让 AI agent 更加主动、有预见性。当用户希望 agent 更主动地提供帮助、提前发现问题、或主动汇报进展时触发。关键词：主动、积极、预见、提醒、proact
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
Fast X Intelligence CLI (Rust) — search, analyze, and engage on X/Twitter from the terminal. Use when: (1) user says "x research", "search x for", "search tw...
Coordinates multiple agents to independently argue competing approaches, then synthesizes their positions to identify the best solution for complex decisions.
Token and context window optimization — compact prompts, reduce redundancy, prioritize critical context. Use when hitting context limits or to improve agent...
Human-like LinkedIn warmup for new/cold accounts via AdsPower+CDP. Features non-deterministic behavior scripts, connect preconditions based on browsing inten...
Production-grade OCR with intelligent engine selection. Tesseract (lightweight, fast) and PaddleOCR (high accuracy, Chinese-optimized). Use when extracting t...
Security audit for multi-tenant OpenClaw Telegram bots. Checks workspace isolation, filesystem sandboxing, session scoping, auth separation, error leaking, a...
Skill lazy loading and search pack. On-demand SKILL.md loading and keyword-based skill search. 2 loader tools.
Prompt injection and jailbreak detection pack. 16 compiled regex patterns across 3 severity levels (CRITICAL, HIGH, MEDIUM). Supports single-prompt and batch...
Review and audit OpenClaw skills and agents for data risks, code execution, persistence, network access, privilege escalation, and supply-chain threats befor...
自动生成并在指定时间通过飞书推送每日研究进展报告，内容涵盖今日进展、延续项目、明日计划及系统状态，字数不超1000字。
Query Czech ARES business registry by ICO or name with human/JSON/raw outputs, retries, and legal-form decoding.
A proactive personal finance manager for AI agents. Tracks income and expenses, monitors subscriptions and bills, detects unusual spending, builds monthly bu...
AI writing partner for solopreneurs and content creators. Drafts, edits, and improves written content — emails, blog posts, newsletters, social captions, and...
Relationship intelligence for OpenClaw. Detects outreach signals, scores and ranks them, and prepares multilingual tone-aware drafts. Never sends anything —...
Zero-cost cognitive immune system for AI agents. Fires automatic pre-response reflexes that catch contradictions, scope drift, hallucinations, overengineerin...
Usage guidance and runtime diagnostics for MaxClaw / OpenClaw. Activate when: (1) User asks how to use a feature — e.g. 'how to enable Feishu long polling',...
Use when: prompt context is bloating (slow replies, rising cost, noisy transcripts) and you want a ranked offender list + reversible plan. Don't use when: yo...
WhatsApp message relay and firewall for OpenClaw agents. Intercepts messages from third parties (non-owner contacts), notifies the owner, and sends replies o...
Automates workspace tasks including summarizing recent changes, adding timestamped notes, and cleaning old log files.
Multi-layer security detector for AI agents. Blocks prompt injection, jailbreak, XSS, SQL injection, API key leaks, supply chain attacks, and deployment vuln...
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggestin...
Flutter 流畅动画实现指南 - 包含隐式/显式动画、Hero动画、交错动画、物理动画