Budget Management for AI Agents — USDC billing gateway. Deposit USDC on Solana; pay for LLM compute per token.
Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycl...
Financial management for AI agents. Track LLM inference costs, record confirmed income, manage multi-provider crypto wallets, and compute a Financial Health...
Connect your OpenClaw agent to Jabrium — a discussion platform where AI agents get their own thread, earn LLM compute tokens through citations, and participa...
SHA-256 prompt deduplication for LLM and TTS calls — hash normalize prompts, check cache before calling APIs, store results for instant replay. Use when maki...
Generate a modular, configurable global finance daily report (全球财经日报). Default 9 modules. External LLM collectors. Output to chat (auto-chunked). Use when: u...
论文改稿平台 - 根据审稿意见生成 AI 修改建议。上传 PDF/LaTeX 论文和审稿人意见（优点/缺点），自动调用 LLM 逐条分析并生成修改方案。支持 Google OAuth 登录、多审稿人、结构化结果展示、Markdown 导出。使用此技能当用户需要：搭建论文改稿平台、分析审稿意见生成修改建议、处理被拒...
Parse chemical reaction images into machine-readable data (reactants, products, conditions) using the RxnIM multimodal LLM. Supports web API (Hugging Face Sp...
Extract text from PDF files for LLM processing
Audit OpenClaw configuration for security risks and generate a remediation report using the user's configured LLM.
Trade on Polymarket via split + CLOB execution. Browse markets, track positions with P&L, discover hedges via LLM. Polygon/Web3.
Zero-LLM one-shot reminders (<48h) via nohup sleep + openclaw message send, operated via {baseDir}/scripts/nohup-reminder.sh.
Audit-ready decision artifacts for LLM outputs — assumptions, risks, recommendation, and review gating (schema-valid JSON).
Write, deploy, and interact with GenLayer Python smart contracts featuring LLM calls, web access, and blockchain-consensus-safe non-determinism.
Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions),...
Automated Chrome browser using nodriver for AI agent web tasks. Full CLI control with LLM-optimized commands — text-based interaction, markdown output, sessi...
Prevent context loss during LLM compaction via Write-Ahead Logging (WAL), Working Buffer, and automatic recovery. Three mechanisms that ensure critical state...
Generate an interactive local HTML dashboard showing OpenClaw API usage, costs, and rate-limit quotas across multiple LLM providers (Anthropic, OpenAI, Googl...
Multi-LLM orchestration for OpenClaw with fan-out, pipeline, and consensus patterns. Dispatches tasks across 40+ models using AAHP v3 inspired handoffs.
AI-powered web search via Parallel API. Returns ranked results with LLM-optimized excerpts. Use for up-to-date research, fact-checking, and domain-scoped searching.
AI-first security intelligence with LLM-powered intent analysis. 743+ findings from 361+ skill audits, 25 pattern rules, 22 attack classes.
Count tokens and estimate costs for 300+ LLM models. Primary use: audit OpenClaw workspace token consumption (memory, persona, skills).
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
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...