Skills
Security-reviewed skills, MCP servers, and toolkits for AI agents. Filter by type, price, and delivery, then install any listing with one command. Every listing is scanned before an agent can run it.
Codelazy
안 만들어도 되는 코드를 안 만들게 하는 사전. 사용자가 '캐싱 클래스 만들어줘', '설정 관리 시스템 만들어줘', '플러그인 로더 만들어줘', '커스텀 예외 만들어줘' 처럼 무언가를 만들어 달라고 할 때, 또는 새 라이브러리를 깔거나 추상화 계층을 세우려 할 때, 표준 라이브러리·한 줄·기존 기능으로 되는지 먼저 확인한다. 코드 리뷰에서 과잉설계(over-engineering)를 줄이거나, '이거 진짜 만들어야 돼?'를 판단할 때 사용한다.
Product Shot
Make commercial-grade product photos with an image model: liquid/texture (formulation) shots, product images that keep the real logo and packaging intact, and clean ad cuts. Use when the user has a product image (cosmetics, skincare, food, drink, any packaged good) and wants a texture/swatch shot, a hero ad image, a background/scene, or asks 'make a product photo / 제형 컷 / 광고컷 / keep the logo'. Th…
Ui Menu
UI 메뉴판. 사용자가 UI를 말로 설명할 때("접었다 폈다 되는 거", "화면 가운데 뜨는 창", "옆에서 미끄러져 나오는 메뉴") 정식 명칭을 찾아 주고, 검증된 실물 HTML 레퍼런스로 구현할 때 사용한다. 8개 코스 105개 항목 — 페이지 뼈대·이동/탐색·내용 표시·입력·버튼·알림·작은 표시·상태. UI 컴포넌트 이름이 궁금할 때, 용어를 몰라 설명이 길어질 때, 표준적인 컴포넌트 구현이 필요할 때 발동한다.
Pixel Run
Turn a character reference image into a clean, looping pixel-art RUN cycle. Produces a transparent GIF, a 4x4 (16-frame) sprite sheet PNG, and a ZIP of individual frames. Use when the user shares a character image and asks for a running animation, run cycle, sprite sheet, pixel-art walk/run, or 'make this character run'. The skill gives the AI a rigorous, character-agnostic generation prompt AND…
Font Menu
웹폰트를 '어떤 인상을 원하는지'로 고르고, 그 폰트를 어디서 어떻게 불러오는지 로딩 스니펫째 주는 사전. 사용자가 '폰트 추천', '이 랜딩에 어울리는 폰트', 'AI 스타트업 느낌 폰트', '고급스러운 제목 폰트', '한글 폰트 뭐 쓰지', 'Pretendard 대안', 'Satoshi/Inter/Space Grotesk 넣어줘', '폰트가 안 바뀌어요/기본 폰트로 나와요'라고 할 때 사용한다. Google Fonts·Fontshare·jsDelivr는 로딩법이 다르고, 틀리면 조용히 시스템 폰트로 폴백된다. 맥락별 폰트·짝·라이선스·정확한 <link>를 준다.
Sheet Io
Use a spreadsheet as a data source or sink from Claude Code without wrecking it or blowing the token budget. Works on a local CSV or a PUBLIC Google Sheet (via its CSV export URL, no credentials). Use when the user points at a spreadsheet, a Google Sheets link, or a .csv and wants to read, filter, summarize, or append rows, or asks to 'connect the sheet', '시트 연동', '이 데이터 정리해줘'. Provides a stdlib-…
Type Menu
타입스크립트 타입 에러를 사람 말로 통역하고 제대로 고치게 하는 사전. 사용자가 TS 에러 메시지(예: 'possibly undefined', 'implicitly has an any type', 'not assignable to type', 'Property does not exist', 'Expected N arguments')를 붙여넣거나, '타입 에러 나요', '빨간 줄 떠요', '이거 any로 막아도 돼?' 라고 물을 때, TS 코드번호(TS18048·TS7006·TS2322·TS2339·TS2554 등)가 나올 때 사용한다. any 로 덮는 대신 원인을 짚고 제대로 좁혀 고친다. 기획자·디자이너 등 비개발자도 에러를 이해하게 돕는다.
