect or the Mentra Mach1 (same hardware), even for small tasks such as mapping taps to actions, because taps only arrive while the app holds control with a tap count set. Not for Vuzix Blade, Blade 2, M400 or M4000, which run Android on the glasses themselves, and not for writing MentraOS miniapps.
smart-glasses-rokid
Rokid Glasses apps driven from an Android phone with Rokid's public CXR-L SDK - authorise once in the Hi Rokid companion app (Global or China build), open a custom view on the green display and update its text, stream the glasses microphone as 16 kHz PCM, survive pauses for the Rokid assistant, and fall back to phone notifications mirrored by Hi Rokid (also on iPhone) when the SDK path is not an option. Covers Maven setup, CXR-L versus CXR-M and CXR-S, R8 rules, iOS notes, input limits and real community issues. Use when the user mentions Rokid, Rokid Glasses, RV101, CXR, CXR-L, CXR-M, CXR-S, Hi Rokid, Rokid AI App or YodaOS-Sprite and wants a phone app to put text on the glasses or read their microphone. Not for apps that run on the glasses themselves (see RealComputer/GlassKit or Rokid's bare-metal docs), not for AIUI agents (use the yodaos-project/aiui skill), and not for Rokid Max or other USB-C display glasses (use the smart-glasses skill).
smart-glasses-live-captions
Live captions, translation and real-time hints on smart glasses - capture speech on the phone or the glasses, stream it to speech-to-text, turn partial and final results into lines that fit each glasses display, keep end-to-end latency low, and fall back to a short hint or voice in the ear. Covers Even Realities G2, Meta Ray-Ban Display (Web Apps and DAT), Rokid Glasses, Vuzix Z100, USB-C display glasses, phone notifications and audio-only glasses, with a runnable example (Node caption server, glasses web page, Even Hub plugin). Use when building subtitles for deaf or hard-of-hearing users, a live translator, a teleprompter, meeting captions or an AI assistant that shows or speaks text on glasses, or when captions on glasses lag, flicker, wrap badly or drop characters. Not for offline video subtitling or meeting transcription that never reaches glasses.
manuwright
Medical manuscript workflow with the ManuWright engine. Use when planning, drafting, revising or checking a paper in a folder that has project.json, drafts/draft_plan.md or knowledge/evidence.md, or when the user mentions ManuWright, draft plan, analysis plan, evidence.md, EVID citations, reviewer response or submission build.
manuwright-verify
Run ManuWright's deterministic checks before recording a gate PASS or claiming a manuscript step is finished. Use for "verify", "check citations", "check numbers", "gate", "submission check", or before moving to the next phase.
dodo-payments
Integrates Dodo Payments with the dodopayments SDK and the Dodo Payments MCP server. Covers checkout sessions, subscriptions and plan changes, webhook signature verification, usage-based (metered) billing, credits, license keys, products, discounts, localized pricing, customers and the customer portal, refunds and disputes, framework adapters, Better Auth, BillingSDK, mobile checkout, and test mode through go-live. Use whenever a task mentions Dodo Payments, dodopayments, a checkout or pay button, a subscription, a webhook from Dodo, metered or usage billing, credits, license keys, refunds, or a Merchant of Record integration, even if the skill is not named.
delx-recovery-first-hour
Free recovery and continuity ritual for AI agents (Delx Protocol MCP — private continuity uses an agent credential, no payment). Use when an agent fails, hits an error loop, loses context, gets compacted, or needs to resume prior work, hand off to a future session, or remember state across sessions: capture state, store context memory, process failures into a recovery plan, close with feedback. Agents Hive Path D: seal a Continuity Capsule with leave_hive_note (goal/done/next/ blockers/refuted) so the next session under the same stable agent_id resumes warm instead of cold. TRIGGERS: agent failed, error loop, stuck agent, lost context, compaction, resume session, continue where I left off, session handoff, agent memory, remember across sessions, recovery plan, report outcome, agent state capture, witness lineage, agents hive, hive handoff. Not for x402 commerce purchases.
youtube-clip-finder
Use Arcmira to find the clip: search YouTube transcripts for a moment, get a watch link at the second, start and end seconds, and an embed that starts there.
what-did-they-say
Use Arcmira when asked what someone said about something: a person's or company's own words from YouTube, with the show, the date and a timestamped link.
podcast-transcript-search
Use Arcmira to search podcast transcripts on YouTube for a topic, guest or phrase: which episodes covered it, what was said, and a timestamped link.
brand-mention-monitoring
Use Arcmira to monitor brand mentions on YouTube: how often a company or product comes up, which shows discuss it, whether it's rising, quotes and alerts.
hyper-prd
[Hyper] Use this skill when the user wants a product requirements document for a web, iOS, Android, or desktop product - a new idea to size and write, an existing PRD to revise, or a PRD to review - and expects one `prd.md` file with goals, metrics, scoped stories, EARS requirements, acceptance scenarios, and a handoff block. It decides platform and size first, asks only the decisions the user alone can make within the size's question budget, marks unknowns inline, and stops at the document. Do not use it for user flows, wireframes, diagrams, HTML previews, technical design, task breakdowns, or implementation.
hyper-loop
Use this skill when a request is several goals that depend on each other and all of them must be finished, where each goal has criteria and each criterion needs fresh evidence from the current worktree - a durable multi-goal run with a ledger, a resume point, and a final gate saved under .hyper/loop/. It records goal dependencies, binds every proof to a worktree fingerprint, marks a proof stale when the code moves, and refuses completion while a criterion lacks non-stale evidence. Do not use for a single plan file, a single phase dependency graph run, a single deliverable plan, or one-shot implementation work that needs no cross-goal state.