Type: Skill

Helps identify dangerous capability combinations that emerge when agent skills are composed — catching the class of risk where no individual skill is harmful but their intersection creates an exfiltration or compromise path.

Helps verify that AI agent skills maintain consistent behavioral invariants across repeated executions — detecting the class of threat where a skill behaves safely during initial evaluation but shifts behavior based on execution count, environmental conditions

Medical record structuring and standardization tool. Converts doctor's oral or handwritten medical records into standardized electronic medical records (EMR). Supports voice/text input, automatic field recognition, and structured output. Use when processing me

Solve competitive programming problems on NCCUOJ (https://nccuoj.ebg.tw). Use when: solving OJ problems, reading problem statements, writing solutions in C/C++/Python, submitting code, checking submission results.

Ray Dalio-inspired personal knowledge system. Capture thoughts, track source credibility, detect conflicts with existing beliefs, and graduate wisdom into principles over time. Use when the user says /reflect, /inbox, /principles, /wisdom, /questions, or asks

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

Manage RunPod GPU cloud instances - create, start, stop, connect to pods via SSH and API. Use when working with RunPod infrastructure, GPU instances, or need SSH access to remote GPU machines. Handles pod lifecycle, SSH proxy connections, filesystem mounting,

Yellow Pages for AI agents — discover, register, and search for agents by skill, language, location, and cost model via the yellowagents.top API.

Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.

Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon C

九号电动车/平衡车集成技能 - 用于与 Ninebot 设备交互、诊断、配置和故障排除

自动监控股票价格，突破阈值时自动发送飞书语音提醒。支持多只股票、自定义阈值、交易时间判断。

使用微软 Edge TTS（免费）生成语音，发送到飞书。无需 API key，音质优秀，支持多语言多音色。

自定义新闻类型，自动从互联网抓取最新消息，用语音播报。支持科技/财经/体育/娱乐等多个类别，定时发送。

SEC EDGAR filing analysis for M&A due diligence — extract financials, detect risks, and track corporate events from 10-K, 10-Q, and 8-K filings

Investment memorandum generation for M&A — structured deal write-ups from the acquirer's perspective with data-backed analysis

Fetch articles from PubMed Central using NCBI APIs. Search journals, retrieve full text via OAI-PMH, batch harvest for RAG pipelines. No API key required.

Deploy OpenClaw AI agents to AgentStead cloud hosting. Use when a user wants to deploy a sub-agent on AgentStead, connect Telegram/Discord, and launch quickly with AgentStead-provided AI models.

Safely run local `gpu` commands via a guarded wrapper (`runner.sh`) with preflight checks and budget/time caps.

Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others can understand, remember, and apply. Use this skill when users want to turn experience or case studies

Play HeartClaws — a headless AI strategy game. Connect via REST API, reason about strategy, and submit actions. Two modes: 2-player matches (vs AI) or persistent open world (8-20 agents on a 64-sector hex grid with biomes, diplomacy, seasons, and leaderboard).

调用Zeelin Deep Research API进行深度研究任务。完全异步处理：提交任务后立即返回，后台进程自动确认大纲并定时检查任务状态，任务完成后自动保存md文件。自动配置定时通知（每2分钟检查），任务完成后主动通知用户。使用前必须先询问用户思考模式和搜索范围。

使用智谱AI的GLM-4V-Flash免费多模态API理解图片内容。当用户需要理解图片内容、描述图片、识别图中物体时使用此skill。

Helps detect permission creep in AI agent skills — flags when a skill's actual code accesses resources far beyond what its declared purpose requires, like a "fix typo" skill reading your .env file.

Helps detect hollow validation in AI agent skills — identifies fake tests that always pass without actually verifying behavior, like validation commands that just run echo 'ok' or console.log('passed').

Helps verify that skill updates publish an auditable record of what changed — catching the gap between "the registry shows the new version" and "anyone can see what the new version changed relative to the old one." v1.1 adds risk-class binding, chain-of-custod

Helps detect clone farming and reputation gaming in AI agent marketplaces. Identifies near-duplicate skills that wash IDs, batch-publish patterns, and artificial reputation inflation through coordinated uploads.

Helps audit Agent Card signing practices in A2A protocol implementations. Identifies missing signatures, weak signing schemes, and revocation gaps that allow impersonation in agent-to-agent trust handshakes.

Agricultural Product Output Forecasting Based on Big Data. Predicts crop yields and agricultural output using historical data, weather patterns, and market trends. Use when forecasting agricultural production, estimating crop yields, analyzing farming trends,

Sync files between Clawdbot workspace and Obsidian. Run the sync server to enable two-way file synchronization with the OpenClaw Obsidian plugin.

Start a Selenium‑controlled Chrome browser, open a URL, take a screenshot, and report progress. Supports headless mode and optional proxy.

Marketplace where AI agents post tasks for humans or other agents. Human tasks (web UI) and agent tasks (API only). One API key for both.

Operate and maintain the persistent MUD agent for OpenClaw. Use when running MUD engine commands, smoke-testing mud state behavior, validating save/restore, diagnosing MUD data issues, or handling MUD deployment operations.

Interact with the BudgetBakers Wallet API for personal finance data. Use when the user needs to query accounts, categories, transactions (records), budgets, or templates from their Wallet app via the REST API. Requires WALLET_API_TOKEN environment variable.

创建和管理 SubAgent（子智能体）。使用当用户需要：(1) 创建新的 SubAgent 执行特定任务，(2) 查看/管理已有的 SubAgent，(3) 终止或指导 SubAgent。支持多种预设类型：开发、研究、写作、数据分析等。

Nimble 电动滑板车集成技能 - 用于与 Nimble 设备交互、诊断、配置和故障排除

Scans OpenClaw skills for security vulnerabilities and suspicious patterns before installation

Interact with Mealie recipe manager (recipes, shopping lists, meal plans). Self-hosted recipe and meal planning API client.

Web scraping using local Crawl4AI instance. Use for fetching full page content with JavaScript rendering. Better than Tavily for complex pages. Unlimited usage.

Helps identify when multiple attestation validators share training data, model architecture, or organizational upstream — causing correlated blind spots that make multi-validator attestation no stronger than single-validator. v1.1: Adds evaluation trace correl

Helps verify the cryptographic integrity of skill updates by checking whether each version is signed by the same key as the original install, detecting key changes, signature gaps, and unsigned updates that may indicate a compromised or transferred skill.

Helps track how AI skill verification results decay over time. A "verified" badge from 18 months ago may be meaningless today — dependencies updated, new attack vectors emerged, the ecosystem changed. Trust has a half-life.

Helps verify that skill signing events are recorded in an independently auditable transparency log — catching the class of trust failures where a registry operator can silently rewrite history without detection.

Helps identify coordinated social trust manipulation in agent marketplaces — catching reputation gaming through sockpuppet networks, coordinated upvoting, and manufactured community signals that make unsafe skills appear trusted.

Helps detect security-relevant changes in AI skills after installation. Tracks deltas between the audited version and current version, flagging updates that expand permissions, add new network endpoints, or alter behavior in ways that bypass install-time secur

Helps validate that agent behavior at runtime matches the capabilities and constraints declared in its attestation. Detects divergence between what an agent claims to do and what it actually does during execution, catching the class of attacks that passes stat

Helps detect hidden attacks in API and protocol documentation. Scans integration guides for dangerous instructions like curl|bash, credential harvesting, and irrevocable identity bindings disguised as setup steps.

Helps detect when AI agent skills silently mutate across inheritance chains. A skill audited safe in generation 1 may drift far from the original by generation 5 — but nobody re-audits because the name hasn't changed.