技能列表

Audit your information diet across HN and RSS feeds — beautiful reports with category breakdowns, ASCII charts, and personalized recommendations.

Make your OpenClaw agent portable and persistent. Version-controls SOUL.md, MEMORY.md, and all core knowledge files using git with automatic GitHub push — so your agent's identity, memory, and operating rules are backed up and can be restored on any machine by cloning the repo. Use whenever core knowledge files are modified to commit and push changes. Also use when asked to show history, diff a file, or revert a change. Watch your assistant evolve over time through its git history.

Cryptographic identity for AI agents. Register on-chain identity, sign messages, verify other agents, link platform accounts. Stake USDC to prove you're real. Built by g1itchbot for the USDC Hackathon.

Write Bulgarian that sounds human. Not formal, not robotic, not AI-generated.

Support accounting understanding from basic bookkeeping to professional practice and research.

Send beautifully formatted HTML emails via gog CLI with templates and styling

Analyzes the evolution memory graph for stagnation patterns, recurring failures, and success plateaus. Generates actionable insights to guide future evolution cycles.

Complete MBA curriculum with structured learning, case studies, financial analysis, and practical business decision-making.

Agent web access acceleration layer — reads any URL as structured JSON. Cache-first (public library hit = 0 tokens). The smart alternative to raw web_fetch.

内容研究写作助手。进行研究、添加引用、改进开头、迭代大纲、提供实时反馈。触发词：写文章、内容创作、文案、博客。翻译自 ComposioHQ。

Fail-closed OpenClaw security toolkit (public-safe). Use to prevent accidental or unexpected data leakage by running local-only checks: default-deny allowlists, lightweight secret/token scans, egress-risk pattern scans, and prompt/document injection pattern scans. Use when preparing GitHub/ClawHub publishing, reviewing skills/scripts for risky behavior, or validating inbound text/doc content before tool execution.

>