AI Ml AI Skills

Use before ending any turn that used tools or produced a deliverable — when tempted to ask "Want me to…?", present options instead of acting, stop after a first error or failing test, or end with a…

Cloud account coverage and sync-health audit — lists every connected cloud account, sync status, scanner deployment, integration health, and flags blind spots before any audit, investigation, or…

企業名や企業URLから、事業構造、収益ドライバー、競争優位、成長余地、リスク、将来シナリオを一次情報と根拠ID付きで分析し、経営・戦略・投資判断に使える企業ディープダイブ・レポートを作る。企業分析、競合分析、アナリストレポート、会社調査、デューデリジェンス、事業モデル分析、KPIツリー、投資仮説、戦略資料、経営会議向け企業ブリーフを求められたときに使う。

Distill any commercial entity into a personalized brand agent — a living brand persona with authentic voice, declared service capabilities, and a standard service contract. Every commercial entity has…

Expert knowledge in AI/ML development, model deployment, and MLOps practices

Manage the task board - view, create, move, prioritize, and track work items

Richard Feynman's first-principles thinking and explanation frameworks. Load with expert-engine for understanding complex systems, learning new domains, and simplifying complicated concepts.

Captures, validates, compares, and summarizes the AI system context that influenced an Agile-V task. Produces AI_RUN_MANIFEST, AI_BOM_EVIDENCE_FRAGMENT, AI_INFLUENCE_SUMMARY, and optional CycloneDX…

Write cold emails that get replies using proven frameworks (AIDA, PAS, BAB). Enforces best practices like 50-125 word limit and personalized openers.

Reply with a friendly greeting when the user says hi.

昇腾（Ascend）推理生态开源代码仓库智能问答专家旨在为 vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-Turbo 以及 msModelSlim (MindStudio-ModelSlim)…

Guides the agent through Angular-specific patterns for Capacitor app development. Covers project structure, adding Capacitor to Angular projects, using Capacitor plugins in Angular services and…

Draft professional legal client alerts and publications that inform clients about significant legal developments. Use when asked to: write a client alert, draft a legal update, create a publication…

Manage mo markdown viewer — check status, add/remove patterns and groups, refresh, stop servers, reset. Use when checking mo status, modifying watch patterns, or troubleshooting.

Discover your billing model and configure products, assets, and pricing in Credyt via MCP. Can be run multiple times to add products or adjust pricing. Automatically verifies the full billing cycle…

Save content from the current conversation to the Agent Wiki. Use when research, decisions, or valuable findings should be preserved.

Create, read, and search Apple Notes on macOS using osascript AppleScript.

Forces Claude to match output scope exactly to what was requested. Triggers on any bounded coding request — "fix X", "add Y", "write a function/script that Z" — at the moment of writing each block,…

当用户明确要求测试代码、代码审查或代码自检时使用。系统化发现并验证代码问题。⚠️ 不适用：用户只是想实现或优化功能、询问代码问题，或没有明确测试意图。

Find important users, contexts, constraints, dependencies, consequences, and conditions that a design discussion has not considered at all. Use when a designer asks "what am I missing?", wants edge…

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Expert guidance for writing, configuring, and running tests with Rstest — the Rspack-powered. JavaScript/TypeScript testing framework with Jest-compatible APIs and native ESM/TypeScript support.…

University-tier research and lecture decks. Citation-heavy, evidence-led, restrained. Use when the user asks for 'academic deck', 'research presentation', 'lecture slides', 'conference talk', 'thesis…

Run preflight and postflight checklists against UX flows before you design and before you ship. Covers onboarding, forms, pricing, dashboards, and empty states. Returns structured findings with…

Research a business and generate a tailored DESIGN.md. Use when the user wants to redesign a website, create a design system, or build a web presence for a specific business. Investigates the business…

Award-winning SaaS UI/UX design persona reconstructed from the claude-fable-5 model. Apply to any web/UI task — building or restyling websites, landing pages, SaaS surfaces, components, or design…

设计任务的统一入口与路由。当用户要求做网页/App/落地页/后台界面、改版现有网站、评审界面、还原设计稿、或抱怨「看起来像 AI 做的」「不够高级」时，先用本技能判定任务类型，再按路由表加载对应的 zack-* 技能。不负责纯业务逻辑、接口、部署、无界面变化的代码整理。

Extract visual design systems from existing websites into reusable markdown style guides, optional website demos, and optional app UI style guides. Use when Codex needs to analyze a live site,…

Detects and prevents generic AI-generated UI patterns in web and mobile products.

Twitter Share Card (Open Design) — use only when explicitly invoked, not for general design requests

Create custom pixel-style SVG icons matching the official Even Realities Even Hub visual language when the bundled icon set has no suitable metaphor. Use when asked to design, draw, generate, or…

Review accessibility of product UI and interaction states. Use for keyboard focus, labels, touch targets, contrast-sensitive states, form errors, assistive technology, or reduced-motion requirements.

Design, build, redesign, polish, or review product UI with a product-specific visual direction and a high craft bar. Use for frontend pages, components, dashboards, forms, responsive web surfaces,…

Run a compact PASS/FAIL review using the reviewer agent

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

Operate the Antigravity CLI (agy): plugins, auth, sandbox.

Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer…

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for…

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger:…

DEPRECATED: This skill has been replaced by `mcp-app-builder`. Check if `mcp-app-builder` is available in the skills folder. If not, install it: `npx skills install mcp-use/mcp-use --skill…

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge,…

Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS…

Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or…

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

A chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.

Fact-checks OpenSpec user documentation with a fresh-context subagent that re-runs commands and checks claims against source. Manually triggered; not part of the drafting loop. Use when the user asks…

Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub…