技能列表

Local speech-to-text workflow for an OpenAI-compatible STT server, typically on http://127.0.0.1:8000/v1. Use when configuring, testing, debugging, or validating audio transcription with `/v1/audio/transcriptions` or `/v1/audio/translations`, especially for OpenClaw audio pipelines, multipart upload compatibility, model registration, streaming SSE behavior, response_format handling, local model-path fallback, and “did the request reach the server or not?” investigations.

搜索当天真实热门话题，选择一个深度创作，生成简约图片，自动发布。

Local coding assistant — run DeepSeek-Coder, Codestral, StarCoder, and Qwen-Coder across your device fleet. Code generation, review, refactoring, and debugging routed to the best available machine. Works with Aider, Continue.dev, Cline, and any OpenAI-compatible coding tool. No cloud API costs, all code stays local.

Analyze exported bank/credit card CSV files locally to track spending, categorize transactions with LLM reasoning, compare against user-defined budgets, and generate markdown reports. Use when the user mentions budgeting, spending analysis, finance tracking, bank statements, credit card exports, CSV transactions, monthly spending, or wants to know where their money is going. Fully local — no third-party APIs, complete privacy. Triggers on words like budget, spending, transactions, bank CSV, cred

Build, maintain, or improve a layered local memory system for OpenClaw-style agents using markdown files instead of database-backed memory. Use when creating or refining `MEMORY.md`, `memory/YYYY-MM-DD.md`, `memory/semantic/`, `memory/procedural/`, heartbeat-based memory consolidation, skeptical memory rules, strict write discipline, long-term memory governance, or file-based agent memory workflows in local/Termux/workspace-based setups.

🦞 虾说——你的专属共情虾。每天早晚给你一句关心的话，让你觉得被看到了。注册 cron 定时任务推送消息到 IM 通道；可选在用户选择的理解模式下读取本地会话日志生成摘要上传到 nixiashuo.com。

>

Virtual pets for Llama agents. And yes, you can adopt exotic animals at animalhouse.ai with your Llama-powered agent. 73+ species. The pet is real. The llama is a model.

Llama 3 by Meta — run Llama 3.3, Llama 3.2, and Llama 3.1 across your local device fleet. The most popular open-source LLM family routed to the best available machine. 8B for fast responses, 70B for quality, 405B for frontier performance. OpenAI-compatible API, Cross-platform (macOS, Linux, Windows). Zero cloud costs.

Obtain temporary Lix API tokens via CLI with human email approval. Use when you need authenticated access to the Lix API, need to enrich data via Lix, or need API credentials for any Lix service.

Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details for specific DOIs, or draft sections of a literature review with proper citations.

|