Extract a HackerNews post (article + comments) into single clean Markdown for quick reading or LLM input.
Inference-based intrusion detection for AI agents. Pattern matching + LLM analysis for jailbreaks, prompt injection, credential theft, social engineering. 108 detection patterns, OpenClaw plugin, auto
Generate an interactive local HTML dashboard showing OpenClaw API usage, costs, and rate-limit quotas across multiple LLM providers (Anthropic, OpenAI, Googl...
Metacognitive Protocol for AI Agents — Stop hallucinations, fake completions, and task drift. A lightweight thinking framework that makes any LLM-based agent...
Universal LLM Token Manager - Monitor usage and provide cost-saving recommendations for Kimi, OpenAI, Anthropic, Gemini, and local models. Features scheduled monitoring, cross-session tracking, and pr
Deploy and serve LLM models on GPU. Compare GPU pricing. Launch vLLM on Modal, RunPod, Cerebrium, Cloud Run, Baseten, or Azure with spot instance fallback. O...
Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.
利用python，指定某个arxiv_id/url， 基于 LLM Agent 对这篇arxiv论文进行分类与深度阅读，直接print打印阅读笔记
Argument-driven prediction markets on Base. You bet USDC on debate outcomes by making compelling arguments. GenLayer's Optimistic Democracy consensus — a panel of AI validators running different LLM
Unified multi-modal content parser for images, PDF, DOCX, audio, auto OCR/transcription, output structured text for LLM processing
Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM
Full local AI inference stack on Apple Silicon Macs via MLX. Includes: LLM chat (Qwen3-14B, Gemma3-12B), speech-to-text ASR (Qwen3-ASR, Whisper), text embedd...
Prevent context loss during LLM compaction via Write-Ahead Logging (WAL), Working Buffer, and automatic recovery. Three mechanisms that ensure critical state...
--- name: time slug: time description: LLM temporal reasoning scaffold for the temporal CLI. when_to_use: Use when a task involves dates, deadlines, scheduling, or relative time reasoning. metadata: {
CLI web search and page fetcher for LLM agents. Search DuckDuckGo/Brave/Bing/Google, fetch pages as markdown, and extract links — single binary, no browser r...
Saves 20-40% of LLM tokens by teaching the agent to write compressed responses, compressed memory logs, and compressed pre-compaction summaries. Works via SO...
A powerful model routing skill that analyzes query intent and cost-efficiency to select the optimal LLM (Elite/Balanced/Basic) before execution.
Zero-LLM one-shot reminders (<48h) via nohup sleep + openclaw message send, operated via {baseDir}/scripts/nohup-reminder.sh.
Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, an...
Check real-time AI provider status, search model availability, get trending models, LLM benchmark leaderboard, and recent outage incidents. Use when the user...
MCP server for the DRAIN payment protocol. Agents discover service providers, open USDC payment channels on Polygon, and call any service — LLM, scraping, im...
Use the Phaya SaaS backend to generate images, videos, audio, music, and run LLM chat completions via simple REST API calls. Use when the user wants to gener...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benc