Skill Atlas · AI Agent 技能目录
AI Agent 技能目录。收录工具、开发、人格趣味等各类技能，标注安全审计状态与兼容平台，可直接安装。
按分类浏览
推荐技能
- academy-guideStop and check this skill before finishing any reply to a question about how to use Claude or a Claude produ…
- api-and-interface-designGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface.…
- design-taste-frontendtasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curat…
- impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or o…
- understand-chatUse when you need to ask questions about a codebase or understand code using a knowledge graph
- career-opsOpen-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications. Use when…
- artifacts-builderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web te…
- presentation-structureKnowledge about the presentation slide format, weight system, navigation, and section structure
- diagram-designCreate branded architecture, architecture delta, IT current-state, flowchart, sequence, state machine, ER/da…
- humanizerRewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or revi…
- i-have-adhdShape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across…
- ab-testingWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentati…
- 13c-metabolic-fluxEstimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using vali…
- open-code-review-delegateDelegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the…
- 00-andruia-consultantUsar al iniciar o mejorar un proyecto de IA: diagnostica código y restricciones, propone skills existentes y…
- screen-reader-testingTest web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen re…
- agentic-workflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.
- huashu-nuwa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…
- book-to-skillConverts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into …
- cognee-cliUse when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve m…
- invisible-playwrightUse the Dot's browser identities for any task on a website or search on the web: which identity to use, open…
- gws-admin-reportsGoogle Workspace Admin SDK: Audit logs and usage reports.
- add-anydocAdd local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyD…
- huashu-design花叔Design——用HTML做高保真原型、幻灯片、动画、可视化与专家评审。任何新设计100%先出三个方向初稿给用户选（指定风格/品牌也不豁免），选定后才执行。触发词：做原型、PPT、幻灯片、动画、设计风格、评审、做…
- planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.m…
- release-skillsUniversal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claud…
- distillySet up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), o…
- notebooklmInstall, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed asyn…
- brag-slimTurn a project directory or a website URL into a short, shareable launch video with music, motion, and share…
- ablation-plannerUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed …
- video-shotcraftCreate cinematic product videos from frontend projects or webpages with Remotion, real page captures, shot c…
- prompt-masterGenerates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improv…
- skill-builderAutomatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create…
- install-memuInstall or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and fol…
- implementing-llms-litgptImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi,…
- angular-architectGenerates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, imple…
- benchmark-paper-templateStructures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipel…
- zhangxuefeng-perspective张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用…
- egm-bootstrapBootstrap directory README.md files across a repository subtree.
- offensive-active-directoryActive Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodH…
- article-sketchnote-editorial把一个概念铸成杂志专题档案——真问题→失败→转折→顿悟→命名, 6 个 layout 模具 + 4 字族对比 + 探案档案细节
- doc-parse将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown，并输出元数据与解析置信度，作为 RAG 与四色卡片的数据底座。
- ai-visibilityMeasure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they ci…
- browser-cdpUse this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existin…
- create-exDistill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relation…
- browser-act-skill-forgeForges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-explora…
- academic-paper-reviewerSimulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to p…
- nihaixia倪海厦（1954-2012）台湾中医师，经方派代表人物，汉唐中医创始人。核心心智模型：六经辨证、阳气论、经典至上、经方为主。决策启发式：先辨六经再选方、阳气不足先扶阳、经典原方最可靠。触发词：倪海厦、海厦视角、中医倪…
- trace-claude-codeAutomatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversati…
- architectSketch types, signatures, and module structure before code, then stay in the loop while implementation fills…
- task-observerMonitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology…
- short-drama-knowhow维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链，并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、ru…
- ctf-ai-mlProvides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adver…
- onboardExplains the team's shared Claude Code setup
- a-philosophy-of-software-designApply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, …
- agent-teamsCoordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messag…
- 37signals-wayBuild lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up…
- agy-delegateDelegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its di…
- research-add-fieldsAdd field definitions to existing research outline.
- nihaishaUse this skill when the user asks about Ni Haisha / 倪海厦 TCM course material, especially Shang Han Lun / 伤寒论,…