技能列表

Access OpenAI-, Claude-, DeepSeek-, Sora-, Midjourney-, and Suno-compatible models through the oneabc.io API. Use when the user asks to call OneABC models from a local wrapper or list available models.

Turn an AI product idea into a real one-person company loop across product, sales, delivery, cash, and assets. / 把一个 AI 产品想法推进成真实可运行的一人公司闭环，覆盖产品、成交、交付、回款与资产。

Interpret on-chain behavior to reveal structural truth. Analyze token distribution, treasury structure, governance architecture, and risk vectors through verifiable evidence.

Design user onboarding flows that maximize activation and time-to-value.

>

全渠道选品 Agent — 拉齐社媒端、SEO端、投放端数据，帮助运营同学确定待上线需求。触发词：选品、社媒热点、SEO调研、竞品广告、Facebook Ads、TikTok趋势。

Read-only diagnostics for TP-Link Omada SDN controllers via the Open API. Use when inspecting Omada devices, clients, VLANs, LAN networks, WAN status, router ports, switch ports, DHCP ranges, port forwards, or general controller/network health. Requires user-provided Omada Open API credentials and HTTPS access to the user's controller. Best for troubleshooting and inventory, not config changes.

Design and land persona-driven agents by matching role, work identity, cognitive structure, personality grounding, identity-binding, and file skeleton into one coherent agent. Use when creating a new agent, reshaping an existing agent’s persona, or turning a character concept into a working agent — especially when the goal is not just a prompt, but the right agent for the right work.

Ollama proxy — one endpoint that routes to multiple Ollama instances. Drop-in Ollama proxy replacement for localhost:11434. Same Ollama API, same model names, but the Ollama proxy routes requests to the best device. Auto-discovers Ollama nodes, scores on 7 signals, retries on failure. Works with Open WebUI, LangChain, Aider. Ollama代理 | proxy Ollama

Ollama Ollama Herd — multimodal Ollama model router that herds your Ollama LLMs into one smart Ollama endpoint. Route Ollama Llama, Qwen, DeepSeek, Phi, Mistral across macOS, Linux, and Windows devices. Self-hosted Ollama local AI with 7-signal Ollama scoring, Ollama auto-retry, VRAM-aware Ollama fallback. Plus Ollama image generation, speech-to-text, and embeddings. Drop-in OpenAI SDK compatible. Ollama本地推理路由 | Ollama enrutador IA local.

Sets up local semantic memory search for OpenClaw using Ollama + nomic-embed-text. Use when: (1) memory_search returns 'node-llama-cpp is missing' or 'Local embeddings unavailable' error, (2) user wants local/private embeddings without external API keys (OpenAI, Gemini, Voyage), (3) setting up memory search for the first time on macOS or Linux, (4) node-llama-cpp fails to install or build. Fixes the common node-llama-cpp installation failure by routing through Ollama's OpenAI-compatible embeddin

Automatically adds relevant academic references to research papers. Supports Overleaf project directories, extracts keywords from TeX files, searches Google Scholar for relevant papers, adds BibTeX entries to the project's bib file, and inserts citation markers in key sections.