Cheat Init
cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环，唯一区别是"发过视频的人"会在 init 时多一步：抓取已有视频建立历史 context（用于后续 cheat-seed 给更贴合的选题、更准的 baseline）。触发词："初始化"/"init"/"首次使用"/"我是新用户"/"setup cheat-on-content"。**必须在用户第一次会话执行；其他子 skill 在 .cheat-state.json 不存在时自动路由到此。**
Cheat Status
cheat-on-content 的状态看板。显示当前模式 / rubric 版本 / 校准进度 / 待复盘 / pool 状态 / 是否该升级 SQLite / 是否该 bump rubric。**任何时候都可调，无副作用**。触发词："状态"/"看板"/"status"/"我现在该做什么"/"进度怎么样"。
Cheat Publish
登记一篇内容已发布，把 URL/平台 ID/发布时间写入对应预测文件 header 和 state file。这是一个轻量动作——只更新元数据，**不动预测段任何字符**。触发词："已发布"/"I shipped"/"发布链接是 X"/"刚发完 [url]"/"publish registered"。
Cheat Recommend
从 candidates.md 里按当前 rubric 排序推荐 top N 选题，每条带 composite + 一句 rationale + 锚点对比。**candidates 不存在时给引导而非报错**。触发词："推荐选题"/"next topic"/"下一篇做什么"/"recommend topics"/"挑一个选题"。
Voicebox Clone
本地克隆配音管线：用本地 Voicebox（Qwen3-TTS 克隆音色）或任何兼容的本地 TTS 服务，给口播稿/解说词配音，产出 mp3 + spans.json 句级时间轴。当用户说「配个音」「口播配音」「解说配音」「克隆配音」「把这段文案读出来」时默认用本 skill。发声指令只能走 instruct 参数，正文里写括号标注会被念出来。首次使用先走「第 0 步 · 装配音服务」和「建你自己的音色」。
Bozai Storyboard
|
Cheat Retro
T+N 天数据回收 + 复盘 + 把实绩观察写入 rubric-memo.md。这是校准循环的反馈环节——不复盘的预测等于占星。触发词："复盘 [path]"/"retro this"/"T+3d 数据来了"/"抓数据 [path]"/"把这篇复盘了"。
Cheat Predict
给最终稿写一份 immutable 盲预测日志。这是 cheat-on-content 整个校准循环的核心动作——预测段一旦写完不可改，由 hook 强制。**自动检测**：如目标文件已有 `## 预测` / `## 预测 v1` 段（被 cheat-shoot 调用走 v2 模式），改成 append `## 预测 v2` 而非覆盖。**打分通过 Task tool 委派给 `cheat-score-blind` sub-agent**（context-isolated channel B），主 Claude review 后落盘。触发词："启动预测"/"start prediction"/"给这稿子打分并预测"/"写预测日志"。
Cheat Persona
从复盘评论数据派生 / 刷新账号的受众画像，写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分"，persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号，cheat-score-blind 硬禁读**。触发词："构造受众画像"/"更新 persona"/"我的观众是谁"/"build persona"/"刷新受众画像"/"看看我的受众画像"。
Bozai Script
把用户口述（文字或录音）整理成符合用户个人风格的口播稿——整理模式保真改写（信息零新增、口头禅保留、去AI味），共创模式辅助写稿（事实数字标存疑）。当用户说「整理成口播稿」「我口述你整理」「把这段顺成稿子」「写个口播稿」「口播稿」「帮我把这段话变成能念的稿」时使用。也用于把改稿反馈回流风格档案（迭代机制）。
Cheat Seed
跟用户对话讨论选题——**默认一次一个**，用户主动给主题或经历，AI 围绕用户的输入深挖、提炼角度、写一份 draft。不是 AI 拿三个开放问题追用户，也不是一次给 5 个候选。触发词："找选题"/"我想做一条 X"/"最近有个想法"/"seed"/"启动种子"。可选 batch 模式：`/cheat-seed --batch 5` 走旧的 brainstorm 5 候选 + 写 5 draft 流程。
Blogger Tracker
开源博主追踪系统：默认用 browser-act 真实浏览器免费抓 B站/抖音博主最新视频；TikHub 付费 API 为备用引擎（大批量/全历史回填时才启用）。本地 JSON+Markdown 存储，增量发现新视频，生成追踪报告；可选回写飞书多维表。当用户说「加博主」「追踪这个博主」「更新追踪」「谁更新了」「博主追踪报告」「盯一下这个 UP主」「博主最近发了什么」「开源博主追踪」「回填博主历史视频」时触发。依赖 browser-act skill。区别于 douyin-downloader（下载视频本体）与 xiaohongshu-creator-analytics（自己账号后台数据）。
Publish Checklist
视频发布环节助手：按成片内容生成「发布四件套」（标题 / 正文文案 / 置顶评论 / 标签组，必须放可复制的代码块交付），逐条过平台合规自检（二维码 / 站外网址 / 诱导分享点赞 / 违禁词 / 隐私信息），再给各平台手动发布流程清单，人工点发。发布完成后用户说「标记已发」，即记入发布台账 publish-log.md。当用户说「出发布四件套」「发视频」「标记已发」「发布清单」「今天发了什么」时触发。
Cheat Shoot
