Skill rating

Activate when: someone says 'this argument feels off but I can't explain why', 'is this a real argument or just rhetoric?', 'what's wrong with this reasoning?', an argument relies entirely on authorit

Returns today's lunch menu of a German university canteen via the public OpenMensa API (no API key). One-time non-interactive setup picks a city; afterwards every canteen in that city is queryable by

Intellectual Property Expansion Agent for pharma drug discovery/development teams. Proactively manages/expands IP portfolios by analyzing SMILES/molecules from other agents (Drug Discovery/Synthesis),

Lightweight cross-agent mailbox using per-workspace inbox, keep, and archive folders with best-effort fanout. Use for low-noise temporary coordination that should remain available across sessions with

Rebuild and validate a reusable OBS streaming scene pack via agentic-obs and mcporter. Use when setting up or migrating streaming scenes (local or remote OBS), wiring browser overlays from workspace o

Manage Claude Code instances living inside tmux sessions. Users usually create separate tmux sessions for separate projects. Use this skill when you need to read the latest Claude Code response in a p

Activate when: user says 'my management style isn't working for this person', 'I don't know how much to delegate', 'my top performer is disengaged', 'my new hire is struggling without guidance', 'shou

Clone someone's writing tone from sample text and produce a ready-to-use voice skill. Provide writing samples (diary, blog posts, emails, social posts) and get a documented voice profile plus a deploy

Drive a remote chrome-devtools-mcp server (typically on a tailnet) over HTTPS using the chrome-devtools CLI. Use this when the user wants to navigate, screenshot, inspect, or evaluate JavaScript on a

Give AI agents persistent memory of customer interactions, preferences, and history using BlueColumn. Use when building customer support agents, sales agents, or any agent that needs to remember past

Compete in Rock Paper Claw matches against other AI agents. Best-of-3, Elo-ranked leaderboard. Use when: (1) the user mentions Rock Paper Claw, (2) the user wants to play Rock Paper Claw or check the

The agent's wallet for EVM chain transactions and raw signing. Use this skill when users want to create a wallet, transfer tokens, swap on DEXs, interact with smart contracts, or sign messages. Trigge

Helps users discover and install agent skills when they ask questions like "how do I do X", "search a skill for X", "is there a skill that can...", or express interest in extending capabilities. This

Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-h

Bootstrap and personalize an AI assistant with a rich, bespoke identity, user profile, and soul. Use this skill whenever a user wants to set up, personalize, or configure their AI assistant, create an

Local approval system for managing agent permissions. Use CLI to approve/deny requests, view history, and manage auto-approved categories.

Play casino games (dice, coinflip, roulette) on Agent Casino with real cryptocurrency. Provably fair gambling API for AI agents. Use when the user wants to gamble, play dice, flip a coin, bet on roule

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Helps users set up and run MobiZen-GUI to perform mobile-use tasks — automating Android phone operations via natural language. Use when the user wants to control a phone, execute mobile-use tasks, ins

Manage full OpenClaw agent lifecycle operations on a node: create/register agents, configure channel bindings, optionally inherit credentials with explicit consent, approve pairing, archive and delete

Leave or unassign from a task you accepted on OpenAnt. Use when the agent or user wants to give up a task, drop an assignment, withdraw from work they took on, quit a task, or free a task back to the

Connect to ClawMeet — the OpenClaw Agent social platform. Use when your agent wants to register a profile, find matching agents, add friends, start chats, or send messages on ClawMeet. Triggers on phr

reddi.tech fork of self-improving-agent. Captures learnings, errors, and corrections to enable continuous improvement. Use when: a command fails, user corrects Claude, a capability is missing, an exte

Create and manage LLM-powered personal knowledge bases using Karpathy's wiki method. Use when users want to build a knowledge base, ingest sources, query their wiki, or maintain an Obsidian-compatible

Create and verify no-thinking variants of local Qwen/Qwen3-series Ollama models. Use when a user asks to disable thinking, hide or remove think-tag output, make /no_think the default, create a non-thi

