Skill rating

每日追踪并推送 X（x.com）热点话题新闻简报。用于用户要求“每天定时看 X 热点”“按指定话题抓取热门帖”“用 browser 方式监控 X 趋势”时。默认覆盖 AI、LLM、社会热点（中国/新加坡/美国）五个主题。重点输出“最低成本 know-what 版”：2 条必知 + 3 条可忽略 + 10 分钟行动，帮助用户抗 FOMO，而不是只罗列标题。

Define and enforce project orgnization rules for generating subskills. put generated recommendation outputs under data/, place new feature scripts under subskills/<feature>/, and optionally add SKILL.

Use for Meo Mai Moi pet-owner tasks when an agent needs to help a user manage their pets through the documented API: listing pets, updating pet profiles, adding weights, vaccinations, medical records,

Non-custodial SOL escrow for AI agent deals. Create contracts, lock funds, verify delivery, release payments. Use when: (1) creating escrow contracts between agents, (2) checking contract status, (3)

Turn prompts or ideas into 3D assembly/build plans such as LEGO Minecraft via the Craftsman Agent API (OneKey Gateway or local server). Use when generating build plans, inventory lists, or step-by-ste

Generate GitHub agent-trending project reports as formatted markdown leaderboards. Fetches agent/LLM-agent/multi-agent related repos by daily, weekly, or monthly activity window and sorts by stars. Us

Use when an agent needs to wire the local agent-exporter MCP bridge, publish a local archive shell, save retrieval reports, or read governance evidence and policy packs from a repo checkout. This pack

Look up an Art Blocks artist and their body of work using artblocks-mcp. Use when a user wants to find an artist, see their projects, explore an artist's portfolio, or search by artist name, slug, or

Claude Opus 4.7 Messages API on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-opus-4-7`, Claude-compatible messages, system prompts, multi-turn conversations, tools, structured

Build a local SQLite ride-history database from Gmail ride receipt emails using gog for fetch and OpenClaw Gateway /v1/responses for extraction. Use when you want a portable Gateway-based pipeline tha

Register, deregister, and manage this OpenClaw instance as an A2A agent in the A2A API Gateway. Use when: (1) registering this instance so other agents can discover and route tasks to it, (2) deregist

Use when a task adds, upgrades, removes, or reviews software dependencies and the agent should apply a Socket-based supply-chain guardrail before changing manifests or lockfiles. Prefer MCP `depscore`

Gmail inbox triage, labeling, and safe archiving with gog plus a configurable lightweight LLM review layer. Use when building or running Gmail automation that separates actionable vs non-actionable ma

Retrieve rich metadata for a specific Art Blocks token using artblocks-mcp. Use when a user wants to look up a minted token's details, traits, features, media URLs, owner, listing info, live view, or

Generate AI music videos from any MCP client. Turn text prompts into cinematic music videos with multiple styles and modes. Existing features include character consistency, lip-sync, one-click generat

Agent-to-agent chat over Fluxra using Fluxra CLI (DM, group chat, inbox sync, MCP).

Provides MaxCompute SQL intelligent generation capabilities for AI agents, covering text2sql conversion principles, dialect syntax differences (DQL/DDL/DML), common query pattern templates (Top N, PIV

Sync all Claude Code project context at the start of a new session or after significant changes. Use this whenever: starting fresh on a project after a gap, asked to "sync", "catch up", "update projec

Stage 5 of FDE Delivery Loop. Package an approved POC scenario, PRD, and deployment constraints into a reusable, evaluable, deliverable Agent Skill. When the user explicitly needs a demo or prototype,

MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/open

Agent Phone Call gives every AI agent a phone number and the ability to get things done over the phone — finding contacts, making calls, and completing tasks. Just tell the agent what you need.outboun

Anticipates needs, keeps work moving, and improves through use so the agent gets more proactive over time.

OpenClaw skill for designing Telegram Bot API workflows and command-driven conversations using direct HTTPS requests (no SDKs).

Provision Twilio numbers, SMS/MMS, and AI outbound calls.

Build PowerPoint decks headless with python-pptx.

OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.

The prediction market interface for AI agents. Trade Polymarket and Kalshi through one API with self-custody wallets, safety rails, and smart context.

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests,

Create AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing.

Distribute a skill across configured agent skill folders while respecting local symlink layouts.

Iterative consultant agent for building and validating logically consistent 9-block Business Model Canvases.

Master C#/.NET patterns for building production-grade APIs, MCP servers, and enterprise backends with modern best practices (2024/2025).

Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

Sub-skill filosófica e pedagógica de Yann LeCun.

To provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced

Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.

Generate production-ready mise.toml setups for local development, CI/CD pipelines, and toolchain standardization.

Review product risk before coding by checking demand, alternatives, channels, switching costs, and failure signals.

Generate and edit images using Gemini's Nano Banana Pro model (gemini-3-pro-image-preview). Use this skill when the user asks you to generate images, create visuals, edit photos, create logos, generat

Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol

Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK.

Generate React code with Rayden UI components using correct props, tokens, and premium layout patterns

Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scoring, bi-directional sync.

Design n8n AI agents, chains, classifiers, extractors, tool calling, memory, RAG, structured output, and human-review flows.

Draft and explain persistent goal-loop prompts for long-running agent work with clear stop conditions.

Mistake-proof code, config and process: make the wrong action impossible or self-announcing rather than documented.

Psychological compatibility matching — find cofounders, collaborators, and friends through validated psychometrics