AI Ml AI Skills

Scans directory structure, detects projects, maps dependencies, and documents code organization into a repo.md file. Use when the user needs a codebase overview, project structure map, or repository…

Regenerate the ranked GitHub LLM applications pool (section/x_llm_apps.md) with fetch_llm_apps.py. USE FOR: refreshing the pool linked from applications.md. DO NOT USE FOR: hand-curating entries in…

Plans PM career growth using frameworks from 40+ career episodes and Ami Vora's advancement strategies. Use when planning promotions, identifying skill gaps, navigating career transitions, or choosing…

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server…

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots,…

Install or diagnose the local GreenBubbles CLI and read-only WeChat access. Use for a missing CLI, failed database access, source selection, or initial owner-operated key capture.

Reach for this whenever what was SAID in a YouTube video matters: a pasted link or bare video ID, a summary, quote, translation or fact-check request, notes from a lecture, or research that leans on a…

Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE…

用户用自然语言描述交易风格，自动创建加密货币交易Bot并运行本地回测。支持周期反思进化。可选连接外部平台进行验证和模拟交易。

通过 Abu Chrome 扩展操作用户现有的 Chrome 标签页、登录态和浏览器资料。仅在用户明确要求使用 Chrome、已有标签页或现有登录状态时使用。

Native PDF editing, region reflow, images, forms, annotations, OCR and verified raster redaction.

获取 linux.do 帖子的正文及评论区内容，并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能。

Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.

CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용

Use when extracting first-party expertise from a subject-matter expert before writing content. Produces a knowledge document of contrarian takes, specific examples, and surprising outcomes that AI…

produce a chinese deep reading note for a single academic paper when the input is a pdf, arxiv link, title with abstract, or paper excerpts and the user needs a grounded reading card, contribution…

Schedule, list, pause, resume, edit, or run the user's agentica cron jobs with the cronjob tool. Use when asked to remind, schedule a recurring or one-shot task, try a job now, or manage jobs that…

Autonomously remove your info from data-broker sites.

Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A…

Drive a booted iOS Simulator like a user with the axe CLI (describe-ui, tap, swipe, type, screenshot, record-video) to verify UI flows, reproduce bugs and capture screenshots. Use when asked to tap,…

Review code changes against hard rules and conventions

本地文件包含 (LFI) 漏洞检测和利用工具。使用 curl、ffuf 等工具测试 LFI 漏洞，支持路径遍历、PHP 伪协议利用、日志投毒 RCE、敏感文件读取。当用户需要检测 LFI 漏洞、利用文件包含漏洞读取服务器文件时使用此技能。

Rewrite a memory or context file (CLAUDE.md, AGENTS.md, a todo or notes file) into Honey-terse form so it costs fewer input tokens every session, without losing meaning. Backs up the original first.…

Build, run and improve Stash intuitions — small calibrated classifiers that capture a person's judgment from a handful of labeled examples — over MCP or REST.

Create or improve a 32×32 pixel-art persona face for the Frontier Faces demo (examples/04-frontier-faces/personas.mjs) — the animated agent avatars rendered by face-term.mjs / the browser <cotal-face>…

Use when starting any conversation - establishes how to find and use skills, requiring skill loading via view_file before ANY response including clarifying questions

AI/Tools目录外链情报收集与评估。当需要为项目寻找外链机会时使用，包括： (1) 搜索免费AI工具目录、SaaS目录、创业目录 (2) 批量评估目标站点的收费/登录/审核要求 (3) 记录外链提交结果到memory文件 (4) 生成待提交清单 触发场景：用户要求"提交外链"、"找目录"、"增加曝光"、"外链情报"等

Diagnose ClickHouse runtime query failures when the user wants database-level cause and fix guidance from an error or numeric error code, not source-code root cause analysis.

Define a real ICP and the developer personas in the sale. Use when the user says the product is "for developers," can't name who would say no, or is marketing to whoever holds the budget instead of…

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a…

只读检查一个已生成的备考工作区是否健康并报告问题，默认不做任何修改。核对 .ingest 原材料版本、 内容单元、接管队列与派生产物完整性，以及 wiki、题库、视觉证据、计划和进度的一致性。当用户怀疑 工作区有问题、建库 readiness 被阻断、或想在开始复习前体检时使用。

Adds, changes, or reviews a screen, sheet, dialog, or destination slice (endpoint to repository to ViewModel to UI to navigation to DI to tests) in a Compose or CMP project. Use when adding a screen,…

Turn PRD.md into FEATURES.md: permanent feature IDs, MoSCoW priorities, acceptance criteria and the PRD requirement each feature comes from.

Create and revise polished self-contained HTML reports, landing pages, infographics and local interactive visualizations with responsive layout and final-file QA. Use the separate html-slides skill…

为语音助手宿主（如小布助手 Breeno 等）适配新版本 Xposed 接管支持。当用户要求支持新版本助手、适配助手应用更新、分析新版本 hook 点或解决宿主升级导致的接管失效时使用。

Control desktop GUI applications via screenshots and automated actions.

OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or…

Revises a plan written by create-plan from its review comments or new instructions: rewrites the plan body, leaves each comment intact and bumps the revision. Use when a plan file got feedback or its…

Load the user's Emulo profile, rules mined from their own local AI coding session logs (Claude Code, Codex, Copilot CLI, OpenCode, Google Antigravity), each with dated quotes. Read it before working…

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk…

将科普内容文本转换为可视化PPT风格网页的完整工作流。当用户输入科普内容并希望生成演示页面时触发。支持两种模式：(1) 默认模式：将科普内容生成为仿PPT轮播的单页HTML动画网页；(2) 流程图模式：使用Animation模板将已生成的AI_Animation.html按平面UI样式重构。模板已内置于Skill中。触发词包括"生成PPT"、"生成演示网页"、"生成流程图"等。

用户学任何新概念/新技术/新理论的默认深度入口——一次性用五个视角把概念讲透并帮他选深入方向：crossover 用已会的撬动、occam 框定该学多深、graph 建知识地图、prototype 最小原型迭代、feynman 拷问检验。触发场景：我想学 X、理解 X、X 是什么、讲讲 X、搞懂 X、学一下 X、深入 X、给我讲讲 X。除非用户明确只要某一个视角（那时改用对应的单个 learn-*…

Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.

Test web applications end-to-end by simulating user interactions and verifying expected outcomes. Trigger when the user asks to: test a web app, verify a user flow, run end-to-end tests, QA a feature,…

Professional React animation skill for creating Awwwards/FWA-level animations using GSAP (useGSAP), Motion (Framer Motion), Anime.js, and Lenis. Use when building premium scroll experiences, custom…

Anti-debug detection and bypass for protected binaries. Activate before patching commercial apps that use ptrace/PEB/timing/exception checks on Linux or Windows.

S'active automatiquement lorsque des patterns de sur-ingénierie sont détectés : (1) Modifier du code ou des fichiers que l'utilisateur n'a pas explicitement demandé de changer (2) Créer de nouvelles…

Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.

Framework for competitive landscape analysis across any industry. Use when creating competitor analysis, market positioning assessments, investment memos, strategic reviews, or any analysis requiring…

Review a closed trade or a year of trades — process vs. outcome matrix, plan adherence, the biases that showed up, what the pre-trade skills said, and the one lesson for the journal; reads closed…

设计深模块时共用的词汇。当用户想设计或改进某个模块的接口、寻找加深机会、决定接缝放在哪里、让代码更可测试或更适合 AI 导航，或者当另一个技能需要深模块词汇时使用。