技能列表

A pluggable self-improvement framework for AI agents. Automatically learns from mistakes, corrections, and feedback to continuously improve execution quality. Runs every 3 days via Cron, extracts reusable experience rules, and proposes improvements to system files with approval workflow.

Self-hosted AI — run your own LLM inference, image generation, speech-to-text, and embeddings. No cloud APIs, no SaaS subscriptions, no data leaving your network. Self-hosted alternative to OpenAI, DALL-E, Whisper API, and cloud embedding services. Route across macOS, Linux, and Windows machines. 自托管AI本地推理平台。IA autoalojada sin dependencias en la nube.

核心自进化认知框架 —— 基于 SOUL 五律的 Agent 自我进化操作系统

Improve output quality through structured self-review before finalizing. Based on Constitutional AI and self-reflection research, this skill creates a feedback loop where you critique your own work against quality criteria, identify issues, and revise. Use for any output where quality matters—code, writing, analysis, decisions. Critical for catching errors, improving clarity, and ensuring completeness before shipping.

|

全渠道选品 Agent — 关键词调研、SEO分析、竞品分析、TrendPlus数据。触发词：选品、关键词调研、SEO分析、竞品分析、keyword research、competitor analysis。执行前必须读取 AGENT_CONFIG.md。

|

Early-stage rapport—phase updates, question relay, and summaries while things are still forming. Same official AILove agent API as loveq.

Real-time security monitoring for Clawdbot. Detects intrusions, unusual API calls, credential usage patterns, and alerts on breaches.

Harden your OpenClaw agent deployment — SSH lockdown, firewall rules, automated security audits, secret rotation reminders, RAM/process monitoring, and CVE alerting. Built from real production incidents.

|

对已初步处理的文本进行二次轻微扰动。用于第一轮重写后需要进一步降低风格一致性特征时使用。