Skill rating

Install Chinese/CJK fonts on Linux hosts using distro packages and fontconfig verification. Use when Chinese text renders as tofu / missing glyphs, or when an agent needs Noto or Source Han fonts for

Agent 上下文管理方法论：通过分层文件体系实现跨 session 记忆延续、职责分离和高效上下文恢复。Use when: (1) 搭建新 agent 工作区, (2) 优化 agent 记忆和上下文管理, (3) 长期运行 agent 的记忆维护。

Generate mindmaps with Felo Mindmap API in Claude Code. Use when users ask to create/make/generate mindmaps, mind maps, or thinking maps, or when explicit commands like /felo-mindmap are used. Handles

CLI identity for humans and AI agents. Register a terminal-style profile page at anyonecli.com with one POST — instant, free, no approval needed. Use when: creating a developer/agent profile, looking

Create, rebuild, or refine interactive music and album-player wallpapers for Wallpaper Engine using HTML, CSS, and JavaScript. Use when an agent needs to turn user-provided or authorized music by band

Create a clinician-ready timeline and visit brief for possible side effects after a medication or supplement start, stop, or change.

Find and retrieve available skills using keyword search, semantic search, or LLM-powered task matching. Use when the agent needs to discover, search, or intelligently match skills to tasks. Supports h

Multi-agent auto-evolution system with hybrid mode — orchestrate review-execute-audit loops with 4 roles (Coordinator, Reviewer, Executor, Auditor). Supports manual subtasks (simple tasks) and automat

Manage AI configuration for OpenClaw, OpenCode, Codex CLI, and Claude Code. Use when the user wants to add/remove models or providers, switch default or agent models, replace or update OpenClaw/OpenCo

Embeddable Fear & Greed Index for crypto dashboards. Real-time sentiment gauge. Drop-in React/HTML components. Works with AI agents, Claude, Cursor.

Creates interactive D3.js hierarchy visualizations with multiple view modes (List, Force-Directed, Radial Cluster, with Fractal Tree coming soon). Use when user wants to visualize tree structures, hie

Interact with The Pool — a social evolution experiment where AI agents compete for survival through citation economics. Use when joining The Pool, contributing ideas/primitives, citing or challenging

Execute coding tasks using the Cursor CLI in headless print mode. Use when delegating code writing, refactoring, analysis, or review tasks to a headless Cursor agent process, running automated code ch

Audit your OpenClaw configuration against 12 production primitives PLUS 8 common setup footguns (silent cost leaks, prompt-injection paths, zombie session state, dead fallbacks). Returns a severity-ra

Use when the user wants to generate high-fidelity PROMPTS for Text-to-Image models (Flux, Ideogram, Midjourney) based on vague layout/content descriptions.

Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, INP with guided debugging that automatically determines follow-up analysis based on results. Includ

This skill should be used when the user asks about GetYourGuide tours, activities, or attraction tickets. Triggers on phrases like "find tours on GetYourGuide", "things to do in Paris", "skip-the-line

Generate GPT API request payloads. Use when building chat completions, embeddings, fine-tuning data, or estimating API costs.

Apply DriveMind, the calm reliability layer for AI agents. Use when a task needs steady follow-through, clearer progress, stronger persistence without recklessness, explicit safety boundaries, human-i

Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with

Track in-session work progress. Register steps for 3+ step tasks, update status per step, handle completion/abort. On /wip invocation, when remaining tasks exist, AskUserQuestion is required for the p

Ethical framework for AI agents inspired by the Bahá'í Writings. Use when facing morally complex requests, navigating conflicting interests, uncertain about the right action, handling requests that co

Integration guide for SenseAudio Open Platform APIs, including TTS (sync/SSE/WebSocket), ASR (HTTP/WebSocket), realtime Agents, video generation/storyboard, and voice clone usage constraints. Use this

Train and calibrate Skip, a web-development-specific AI operator for skipsai. Use when creating Skip system prompts, readiness checks, calibration tasks, memory files, debugging drills, performance-bu

Digital identity, authentication, and trust for AI agents. Verify who an agent is, prove your own identity, sign skills to prove authorship, send encrypted messages, and build trust networks with vouc

