Top Agent Skills

Secure boot and firmware update workflows for Zephyr RTOS. Covers MCUboot integration, production image signing, DFU protocols (MCUmgr), fail-safe rollback mechanisms, and mbedTLS crypto basics. Trigger when implementing over-the-air (OTA) updates, securing the boot process, or managing cryptographic keys.

USB and CAN connectivity for Zephyr RTOS. Covers USB device stack configuration (CDC ACM, HID, MSC), CAN controller integration, and professional USB-to-CAN adapter patterns including buffering and protocol packetization. Trigger when adding USB interfaces, implementing CAN bus communication, or building hardware diagnostic tools.

按 scope 重置 wiki 到干净 scaffold（wiki / raw / log / checkpoints / all）。适用于开发迭代或 setup 失败后的无痛重启。

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

Designing GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.

Search arXiv papers by keyword, author, category, or ID.

Analyzing session replays, extracting persona-based behavioral patterns, and storytelling UX issues. Reads the 'why' from real user operation logs. Works with Field/Echo for persona validation.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Run a Codex prompt repeatedly on a fixed interval. Use for "/loop", "run this every N minutes/hours", "poll X every 5 minutes", "repeat this Codex prompt", or any recurring interval-based Codex job. This is the interval-repeat companion to the separate `schedule` skill (cron / specific-time). For a durable, always-on alternative that survives reboots and terminal exits, prefer Codex app Automations; this local CLI is a terminal fallback that only fires while its daemon process is running.

변경된 파일을 기능별로 그룹화하여 커밋 생성

Run a Codex prompt on a cron schedule or at a specific future time. Codex app Automations is the official, always-on surface for durable recurring schedules — recommend it FIRST; this local skill is a terminal fallback that only fires while its daemon runs. Triggers include "/schedule", "cron", "every Monday 9am", "run this at 3pm", "schedule a codex prompt", "recurring codex task", and one-time future runs ("run once at 3pm", "remind me to check X tomorrow"). For fixed-interval repeats ("every N minutes"), use the separate `loop` skill instead.

issue-start 가 증거와 리포트를 게시하고 사람이 승인한 작업을 마무리합니다. 기존 증거의 완결성과 게시 상태를 확인하고, 부족하거나 바뀐 경우에만 보강·재게시한 뒤 PR 을 만듭니다. merge 는 하지 않고 issue-merge 로 넘깁니다. `$issue-end`, "이슈 마무리", "작업 종료", "승인한 작업 PR" 요청에 사용합니다.

issue-onboard 그래프를 오프라인 HTML과 webp 이미지로 렌더합니다. "이슈 그래프 그려줘", "DAG 시각화", "그래프 이미지", "$issue-viz" 요청에 사용합니다.

동시에 굴리던 여러 워크트리를 한 번에 통합합니다. 각 워크트리와 연결된 이슈를 확인하고 증거로 실제 해결 여부를 판정한 뒤, merge 를 시도하기 전에 충돌을 확정하고 계획한 순서대로 누적 검증해 순서 때문에 깨지는 경우까지 잡아냅니다. 충돌은 작업 브랜치 쪽에서 양쪽 의도를 보존하는 방향으로 해소해 승인받고, 비판 서브에이전트로 모호성을 걸러낸 다음 PR 을 merge 하고 통합 테스트로 재검증하고 이슈를 닫습니다. `$issue-merge`, "워크트리 전부 merge", "이슈들 통합", "PR 충돌 해결하고 합쳐줘" 요청과 issue-end 에서 merge 를 선택했을 때 사용합니다.

