AI Skills Directory

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare…

AI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.

Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing `.step`, `.stp`, `.glb`, `.stl`, `.3mf`, `.dxf`, `.urdf`, `.srdf`, or `.sdf` files, especially…

Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount. Use when the user wants animation in Vue, Nuxt, Svelte, SvelteKit, or asks about…

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from…

道具最终提示词规范 — 白底单品静物，标准产品摄影视角：比例准确、边缘完整、背景不承载叙事

Use when testing the golden_chat golden build

Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UIMessage parts), including migration from v4.

How to build desktop applications with GPUI Kit, the Rust framework published as the gpui-kit crate (GPUI plus gpui_kit::component, gpui_kit::base, gpui_kit::assets). Use when setting up a gpui-kit…

Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production…

Use when working with Flutter Bloc/Cubit state management. Covers when to choose Bloc vs Cubit, how to use bloc and flutter_bloc together, lifecycle, testing, and safe defaults.

Select a consistent visual design system for PPT slides using radius/spacing style recipes. Use when users ask for overall style direction or component styling consistency. Includes…

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of…

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18…

Search Inbox Zero mail, read threads, create mailbox drafts, and manage automation rules through a remote MCP server. Use when the user wants ChatGPT, Claude, or Cursor to work with their Gmail or…

Catalog of the AO Cloud `ao` CLI available inside a cloud sandbox: spawning worker sessions, listing them, messaging them, reporting to the orchestrator, killing them, and claiming pull requests. Use…

Use this skill when the user asks the agent to open, browse, inspect, extract content from, click through, fill forms on, screenshot, or verify a web page with a browser. Also use it for MoviePilot…

Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve an existing one's logic or rubric, choose…

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling…

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate…

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication;…

Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a db_path field.

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure,…

Check refund eligibility and use the refund-order tool safely

当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I

Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers…

长篇网文市场、榜单、平台趋势与对标研究。Use for evidence-based long-form fiction market research, not for ordinary drafting.

Open Plannotator's browser-based code review UI and address the returned feedback.

Create or update a DESIGN.md from an existing product repository or public website. Use when asked to document an interface's design language, reconstruct its visual system, extract design tokens and…

Convert Stitch HTML designs to React Native components, or syncs/updates existing native components to align with the latest Stitch designs, using StyleSheet.

中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable…

Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.

Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent),…

Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan…

Provide technical guidance for Android camera development with CameraX. Use when implementing camera features, handling asynchronous recording lifecycles, wiring low-level hardware interop using…

Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and how its evidence or events change understanding. Keep the book's…

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific…

Create effective data visualizations using best practices for clarity, accuracy, and visual communication of insights

Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review…

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…

使用 Markdown `html:preview` 围栏输出轻量静态 HTML/CSS 可视化。当普通 Markdown 难以清晰表达数值对比、层级关系、流程、时间线、关键指标或布局示意，或用户明确要求可视化 HTML 预览时使用。询问 HTML 源码、教程示例或可复制代码时不要使用。

Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.

Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot.…

Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

个股深度分析的核心工作流。当用户要求"深度分析 / 全面分析 / 帮我看看 / 值不值得买 / DCF / 机构建模 / 首次覆盖 / 投委会备忘录"等涉及个股研究的请求时触发。覆盖 A 股、港股、美股，产出 22 维数据 + 66 位大佬量化评审 + 6 种机构级估值建模 (DCF/Comps/LBO/3-Stmt/Merger) + 7 种研究产物…

AI/LLM应用攻击:提示注入,Agent工具滥用RCE,RAG投毒,MCP供应链,torch.load pickle RCE。Use when testing LLM apps, agents, RAG, MCP plugins, or AI model file risks.

基于解析后的文档与用户意图，生成四色卡片——事实蓝卡、解释绿卡、风险黄卡、行动红卡，是八官署方法论的核心分析输出。