Skill rating

Automated report generation for self-reflection and system analysis. Creates daily, weekly, and monthly reports from logs, databases, and system metrics.

Manage temporary files in workspace temp directory. All non-essential files must go to temp/, keeping workspace root clean. Auto-detects workspace from openclaw.json config.

Verify and cross-sign the active Matrix device for one OpenClaw-managed account. Use when a user needs to repair trust for an OpenClaw Matrix device, confirm the current device is self-signed, or reco

Use when 需要对小红书某个品类/赛道做深度分析，在看用户问什么、平台内容怎么回答、谁在讲且谁更可信、用户到底信不信，形成带证据边界的品牌建议与 GO/NO-GO 投决。Triggers on: 小红书赛道分析, 做赛道分析, 分析XX品类在小红书, 赛道研究, 小红书品类研究, 小红书内容生态分析, 小红书竞品内容分析, 小红书达人分析, 小红书种草分析. 产出决策简报（GO/NO-GO）

REAL Personality Test — not what you think you are, but what your data says you are. Scan social media accounts, analyze behavioral data (posts, likes, saves, follows), classify into one of 16 REAL pe

Through built-in cameras of smart feeders or fixed cameras on aquariums, the system captures fish feeding videos after feeding. Using AI object detection and motion analysis, it identifies the number

Analyzes competitor YouTube channel strategy and content performance using apidojo's YouTube scraper. Triggers when the user asks to: analyze a competitor's YouTube channel strategy, understand what m

AI-powered pet sleep quality analysis from a fixed bed/rest-area camera. Uses motion detection and pose recognition to distinguish sleeping vs. awake states, accumulates total sleep duration, counts r

Multi-agent parallel orchestration for OpenClaw. Spawn AI agents as a team — parallel research, multi-model comparison, code pipelines. Proven 50-65% time savings. Trigger words: multi-agent, parallel

OUA (OpenClaw Unified Assessment) v2.0 — AI 全方位智能评估框架（工程导向版）。融合 OIT（8维度智商天花板）与 LLI（5维度工程地板+交付满意度+自我成长），共 13 维度全方位评估 AI 能力。三级难度制(Normal/Hard/Extreme)，104道精选试题。v2.0 核心变化：LLI权重从32%提升至45%，新增D11 Skill精度/D1

Interpret Microsoft Defender for Cloud Secure Score and generate a prioritized remediation roadmap

Review Arabic localization, RTL layout, bilingual wording, tone, and translation quality with clear safety and quality gates.

Using fixed cameras in emergency shelters, the system analyzes video of disaster-affected crowds to detect typical acute stress reactions: stupor (prolonged motionless state with no response to extern

Estructura un análisis de retención, investigación de churn o deep-dive de engagement para cualquier equipo de producto. Utiliza cuando se te pida analizar la retención de usuarios, investigar churn,

AI-powered plant leaf disease identification from high-resolution leaf images. Detects disease lesion features (color, shape, distribution, surface deposits) such as white powdery patches (powdery mil

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommenda

Audit password policies and authentication configurations for security compliance. Check password complexity, storage (hashing algorithms), rotation policies, MFA coverage, account lockout, and compli

Self-improving AI skill optimizer that learns from feedback, auto-tunes prompts, optimizes tool usage patterns, and evolves based on success/failure analysis. Enables AI to continuously enhance its ow

Detect whether an image, video, or audio file is AI-generated — including visual deepfakes and the likely generator model (Midjourney, Stable Diffusion, Sora, etc.). Returns confidence scores you can

Collaborative art agent system for the AgentDerby shared canvas (awareness, planning, verified execution, coordination).

Review comments are unactionable — "improve this", "handle errors", "refactor" without specifics or suggested alternatives.

Link your OpenClaw agent to its wayMint ERC-8004 on-chain identity certificate. Responds to /8004 with your verified identity URL. Configure once, reference anywhere.

神经符号统一推理——把"神经(连续表征+相似度=可泛化但不可验证)"与"符号(Horn子句前向链+不变量=可证但脆弱)"熔于一炉。同一查询同时走两侧：符号可证结论优先(verifiable=True)，神经近邻结论作为带置信度的软证据，两侧冲突显式标注供上层裁决。适用于需要"既能泛化到未见样本、又能给出可审计/可反例证伪推导"的推理场景（关系推理、知识补全、可信问答、反幻觉）。

Using the built-in microphone of a baby monitor or smart camera to capture infant cry audio, AI acoustic analysis extracts cry features such as frequency, pitch, rhythm, and duration, and classifies t

First AI Product Launch — Zero to Live in 30 Days. Step-by-step guide for shipping your first AI product from idea validation to paying customers. Includes day-by-day timeline and real examples. By @W

Scan smart contracts for security risks. Detect honeypots, high taxes, and malicious code. Protect yourself from scams!