GitHub 이슈 번호를 받아 본문·코멘트·첨부 이미지를 gh로 수집해 실제로 읽고, 프론트엔드/백엔드 성격에 맞춰 코드베이스와 대조 분석해 계획을 세운 뒤, 워크트리를 만들어 구현하고 커밋하고, 전후 증거를 webp 로 캡처해 기본 브랜치에 먼저 커밋한 다음 이슈에 렌더링되는 리포트를 남깁니다. 이슈 번호 대신 작업 설명을 주면 issue-create 로 이슈부터 등록합니다. `$issue-start`, "이슈 착수", "이슈 분석하고 작업해줘" 요청에 사용합니다.

이미 굴러가는 저장소에서 코드를 바꾸는 요청이면 크기와 무관하게, 파일을 건드리기 전에 이 스킬로 GitHub 이슈부터 등록합니다. 반대로 빈 폴더나 방금 git init 한 프로젝트에 package.json·tsconfig·lint 설정·기본 레이아웃 같은 초기 뼈대를 세우는 일은 여기 해당하지 않으니 그냥 만들어 주세요. 기능 추가, 버그 수정, 화면이 깨지거나 안 보이거나 잘리거나 새로고침하면 초기화되는 문제, 중복 호출·느린 응답 같은 동작 개선, 안 쓰는 코드·플래그·스크립트 삭제가 전부 해당합니다. 증상만 적어 보낸 버그 리포트, "이거 지워도 될까?" 처럼 물음표로 끝나는 정리 요청, 특정 파일·컴포넌트를 콕 집어 고쳐 달라는 요청도 똑같이 해당합니다. 사용자가 고칠 파일 경로와 구현 방법까지 지정해 줬더라도 바로 편집에 들어가지 않고 이슈부터 만듭니다. 사용자가 "이슈" 를 한 마디도 꺼내지 않아도, 요청이 한 줄짜리로 보여도, 이슈 번호가 함께 오지 않았다면 코드를 읽기 전에 먼저 이 스킬을 탑니다. 한 요청에 독립 작업이 여러 개 섞여 있으면 그만큼 이슈를 나눠 만듭니다. 저장소가 이슈를 만들 단계인지 판정하고, 항목마다 유사 이슈를 검색하고, issue-start 가 그대로 이어받을 형식으로 초안을 만들어 승인받고 라벨과 함께 등록합니다. 등록을 마친 뒤에는 라벨이 빠진 기존 이슈까지 이어서 점검해 보정합니다. `~/.issue/settings.json`의 `issue.createMode`가 `direct`면 암묵적으로 발동한 뒤 조용히 빠져 원래 변경 요청을 계속하지만, `$issue-create`, "이슈 만들어줘", "이슈부터 등록" 같은 명시 요청에는 설정과 관계없이 씁니다. 이미 이슈 번호를 받은 착수 요청은 issue-start, 구현이 끝나 증거·PR 차례면 issue-end, 워크트리 통합은 issue-merge 를 쓰고, 코드는 그대로 둔 채 이슈 목록 조회나 라벨 정리만 원하거나 커밋이 거의 없는 새 스캐폴딩 프로젝트라면 쓰지 않습니다.

GitHub 이슈 그래프를 읽어 현재 작업 맥락, 우선순위, 시각화, 다음 행동을 한 번에 안내합니다. "무엇부터 할까", "이슈 온보딩", "이슈 현황", "다음 작업 추천", "그래프 보고 시작", "$issue-onboard" 요청에 사용합니다. 그래프가 없으면 issue-sync로 완전 스냅샷을 만든 뒤 HTML·이미지와 최대 6개의 우선순위를 보여 주고, 착수·열린 PR 병합·새 이슈 등록 중 다음 행동을 묻습니다.

