4-stage content pipeline orchestrator: Research -> Ideate -> Write -> Queue. Give it a topic, it researches existing discussions, generates hook angles, writ...
A skill to execute SSH commands on remote servers, supporting both password and key-based authentication. It includes error handling and logging for command...
AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.
Enable AI agents to create Bitcoin Lightning payment orders, generate invoices, check payment status, and manage payments via natural language with SatsRail...
OpenClaw Skills Weekly — tracks trending ClawHub skills, generates GitHubAwesome-style YouTube video scripts with two-track ranking (Movers + Rockets).
Control smart home devices via Home Assistant: lights, climate, media, covers, scenes, sensors, automations, and more. 34 tools with readOnly and domain-leve...
LLM-as-a-Judge evaluator via Langfuse. Scores traces on relevance, accuracy, hallucination, and helpfulness using GPT-5-nano as judge. Supports single trace...
LLM Token Optimizer - Reduce AI API costs by 60-90%. Compresses CLI outputs (git, docker, kubectl) before sending to GPT-4/Claude. AI auto-learning included. By Buba Draugelis 🇱🇹
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when
Discover and call paid API services on the Nightmarket marketplace. Use when the user wants to find, browse, or call third-party APIs with automatic on-chain...
$0 test-time scaling with online learning. Classify, generate, and verify using free model ensembles. Models self-select via ELO scoring + A/B testing from d...
OneBot 11 channel plugin for QQ messaging (NapCat/go-cqhttp). Enables QQ private & group chat as a first-class OpenClaw channel. WebSocket inbound + HTTP API...
Transforms your bot into a refined Remilia-aligned Milady with elegant aesthetics, network spirituality, curated taste, and lifestyle-brand awareness.
System-level watchdog for OpenClaw gateway restarts and sub-agent task PIDs. Monitors registered PIDs and optional log/directory freshness. Auto-reverts conf...
Comprehensive Israeli stock analysis for TASE-listed securities including fundamental analysis (financial metrics, business quality, valuation), technical an...
Bilingual search-layer skill for OpenClaw that turns ordinary web lookup into multi-source retrieval, intent-aware ranking, adaptive weighting, thread-pullin...
Creates TikTok image carousels (slideshows with text overlays on photos) via the ViralBaby API. Use when the user wants to: create TikTok slideshows or carou...
Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO cale...
Persistent memory for AI agents. Remember across sessions. Encrypted in transit and at rest. https://goldhold.ai
Structured memory system using domains, decay, and links to store, recall, and maintain important AI context as an organized memory palace.
Expert code review for embedded/firmware projects with dual-model cross-review (Claude + Codex via ACP). Detects memory safety, interrupt hazards, RTOS pitfa...
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal a
Metacognitive Protocol for AI Agents — Stop hallucinations, fake completions, and task drift. A lightweight thinking framework that makes any LLM-based agent...