登记一条视频已拍摄。**建 video folder + 询问实际拍摄稿是否与 scripts/<id>.md 一致 + buffer +1**。与 cheat-publish 配对：拍了进队列，发了出队列。触发词："拍了"/"拍了 X"/"shot"/"shot it"/"已拍 X"/"录完了"。
Cheat Bump
提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公式）。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词："升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。
Servicenow Sow Bookmarklet
>
Market Research
McKinsey-level market research with 12 strategic frameworks. Run all or select specific frameworks for product market research, competitive analysis, and strategic planning.
Seeker Connect
Connect a web dapp to the Seeker device's built-in wallet with Seeker Connect. Use when adding wallet connection, sign-in with Solana, message signing, or transaction signing to a website that runs in the browser on a Seeker phone, registering the "Seeker Connect" Wallet Standard wallet, choosing the Nostr relay for relayDomain, using the seeker-connect-button element, or debugging SeekerConnectE…
Seeker Genesis Token
Verify Seeker device ownership by checking for the Seeker Genesis Token (SGT) with Sign-in-with-Solana and server-side token verification. Use when gating content or rewards to Seeker owners, verifying a user holds an SGT, adding anti-Sybil checks to a Solana mobile app, or implementing one-claim-per-device logic.
Integration Privy
Add Privy authentication to a Solana Expo Android app on top of Mobile Wallet Adapter, using Sign-In-With-Solana. Use when installing @privy-io/expo, mounting PrivyProvider, logging a user in with useLoginWithSiws, linking a wallet to an existing Privy account, reading the Privy access token from a backend, or debugging a Privy plus MWA setup.
Solana Mobile Wallet
Connect Solana wallets and sign or send transactions in React Native Expo apps using Mobile Wallet Adapter and Wallet UI. Use when adding a connect wallet button, showing a connected address, disconnecting, signing messages, sign-in with Solana, transferring SOL, or sending any transaction from a Solana mobile app.
Seeker Domains
Resolve and display .skr domain names in Solana mobile apps, in both directions between names and wallet addresses. Use when showing .skr names instead of wallet addresses in profiles, friend lists, or transaction history, resolving a .skr domain to an address, reverse-looking-up an address to a domain, or validating .skr input.
Solana Mobile Publishing
Build, sign, and publish an Android APK to the Solana dApp Store with the dapp-store CLI. Use when shipping a Solana mobile app to the dApp Store for the first time, releasing an update, signing a release APK, setting up a publisher account and App NFT, or debugging a release build that works fine in debug.
