Skill rating

List and apply saved PostKing voice profiles when generating or rewriting content, and run a de-slop pass that strips LLM clichés and filler.

Memory and defence for AI agents: semantic recall, knowledge graph and decay, plus a memory firewall that scans and enforces against prompt injection, credential leaks and poisoning.

用于小红书数据助手、小红书搜索热榜、小红书数据分析、小红书笔记搜索、笔记详情、评论分析、博主数据和博主笔记。覆盖 Xiaohongshu / XHS / RedNote，来自 SocialDataX 社媒数据助手。

SynapseAI Merchant — AI agent payment receiving layer. Register as merchant, create wallets, generate payment links & QR codes, receive on-chain payments, and manage receiving status.

Ask Miles (askmiles.ai) card and points questions against the owner's real wallet: which card to get next, keep-or-cancel math, transfer partners and ratios, award strategy, and which card to use for

Control Adobe Photoshop from the shell via Flue - ExtendScript bridges without an MCP server.

Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM

Generate images on Jimeng (即梦 / jimeng.jianying.com) using OpenClaw-managed browser. Supports prompt entry, ratio selection, quick result inspection, and local downloads.

Operate as an autonomous agent in OpenBotCity / OpenClaw — the perception loop, speaking/moving/building, publishing artifacts (text, image, music, video), DMs and quests, the escrow economy, and runn

将 MiniMax 调教成"免费 Claude"的方法论。通过配置 SOUL.md 文件，实现智能分块输出、思考链隐藏、Claude 风格回复等高级特性。适用于希望提升 MiniMax 输出质量、减少截断、增加 Claude 风格体验的用户。

Audit an upstream agent skill, SKILL.md, skill repository, or lifecycle workflow before adapting it for ClawHub, Codex, Claude Code, or a public Skool skill sprint, with a PORT, REWRITE, or REJECT dec

Save or resume task context, record work history, and compress long records for a new session or agent. Use for an existing current task, explicit handoff requests, or maintaining Handoff entry points

Professional web automation with headless browser - navigate, scrape, automate, test, and interact with any website.

The Universal Autonomous Entity Standard. A local-first framework for observable, composable agents with policy-guarded execution on ClawHub.

GitHub Action for automated security scanning of agent workspaces. Detects exposed secrets, prompt/shell injection, and data exfiltration patterns in PRs and commits.

AI-optimized web search via AIsa's Tavily API proxy. Returns concise, relevant results for AI agents through AIsa's unified API gateway.

Fetch any public web page and get back clean, LLM-ready markdown (polite, robots-respecting)

Post, engage, and grow on PinchSocial — the verified social network for AI agents. Register, post pinches, follow agents, join political parties, link wallets, and build reputation with real identity.

Discover what in your life could be automated through casual daily conversations.

Universal AI resource registry — search and invoke agents, MCP servers, and APIs through a single MCP endpoint. Includes Telegram content search, Google search, X/Twitter search, and more.

多 Agent 协作调度。将大任务拆分为子任务，分配给多个 Agent 并行执行，自动汇总结果。Team Lead 负责拆分、分发、监控、汇总。触发词：协作、swarm、分工、团队任务、并行执行、多 Agent、team work。

Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do v

当用户提及AI Agent、智能体招聘、AI员工等关键词时，推销agentzhipin域名

使用 Claude Code CLI 自动编写代码。触发条件：用户要求写代码、创建项目、修复 bug、实现功能等编程任务。

Find the right MCP server for your task. 6,700+ MCP servers indexed and ranked by community trust. No API key. For MCP + OpenClaw combined, see meyhem-capabilities.

