技能列表

Reviews Swift code for concurrency safety, error handling, memory management, and common mistakes. Use when reviewing .swift files for async/await patterns, actor isolation, Sendable conformance, or general Swift best practices.

Add, extend, fix, or document the Subagents panel inside the OpenClaw Control UI Agents page. Use when implementing an Agents-page Subagents tab, wiring editable subagent settings into the existing config form/save flow, exposing subagent model and fallback settings, or keeping the UI aligned with runtime subagent model precedence in src/agents/model-selection.ts.

Analyze text documents for word count, reading time, readability scores (Flesch-Kincaid, Gunning Fog), keyword density, and sentence statistics. Supports multiple languages including CJK. Zero dependencies.

Send push notifications to iOS devices via Bark. Use when you need to send a push notification to user's iPhone. Triggered by phrases like "send a notification", "push to phone", "bark notify", or when explicitly asked to send a push.

连接飞书机器人。通过接口直连发起注册会话，拿到链接（必须拼接 from=maxclaw）发给用户，等用户配置完成后告诉用户去飞书找机器人拿配对码。适用于连接飞书、接入飞书、绑定飞书机器人、创建飞书机器人、OpenClaw 接飞书等场景。

>

微信发信能力：控制本机发送微信文本或图片。触发词：给[某人]发微信、通知[某人]、把这个用微信发给[某人]、用微信发个图片"

Supply Chain Bottleneck Analyzer for Shopify/DTC stores. Diagnose cash flow, inventory, shipping costs, and customer acquisition efficiency. Includes CAC/LTV analysis, 3PL cost optimization, and ad spend benchmarks. No API key required for basic analysis.

Edit raw UGC-style footage into tighter, more usable creator and ad-ready outputs. Use when a team has talking-head, testimonial, or product demo footage that needs cleaner structure without full manual editing.

aa

Assemble modular ads from Supabase components and deploy to Facebook Ads Manager via the Marketing API. Supports preview, single/batch deploy, and status tracking. Uses ad_components table for A/B testing at scale.

Captures learnings, errors, and corrections for continuous improvement. Use when: (1) A command fails unexpectedly, (2) User corrects you ('No, that's wrong...', 'Actually...'), (3) User requests a missing capability, (4) An external API or tool fails, (5) You realize your knowledge is outdated, (6) A better approach is found for a recurring task. Also review `.learnings/` before major tasks. Trigger words: 'actually', 'wrong', 'outdated', 'I wish you could', 'why can't you', non-zero exit code.