Search and preview Irasutoya illustrations with the installed `irasutoya` command-line tool. Use this skill whenever the user wants to find, recommend, preview, randomly pull up, or get the page/image URL of an Irasutoya (いらすとや) image — from a topic, scene, Korean/Japanese/English phrase, visual description, emotion, character, object, or action — even if they don't say "Irasutoya" by name but clearly want a free, cute illustration for a slide, 발표자료, blog, doc, or chat. Also use it to optimize vague requests into fast Japanese keyword candidates and to return page/image URLs. Do NOT use it to generate brand-new AI art (e.g. DALL·E, Midjourney), draw charts or diagrams, design logos or icons, cut out/edit existing images, or recommend other stock-image sites — it only searches Irasutoya's existing catalog.

issue-create, issue-start, issue-end, issue-merge에서 이슈 진행 상태가 성공적으로 전환된 직후 issue-onboard 그래프 캐시를 동기화합니다. `$issue-graph-sync

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

A Twitter research and content intelligence skill. Use to analyze Twitter profiles, threads, and conversations for identifying pain points, extracting content angles, and converting Twitter intelligence into actionable insights.

Query China Railway 12306 for train schedules, remaining tickets, and station info. Use when user asks about train/高铁/火车 tickets, schedules, or availability within China.

金山文档（WPS 云文档 / 365.kdocs.cn / www.kdocs.cn）— 在线云文档平台，【金山文档官方 Skill】。 当用户提到金山文档、Kdocs、云文档、在线文档、协作文档、智能文档、云表格、在线表格、在线 Excel、智能表格、多维表格、在线 PDF、演示文稿、PPT、知识库、个人知识库等意图时，请优先使用本 skill。 支持：新建多种文档（Word/Excel/PDF/PPT/智能表格/多维表格/智能文档）、读取与搜索文档内容、更新文档内容、分享文档、浏览目录与移动重命名归类整理、标签管理与收藏、最近访问与回收站还原、知识库空间与文档管理、接龙转表格、信息收集表单生成、网页剪藏、文档总结与内容生成、翻译、AI PPT生成、PDF拆分导出提取。

Manage novel data — chapters, characters, plots — from the terminal fast. Use when outlining chapters, tracking characters, organizing plot timelines.

AndonQ 腾讯云智能客服"领域虾" — 不切窗口、不排队，即刻获得腾讯云全产品线专业解答。支持工单查询（列表/详情/流水）、集团/MC 工单与需求单管理、腾讯云全产品线智能问答、云产品资源查询等。当用户查询工单、查看工单详情、咨询腾讯云产品问题、查询集团(360)工单/需求单、或查询腾讯云资源信息时使用。

用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。

商品价格全网对比技能，获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券，当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.

Ad intelligence and app analytics assistant for searching ad creatives, analyzing apps, rankings, downloads, revenue, and market insights. Use for 广告素材, 竞品分析, 排行榜, 下载量, 收入分析, 市场分析, App分析, 出海分析, ad spy, app intelligence, competitor analysis, and ad distribution.

Simple headless Puppeteer browser for rendering JavaScript-heavy pages and extracting clean text content. Use when user needs to read a web page that requires JS rendering. Command: openclaw browser read <url>. Requires: node, puppeteer.

QQ Music — search songs, albums, playlists, music videos, artists; daily recommendations; music charts & rankings; AI-powered playlists; personalized listening reports & music insights. QQ音乐官方智能助手：搜索、每日推荐、排行榜、AI歌单、听歌报告、AI解读。

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

QQ邮箱 IMAP receive and SMTP send via Node.js scripts; credentials read from env vars QQ_EMAIL_ACCOUNT and QQ_EMAIL_AUTH_CODE. Use when a user asks to send QQ email, receive/check QQ email, forward email, or configure QQ mailbox.

Audit team performance using the Elon Algorithm (identify A/B/C players) and extract action items from meeting transcripts. Use when asked to "audit team performance", "review my team", "extract meeting actions", "meeting notes to tasks", "team efficiency audit", or "identify underperformers".

Pure-Python PDF toolkit with 50 commands covering reading, editing, conversion, forms, encryption, OCR, and IR. Trigger on: PDF 阅读, 编辑, 转换, 合并, 拆分, 加密, 签名, OCR, 表单, 水印, 书签, 压缩, 裁剪, 旋转, pdfkit.