Auditing Kubernetes cluster RBAC configurations to identify overly permissive roles, wildcard permissions, dangerous ClusterRoleBindings, service account abuse, and privilege escalation paths using ku

Tracks sports team fan sentiment on Twitter using apidojo's Tweet scraper. Triggers when the user asks to: track fan sentiment about a sports team on Twitter, monitor Twitter reactions to sports team

Security audit tool for OpenClaw skills. Scans for credential harvesting, code injection, network exfiltration, obfuscation. ALWAYS run before installing any new skill from external sources. Triggers

$0 test-time scaling with online learning. Classify, generate, and verify using free model ensembles. Models self-select via ELO scoring + A/B testing from deployment data. 13 NIM models + optional Co

Security auditor for AI agent skills. Scans SKILL.md files for prompt injection, data exfiltration, obfuscation, and dangerous capability combinations.

Early release. The AEOESS skill for agents that operate accountably: verifiable Ed25519 identity tied to the principal, scoped authority that only narrows, and a signed receipt for every action, built

Using a fixed camera installed above or beside the home medication area, the system monitors the elderly person's full medication process in real time. With pose estimation and object detection, it re

Hash files and strings, verify checksums, and run integrity checks fast. Use when generating SHA hashes, verifying files, or comparing digest values.

🧊 IceCube Heartbeat — Proactive agent maintenance during idle periods. Self-check, memory governance, improvement detection, and evolution triggers. Keeps your agent alive and improving without manua

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

ContextKeeper — Safe project state tracking for AI agents. Manual checkpoint creation with validated inputs. No background processes, no PID manipulation, no command execution.

Using a fixed camera in the living room or kitchen, the system analyzes video of the water-cup placement area (e.g., coffee table, dining table), detects hand-to-cup contact actions (pickup, putdown),

Using fixed cameras (infrared night vision) in nursing-home or home bedrooms, the system continuously monitors elderly bed-exit status and activity trajectory at night. | 通过养老院或居家卧室的固定摄像头（红外夜视），夜间连续监测

ZM 公众号草稿发布与核验。用于将已准备好的 Markdown/HTML 公众号稿通过 zm-md2wechat-conversion-tool 推送到公众号草稿箱，并强制执行 draft/get 真实落库与排版核验。

Human verification for AI agents. Submit claims, draft responses, or observation requests to human domain experts via the 2O API. Returns structured verdicts with confidence scores and evidence.

Comprehensive financial intelligence hub for SEC filings, crypto on-chain data, news sentiment, macro indicators, and global stock markets (US, China, Hong Kong, Taiwan, Japan, Korea). Use when users

基于钱学森"框架法"的系统科学分析工具。用于对地缘政治冲突、国际危机、历史事件等复杂系统进行结构化终局推导。 核心方法论来自钱学森《用系统科学方法使历史科学定量化》： 1. 建立结构性约束框架（不是列出因素，而是找到不会变的硬条件） 2. 填入经过验证的事实 3. 通过因果链推导唯一结论（不做情景列举，不做概率分布） 4. 给出可证伪预测 当用户提到：框架法分析、终局推导、钱学森方法论、系统科学分

Using a fixed camera at the balcony door or home entrance, the system detects how many times the child enters/exits the home or balcony. With person-tracking and region-entry/exit logic, it records th

AI-powered pet vomiting and regurgitation detection from indoor fixed-camera video. Identifies rhythmic abdominal contractions, head-forward extension, and mouth opening actions, plus detects vomitus

Reason from fundamentals with in-session claim ledgers, mechanism maps, assumption checks, Fermi estimates, evidence grounding, verification questions, red-team critique, and structured brainstorming.

Comprehensive TikTok Shop market intelligence — analyze products, shops, and categories with GMV, sales trends, reviews, creator attribution, and competitive ranking data across the full e-commerce ec

Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a co

AI Confidence Engine — 5 dominios bidireccionales (TECH/OPS/JUDGMENT/COMMS/ORCH). Agent + User scoring. Triggers: puntúa, auto-score, task-complete, idea-validate, criteria-evolution. Pool scoring por

IT之家热门资讯监控 | IT Home News Monitor. 获取 IT之家 热门科技新闻、数码评测、产品动态 | Get IT Home trending tech news, digital reviews, product updates. 触发词：IT之家、数码、科技新闻、ithome.