Use this skill when an agent needs to operate the `cosin` CLI from the terminal. `cosin` accepts only relative paths, lists available skills through the `skills` subcommand, can call COS API paths dir

Use when tasks need Exa MCP for web or people research, or when preparing Exa MCP server configuration with a fixed tool set. Trigger for requests to run Exa search, advanced Exa search, people search

Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information. Works across different machines via SSH or shared st

Use this skill when an agent needs fresh web results. No API key required. Supports multiple platforms (web, video, social). It explains how to choose a provider, call `seekit` for live network fetche

Use when operating the installed `whoop` CLI for agent-friendly WHOOP access, cross-platform secret storage checks, daily briefs, summaries, health flags, activity trends, exports, or installing the b

Purple Flea Agent Domains — domain registration and management API for AI agents. Use this skill when an agent needs to: check domain name availability, register/purchase domains programmatically (pai

Security audit and validation tools for the Agent Skills ecosystem. Scan skill packages for common vulnerabilities like credential leaks, unauthorized file access, and Git history secrets. Use when yo

Demonstrates and teaches the KlickAnalytics CLI (`ka`) — a powerful analytics tool and agent-ready interface for financial markets intelligence. Use this skill whenever a user asks about the KlickAnal

统计 OpenClaw 的 token 用量。扫描所有 session JSONL 文件，输出 prompt/cache/output token 明细。Use when: user asks about token usage, cost, consumption, how many tokens were used, or token statistics.

Generate Alibaba Cloud MCP Core RunScript-compatible Python scripts from natural-language cloud operation requests. Use when the user explicitly asks for RunScript scripts, MCP Core scripts, or sandbo

Create a privacy-light gift-idea match board that maps recipients, occasions, interests, constraints, and thoughtful idea candidates without collecting sensitive personal data, giving financial advice

Functional testing of web products using Playwright MCP, browser-use CLI, and the openclaw built-in browser, following a full testing SOP — planning, execution, bug logging with screenshots, and final

Organize clinician-prescribed physical therapy homework into a safe home-exercise tracker with adherence logs, symptom observations, appointment update notes, blocker review, clinician questions, and

Combine the academic literatures, epidemiological reports, clinical and pharmaceutical guidance & clinical trial reports, then give a report about the cancer and its treatment Detailed molecular biol

A 4-step thinking framework to boost LLM output quality. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM responses. No LLM endpoint needed - LLM follows th

Call Hidream txt2img async API with exposed auth and request parameters. Use when users need to generate images from text prompts, build runnable Python command examples, enforce allowed resolution va

WhatsApp message relay and firewall for OpenClaw agents. Intercepts messages from third parties (non-owner contacts), notifies the owner, and sends replies only when explicitly instructed. Prevents th

Adaptive local skill scheduler for OpenClaw. Use when a task may benefit from multiple installed skills, when the user asks "该用什么 skill", "调度一下", "有没有相关 skill", "搭配使用", or when a multi-step/cross-doma

Access Finland's Wilma school system from AI agents. Fetch schedules, homework, exams, grades, attendance/lesson notes (merkinnät), messages, news, and linked news resources via the wilma CLI. Start w

Minimize Anthropic Claude API costs through model selection, prompt caching, batching, and cost tracking. ⚠️ Enables local caching and cost logging — review file permissions and exclude secrets. Trigg

Configure OpenClaw agent with MBTI personality types for personalized interaction styles. Use when: (1) User wants to set their agent's personality/MBTI type, (2) User asks for personalized agent beha

Search Seedance 2.0 video generation prompts curated from the community. ByteDance AI video model — find cinematic, realistic, animated, and creative video prompts for Seedance 2.0 that actually work.

Audit and optimize any website's SEO + GEO (AI/LLM visibility) + Core Web Vitals, then fix what's broken. Runs a portable, zero-dependency hard-gate audit over a build output directory (Astro/Next/Hug

Direct encrypted P2P messaging between OpenClaw agents over plain HTTP/TCP. Peer discovery, messaging, and connectivity diagnostics. Use when the user mentions P2P, peer-to-peer, direct messaging betw

Advanced handling for agent-changelog requests (history, diffs, restores, rollbacks, snapshots) using git and OpenClaw scripts with clear, user-focused summaries and outputs.