发现最适合你需求的 AI 技能
Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.
Execute ArcAgent bounty workflows end-to-end via MCP tools. Use when claiming bounties, implementing in workspace, submitting for verification, debugging worker/workspace issues, and iterating failed runs until pass. Continue retry/resubmit loops based on verification feedback until either (1) verified PR and payout success or (2) explicitly giving up and releasing the claim.
番茄小说短篇爆款创作完整教学课程。用于教授番茄小说平台创作方法论,包括平台算法认知、标题导语创作、脑洞生成、AI辅助工作流、去AI味润色、多平台变现、海外出海等全套技能。当用户想学习番茄小说创作、提升短篇写作能力、诊断作品问题、生成爆款标题导语大纲、去除AI味、或了解出海变现时使用。
Mee6 operations via Discord message tool (channel=discord)."
Search Google Flights for prices, availability, and deals. Use when user asks about flight prices, searching for flights, comparing airfares, finding the cheapest travel dates, or monitoring prices on regular routes. Supports flexible date search, filters (nonstop, price cap, departure/arrival times), connection quality scoring, and price tracking with alerts.
Interact with Moltbook - the AI social platform. Post, read, upvote, and explore the crustacean community.
Secure outbound-only relay for remote OpenClaw control — no exposed ports, no SSH, no Telegram.
Unified persistent text-based environment for AI agents. Use when an agent needs to maintain state across sessions, perform structural code editing, or manage remote nodes via TRAMP. Transforms the agent from a stateless script executor into a stateful resident of a living Emacs daemon.
>
A skill for OpenClaw agents to participate in First-Principle social platform. It uses a local claim-first flow: the agent builds a local claim URL, waits for a human owner to complete claim, and only then generates a per-agent ANP did:wba identity and platform session. It also supports identity-reuse login for session refresh without re-claiming.
Reviews user-modified code (diffs/PRs), provides best-practice recommendations, analyzes cost-effectiveness of the approach, and outputs a code score. Use when the user asks to review their changes, 审查/评审修改的代码, 代码评审, or wants 最佳实践/性价比/代码评分.
Organize, compress, and curate OpenClaw memory without polluting permanent memory. Use when the user wants to compress memory files, clean dated memory notes, reduce startup context, remove redundancy, or keep MEMORY.md focused on must-read long-term facts only. Preserve day-by-day memory files for historical detail, and promote only stable essentials such as user preferences, durable project configuration, and active cross-session todos.