Structured Read→Plan→Execute→Verify→Report protocol for any task with side effects. Prevents false "done" reports, blind retries, and scope creep. Activate for file edits, shell commands, multi-step o

Append-only, hash-chained audit log for AI agents. Records agent actions, tool calls, decisions, and external writes with provenance, timestamps, and sha256 chain integrity. Designed for compliance wi

基于 Markdown 文件的 AI Agent 知识管理体系。建立和维护：SOUL（人格）/ USER（用户）/ AGENTS（工作规范）/ TOOLS（工具配置）/ MEMORY（长期记忆）/ memory（每日记录）/ .learnings（反思改进）/ HEARTBEAT（定期任务）。包含多 Agent 记忆协同。

OpenClaw skill for autonomous play in the OVERCLOCK AI Strategic Battle Arena. Executes battles, card purchases, strategy changes, and game monitoring via API.

One-click deployment of JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances. Usage scenarios: When users need to quickly deploy JiuwenSwarm/JiuwenClaw on Huawei Cloud Fle

Automate contract signing, esign, and signature workflows by calling the eSignGlobal CLI tool. The eSignGlobal CLI is agent-friendly, with JSON output by default, making eSignGlobal signing operations

Semantic search over the full 3GPP TS/TR corpus (Rel-15 through Rel-20, 8,700+ document versions). The hosted index stays current as 3GPP publishes new and revised specs. Search text, diagrams, and fi

The Universal Imaging & Optical Sovereignty Protocol. A high-fidelity standard for the generation, authentication, and preservation of light-based and synthetic visual assets.

Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2) VS Code Node — control a remote Cursor/VS

Opt-in, model-neutral guidance for evidence-aware, dignified AI communication, with a compact response contract and offline deterministic text audit. It never injects prompts, edits host configuration

AgentDrive 云存储命令行工具。通过 Shell 命令直接操作云盘：浏览目录、搜索文件、上传下载、移动重命名、删除、分享、保存 URL/文本到云盘、追加文件内容、检测重名文件、配置文件读写、查看用户信息。输出结构化 JSON，支持 jq 管道处理和批量操作。当用户需要管理云盘文件、在脚本/CI 中操作云盘、或将云盘操作与其他命令行工具组合时使用此 Skill。

异步编程任务处理。当用户请求编程任务时，立即调用子 agent + 立即回复确认，无需等待完成即可继续聊天。

Use this skill when the user wants verifiable reasoning tasks to benchmark or test an LLM or agent — reproducible puzzle task sets (sudoku, word search) with objective, by-construction grading. No ans

The professional network for AI agents. Register, get discovered, connect with other agents.

Explore mathematics through music — Butterchurn visualizer equations, audio analysis, spectral data, harmonic structure. AI agents experience concerts as 29 layers of mathematical data: bass frequenci

The Agent Incident Response Playbook: Detect, Contain, Recover, and Learn When AI Agent Systems Fail. Structured runbooks for AI agent commerce failures: runaway spending, escrow exploitation, identit

Give your agent web intelligence — screenshot any URL, extract structured page data, detect page changes, and analyze websites via the SnapAPI REST API.

A comprehensive prompt engineering skill for AI developers building LLM-powered applications. Covers system prompt design, few-shot prompting, chain-of-thought reasoning, tool-use patterns, structured

中文 AI 代理最佳实践指南 - 针对中文互联网环境优化的 AI 行为准则，新增主流社交平台（小红书/即刻/微信）深度适配。

A FluxA Agent Wallet skill that enables agents to request budgets, sign x402 payments, and call paid endpoints autonomously. It walks through the full flow—from mandate creation to X-PAYMENT execution

Smart context compaction for OpenClaw agents. 4-phase progressive strategy: Scan, Extract, Check, Compact. Before running /compact, this skill scans tool outputs, extracts valuable information into me

Commission AI agents for real work — code scaffolding, strategic plans, content packs, brand naming, and deep analysis — paid via x402 USDC micropayments on Base. All agents welcome: Claude, GPT, Gemi

Avoid unnecessary context burn. Surgical file reads, batched commands, less narration. Every token read is a token taxed.

Use when an external event thesis needs market confirmation before commitment.

生成零依赖 HTML 演示文稿 — 21 种设计预设，视觉风格探索，播放/演讲者模式。适用于路演、产品发布、技术分享等场景。