Safer agent skills

RAG system combining Docling document processing with ChromaDB vector storage to power openclaw

Score basis：Clear source · Risk needs review · Universal

HTTP bridge powering OpenClaw's AI agents via Claude Code CLI — manages persistent sessions, auto-resume, extended thinking, and provides a real-time React dashboard with per-agent cost tracking.

Score basis：Clear source · Risk needs review · Universal

基于东方财富数据库，支持自然语言查询全球宏观经济数据，涵盖国民经济核算、价格指数、货币金融、财政收支、对外贸易、就业民生、产业运行等多个领域，适配各类宏观经济研究、市场分析、政策解读等多元专业场景需求。返回结果包含数据说明及 csv 文件。Natural language query for macroecono...

Score basis：Source needs review · Low risk signals · Claude

Local memory management for agents.

Score basis：Source needs review · Risk needs review · Claude

Security-first skill vetting for AI agents.

Score basis：Source needs review · High risk signals · Claude

Multi search engine integration with 17 engines (8 CN + 9 Global).

Score basis：Source needs review · High risk signals · Claude

Advanced desktop automation with mouse, keyboard, and screen control The package is internally consistent: it implements desktop automation (mouse, keyboard, screenshots, clipboard) and its files and docs match that purp

Score basis：Source needs review · High risk signals · Claude

Guide for creating effective skills.

Score basis：Source needs review · High risk signals · Claude

The complete operating system for OpenClaw agents.

Score basis：Source needs review · Low risk signals · Claude

基于东方财富数据库，支持自然语言查询金融数据，覆盖A港美、基金、债券等多种资产，含实时行情、公司信息、估值、财务报表等，可用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景，适配机构与个人多元需求。返回结果包含数据说明及 xlsx 文件。Natural language query f...

Score basis：Source needs review · Low risk signals · Claude

Data analysis and visualization.

Score basis：Source needs review · Low risk signals · Claude

You MUST use this for gathering contexts before any work.

Score basis：Source needs review · High risk signals · Claude

Self-reflection + Self-criticism + Self-learning + Self-organizing memory.

Score basis：Source needs review · High risk signals · Claude

Typed knowledge graph for structured agent memory and composable skills.

Score basis：Source needs review · High risk signals · Claude

Ad intelligence & app analytics assistant.

Score basis：Source needs review · High risk signals · Claude

Web search via Tavily API (alternative to Brave).

Score basis：Source needs review · High risk signals · Claude

Search the web using Baidu AI Search Engine (BDSE).

Score basis：Source needs review · High risk signals · Claude

Humanize AI-generated text to bypass detection.

Score basis：Source needs review · High risk signals · Claude

Remove signs of AI-generated writing from text.

Score basis：Source needs review · High risk signals · Claude

基于东方财富数据库，支持自然语言搜索全网最新公告、研报、财经新闻、交易所动态及官方政策等，覆盖全球市场标的，可用于热点捕捉、舆情监控、研报速览、公告精读及投资决策等场景。Natural language search for financial information, covering authoritativ...

Score basis：Source needs review · Low risk signals · Claude

The Runtime Security Layer for OpenClaw/Hermes-agent, the essential safety harness for PII & sensitive credentials protection.

Score basis：Clear source · Risk needs review · Universal

NERV Operations Console aesthetic for web interfaces — Evangelion-inspired instrumentation UI skill for Claude Code / OpenClaw

Score basis：Clear source · Risk needs review · Universal

Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.

Score basis：Clear source · Risk needs review · Universal

Claw-R1: Empowering OpenClaw with Advanced Agentic RL.

Score basis：Clear source · Risk needs review · Universal