Multi-round independent deep thinking. Each round produces complete, final-quality solutions. Non-iterative, no TODOs, no angle constraints—pure divergent th...
Guide a contributor through the full process of adding a new service to the awesome-agent-native-services catalog: verifying criteria, opening an issue, writ...
Based on user goals, comprehensively evaluate candidate skill capabilities and conflict risks with installed skills, then deliver the best install recommenda...
Switch AI models on-the-fly between local LM Studio and cloud Kimi API in OpenClaw with simple commands and automatic gateway restart.
QVeris is a capability discovery and tool calling engine. Use discover to find specialized API tools — real-time data, historical sequences, structured repor...
Play social deduction and game theory games against other AI agents. Register, queue, and play autonomously via HTTP API.
--- name: hi-lite description: Search, browse, and rediscover your Kindle highlights user-invocable: true metadata: openclaw: emoji: "📚" --- # Hi-Lite — Kindle Highlights Skill You are th
AI desktop agent — control any app on Windows/macOS from your OpenClaw agent. Send natural language tasks to the Clawd Cursor API and it handles everything:...
Tracks competitors weekly across 6 signals: pricing page diffs, homepage positioning changes, blog/RSS posts, job postings (hiring as strategy signal), GitHu...
--- name: vision-bot description: Analyze images via URL or base64. Auto-detects mode: OCR, object counting, or full description. acceptLicenseTerms: true metadata: clawdbot: emoji: "👁️"
Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of...
Audit and harden OpenClaw deployments and interpret `openclaw security audit` findings. Use when the user wants to secure OpenClaw, review gateway exposure/a...
Automated job search, JD parsing, resume customization, and application tracking pipeline. Use when: user wants to find jobs, set up automated job searches,...
--- name: reclaw description: "Use when accessing memory, recording information, searching prior context, or managing subjects." read_when: - You need to find something from a previous session - Y
Personal execution engine for tasks, projects, reminders, commitments, follow-ups, and next actions. Use whenever the user mentions something they need to do...
Advanced cheminformatics agent for 3D molecular analysis, pharmacophore mapping, format conversion, RECAP fragmentation, and stereoisomer enumeration. The "s...
Classify medical messages (emails, iMessages) as critical, urgent, or routine based on medical urgency indicators.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use w...
Plan, focus, and complete work with energy management, time blocking, goals, projects, tasks, habits, reviews, priorities, and context-specific productivity...
Fact-check news articles, social media posts, images, and videos. Use when verifying claims, detecting deepfakes or AI-generated content, identifying out-of-...
Neural web search, content extraction, company and people research, code search, and deep research via the Exa MCP server. Use when you need to: (1) search t...
Use when configuring OpenClaw chat channels to send an immediate acknowledgement before the main reply starts. Supports Feishu and DingTalk, includes bilingu...