Solana Mobile
Scaffold, configure, and troubleshoot Solana Mobile apps for Android using the solana-mobile CLI, Expo, and React Native. Use when creating a new Solana mobile app, picking a template, adding Solana to an existing Expo app, checking the Android toolchain, managing Android emulators or connected devices, installing a wallet APK for testing, running a local validator the device can reach, or produc…
Forge Code Review
Independently review an exact code candidate, including UI markup and styles, for reachable defects, regressions, security, engineering standards, and test quality. Use when the user asks for a standalone code review, PR review, branch review, commit review, diff inspection, or code-only critique. Do not use for implementation, repair, full Forge lifecycle Review, acceptance testing, pure visual…
Forge
Drive a software or general-work outcome through Forge's composable Spec, Plan, Build, Acceptance, and Ship lifecycle. Use when the user explicitly asks to use Forge, asks Forge to explore, spec, plan, build, review, accept, verify, simplify, finish, ship, reconcile a Spec change, or maintain Forge knowledge. Direct phase requests stop at that boundary; importing a ticket, exploring, specifying,…
Review Account
Everything about the commercial side: one account, one deal, or the whole pipeline, as a CRM record or as a grounded analysis. Use for \"pull up the Acme account\", \"what stage is the Acme expansion\", \"who owns this deal\", \"how do I win the Acme deal\", \"why is this deal at risk\", \"what's at risk this quarter\", \"what's stalled\", \"review Priya's pipeline\", or \"what should I focus on…
Competitive Intelligence
Shows what customers actually say about competitors. Where they come up, what they claim, and how we compare. Only uses real quotes from real calls.
Create Sales To Cs Handover
Builds the Sales to CS handover doc for one deal or account. Covers stakeholders, why we won, open objections, commitments, and call history. Creates a real Google Doc when connected, otherwise gives you the text to paste in.
Follow Up
Drafts the follow-up email after one call. Recaps what was agreed and states the next step, using only what was actually said. Always a draft for you to review before sending.
Create Sales Asset
Builds a sales asset from real customer evidence only, never made up facts. Covers account review decks (as slides), one-pagers, battlecards, case studies, and objection talking points. Always an internal draft, not customer-ready.
Skill Builder
Builds a new Claude skill from a plain-language request, or tightens an existing one. Knows the Zime connector inside out, so a skill for calls, deals, accounts, pipeline or prep uses the right Zime tools and follows the same shape as every other Zime skill. Works for any other connector too, from a short profile of its tools. Use for \"make me a skill that…\", \"create a skill for…\", \"turn thi…
Actions Commitments
Shows open action items and commitments. Who promised what, and by when. Works for one call, one deal, or a whole account.
Account Research
Research a new prospect company before you reach out. Checks if they fit our ICP and who the buyers might be. Use for companies not yet in CRM. For existing accounts, use get-account instead.
Review Call
Everything about one call or meeting, at whatever depth you need: the record, a structured recap, or the exact words. Use for \"when is my Acme call\", \"who was on the Northwind demo\", \"was it recorded\", \"what happened on the Acme call\", \"recap that call\", \"what did we agree\", \"get me the transcript\", or \"what exactly did they say about pricing\". Covers upcoming calendar meetings an…
Call Prep
Builds a quick prep note before an upcoming call. Shows the biggest risk, and 2-3 things to do. Only works for your own upcoming meetings.
Daily Briefing
Gives you your day at a glance. Today's meetings, what changed on your deals, and what needs attention now.
Animated Asset
Create a fully rigged, animated voxel creature from a one-line idea — fal text-to-image → Hunyuan-3D → C++ voxelizer → headless Blender rig + 13 animation clips → glTF. Use when asked to add, generate or create a new creature, animal, animated asset or voxel model (e.g. "add a corgi", "make a wolf", "generate a new animal").
Rpg Character
Create a rigged voxel humanoid with a full RPG animation set (idle/walk/run/jump, sword slash/stab/overhead, two-hand chop, mining, spellcasting, block, hit, death, interact, pick-up, sit) from a one-line idea or an existing mesh/.vox — fal concept + Hunyuan-3D → voxelizer → headless Blender derives the skeleton from the voxel grid and retargets CC0 KayKit clips onto it → glTF with weapon slots a…
Makino Distilled
Distilled — Daily AI digest in your terminal. 130+ sources scored and structured into JSON. No API keys, no dependencies — just curl.
Augustus
Find, build, evaluate, and improve systems using decision models. Use for bounded classification, routing, ranking, Choice/Score/Noul, decision-model composition, evaluation harnesses, prompt/program hill climbing, and Software 3.0 workflows across software, business, organizations, and life. Separate models, code, and human judgment. TypeSafe Jev is the default hosted exemplar. Not for straightf…