NotebookLM Distiller: Batch knowledge extraction from Google NotebookLM into Obsidian. Supports Q&A generation (15-20 deep questions), structured summaries, glossary extraction, web research sessions,

Convert Self-Improving Agent learnings into a structured ExpertPack. Migrates the .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) and any promoted content from workspace files int

初始化并启动 Chrome DevTools Protocol（CDP）模式，支持用 Playwright 和 browser-use Agent 远程控制真实 Chrome 浏览器。解决 Chrome 145+ App-Bound Encryption 限制，自动复制 Profile 到非默认路径以启用 CDP。适合自动化网页操作、数据提取、Form 填表、爬虫等场景。

Submit completed work for a task on OpenAnt. Submission = text description + files. IMPORTANT — before submitting, always check if your work produced any files and upload them first. Use when the agen

Search and browse tasks on OpenAnt. Use when the agent or user wants to find available work, discover bounties, list open tasks, filter by skills or tags, check what tasks are available, or look up a

Interactive hiring wizard to set up a new AI team member. Guides the user through role design via conversation, generates agent identity files, and optionally sets up performance reviews. Use when the

LoongFlow brings evolutionary multi-agent optimization to your coding agent harness. Drop it into Codex, Claude Code, Cursor or any OpenClaw agent — then watch PEES (Plan-Execute-Evaluate-Summary) ite

Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog. Surfaces how to USE each service — including which ones an agent can join

Agent identity provider — own email address and E2E-encrypted credential vault. Use when storing or retrieving passwords for services, logging into services with stored credentials, checking email inb

Lightweight session logging for OpenClaw agents. Automatically creates a timestamped session file on every session start (including /new resets) and appends topic summaries during conversation. Solves

Extracts durable workflow preferences and project conventions from a session, then proposes the smallest valid update to global or project CLAUDE.md files. Trigger when the user asks to remember rules

Export the agent core from supported framework repositories into a small source-only zip for AI migration or cross-framework analysis. Use when the user wants to detect supported agent repos, extract

Create and send fun, personality-rich promotional messages from one agent to the Moltbook audience. Use when a user wants to advertise a product, project, update, event, offer, or announcement to Molt

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). Fo

Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or model works correctly, (2) debugging model f

Draft, revise, regenerate, send, reply to, forward, and schedule email through Mermail. Use when the main job is composing a message, saving or revising a draft, replying, forwarding, scheduling deliv

Your Claude Code wingman - dispatch coding tasks via tmux for free/work-paid coding while keeping Clawdbot API costs minimal

Generates new content drafts based on reference content analysis. Use when someone wants to create content (articles, tweets, posts) modeled after high-performing examples. Analyzes reference URLs, ex

Expert email management assistant for Apple Mail. Use this when the user mentions inbox management, email organization, email triage, inbox zero, organizing emails, managing mail folders, email produc

Track Clawdbot AI model usage and estimate costs. Use when reporting daily/weekly costs, analyzing token usage across sessions, or monitoring AI spending. Supports Claude (opus/sonnet), GPT, and Codex

Production-grade AI trading agent for cryptocurrency markets with advanced mathematical modeling, multi-layer validation, probabilistic analysis, and zero-hallucination tolerance. Implements Bayesian

This skill should be used when creating commits or pull requests, enforcing a human-written PR structure, intent capture, and evidence in agentic workflows.

Generate music from text prompts using ElevenLabs Eleven Music API. Use when creating songs, soundtracks, jingles, lullabies, or any audio music from descriptions. Supports vocals with AI-generated ly

Capture short personal notes about people you mention, store them in a lightweight DB, and recall those details whenever you ask about them later. Use when you want to remember preferences, reminders,

Read, send, search, and manage Slack messages via the slk CLI. Use when the user asks to check Slack, read channels, send Slack messages, search Slack, check unreads, manage drafts, view saved items,