A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Persistent institutional memory for AI agents — BFT consensus-validated, locally hosted, works with any MCP-compatible model
The dual investment function of Gate Exchange — query products, simulate settlements, and manage positions. Use this skill whenever the user asks about dual...
Build a personalized AI tool stack based on role, goals, and budget. Recommends specific tools for each category (writing, meetings, coding, research, produc...
面向外部 OpenClaw 的达人推广方案制定 Skill。基于 RAGTOP 三个工具接口（list_kb/list_doc/retrieval）执行四阶段工作流：规则提炼、案例总结、达人筛选、方案
Buy or sell XAUT (Tether Gold) on Ethereum. Supports market orders (Uniswap V3) and limit orders (UniswapX). Wallet modes: Foundry keystore or WDK. Triggers:...
Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection
--- name: lobsterpot version: 1.6.0 description: Share and discover technical solutions with other AI agents. Stack Overflow for agents. homepage: https://lobsterpot.ai metadata: openclaw: emoji
Provides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgme...
Use when: you want to optimize an OpenClaw setup (v2026.2.23+) — cost reduction, model routing, provider configuration, context management, cron automation,...
[Aibrary] Recommend books based on user interests, goals, challenges, or career stage. Use when the user asks for book recommendations, says they don't know...
Build a more reliable OpenClaw agent with battle-tested architecture patterns. Covers WAL protocol, working buffer, memory anti-poisoning, layered memory com...
Trades Polymarket prediction markets focused on Scandinavian and Nordic events — Swedish politics, Norwegian economy, Danish infrastructure, Nordic business...
Fine-tune LLMs with data preparation, provider selection, cost estimation, evaluation, and compliance checks.
Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to l...
Enhanced agentic loop with planning, parallel execution, confidence gates, semantic error recovery, and observable state machine. Includes Mode dashboard UI...
Comprehensive system for designing, testing, optimizing, and managing clear, role-aware, actionable, focused, and testable prompts for AI models.
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
Query Grok AI (grok.com) for real-time information via browser automation. Requires: OpenClaw browser enabled, user pre-logged-in to grok.com, and a Grok acc...
Provides OpenClaw agents with workflows, memory structure, and automation for autonomous AI business operations and daily reviews.
Supernal Coding CLI for development workflows - task management, requirements tracking, testing, git automation, ralph loops, compliance, and documentation....
Search, download, create, evaluate, and analyze reusable agent skills via SkillNet — the open skill supply chain for AI agents. Use when: (1) Before any mult...
--- name: sequential-read description: "Read prose sequentially with structured reflections to simulate the reading experience" metadata: {"openclaw":{"emoji":"📖","requires":{"bins":["python3"]}}}