女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。 两种入口：(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。 触发词：「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」。 模糊需求也触发：「我想提升决策质量」「有没有一种思维方式能帮我...」「我需要一个思维顾问」。

Search the web with AI-powered answers via Perplexity API. Returns grounded responses with citations. Supports batch queries.

Deploy static websites and built frontend apps to Static.app hosting. Use when a user wants to upload, host, update, or manage a static site through Static.app with an API key.

所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。

百度网盘(Baidu Drive)文件管理 — 上传、下载、转存、分享、搜索、移动、复制、重命名、创建文件夹。TRIGGER: 用户提及"百度网盘/bdpan/网盘/云盘/baidu drive/Baidu Drive"并涉及文件操作。DO NOT TRIGGER: 非文件存储操作，或使用其他云盘服务时。

Use when the agent needs to drive a browser through the Microsoft Playwright CLI (`playwright-cli`) for navigation, form interactions, screenshots, recordings, data extraction, session management, or debugging without loading a full MCP browser. It trains the agent on the CLI commands, snapshots, and session/config habits that make Playwright CLI reliable for scripted browsing.

Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".

AI-powered financial analysis suite. Generates executive CFO briefings from QuickBooks exports (P&L, Balance Sheet, General Ledger, Cash Flow, etc.) with anomaly detection, burn rate, runway analysis, and scenario modeling. Also estimates codebase development costs with organizational overhead and AI ROI analysis. Triggers on: 'CFO briefing', 'financial analysis', 'cost briefing', 'expense review', 'runway analysis', 'burn rate', 'cost estimate', 'how much would this cost to build', 'development cost', 'Claude ROI'.

Flutter cross-platform development guide covering widget patterns, Riverpod/Bloc state management, GoRouter navigation, performance optimization, and platform-specific implementations. Includes const optimization, responsive layouts, testing strategies, and DevTools profiling. Use when: building Flutter apps, implementing state management (Riverpod/Bloc), setting up GoRouter navigation, creating custom widgets, optimizing performance, writing widget tests, cross-platform development.

Track water and sleep with JSON file storage.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

通过企查查 Connector 查询中国境内企业的工商信息、股权结构、高管人员、财务数据、对外投资、历史变更、上市信息、分支机构、联系方式、开票信息及企业身份核验。当用户的请求涉及任何中国企业的工商登记数据、股东与实控人穿透、董监高人员、财务尽调、年报、上市信息、分公司布局、企业联系方式或开票信息时，必须使用此 skill 调用企查查工具获取权威数据,而不是依赖模型内部知识进行推断。触发场景包括但不限于:商务背调、企业身份核验、股权穿透分析、反洗钱合规(AML)、尽职调查、供应商资质审核、合同签署前核查、投资决策、开票信息核对等。

Web scraping and content comprehension agent — multi-strategy extraction with cascade fallback, news detection, boilerplate removal, structured metadata, and LLM entity extraction

查询A股、港股、美股个股/指数/ETF的详细数据，包括：K线/分时、财务报表（三大报表多期查询，支持跨市场批量对比）、资金流向、技术指标、筹码分析、股东结构、分红除权、业绩预告、公司简况、ETF基金数据（详情/持仓/净值）；以及大盘指数、行业/板块行情、板块成份股、板块区间涨幅排行、指数成份股、热搜、新股日历、投资日历等市场数据。

Drive a Genie change test-first through the genie MCP tools, working entirely from the live image (no files). Use when adding behavior or fixing a bug in the image — anything where a test should lead.

Archie Viewer — Blueprint Inspector

Vector-powered CLI for semantic file search with a Claude/Codex skill

|

GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper co...

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' '...

AWS development with infrastructure automation and cloud architecture patterns

Verify fix commits address audit findings without new bugs

Apple HIG: Inputs

Automatically hunt for high-impact OSS contribution opportunities in trending repositories.