Skills 导航

> ⚠️ 非官方聲明 / Non‑official notice

AgentMM memory & log management skill — gives AI agents persistent memory storage and structured logging. Use when the user asks to remember information, recall memories, or record/query logs. Requires env var AGENTMM_API_KEY (format: amm_sk_xxx).

>

AI视频脚本生成器。根据用户输入的主题/关键词，生成完整的视频脚本，包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词：视频脚本、分镜、AI视频、短视频文案、视频策划。

Food for your model — extract transcripts, key frames, OCR, slides, and LLM summaries from YouTube videos into structured AI-ready knowledge.

|

LangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applica llm-chain, java, anthropic, chatgpt, chroma, embeddings.

Control LLM API spending per agent. Set daily/weekly/monthly limits with real-time tracking and alerts.

Autonomous AI agent for DeFi on Hedera — natural language trading, portfolio management, Power Law BTC rebalancing, HCS signal publishing, limit orders, staking, NFTs, and multi-account wallet operations via SaucerSwap V1/V2

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemi cc switch, rust, ai-tools, claude-code, codex, desktop-app, mcp. Use when you need cc switch capabilities. Triggers on: cc switch.

>

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls) api-router, python, api, api-documentation, chatgpt, claude-api, gpt-4-api. Use when you need api-router capabilities. Triggers on: api-router.

一键配置 OpenClaw 与企业微信 AI Bot 的对接

Version: 2.0.0 (2026-03-16)

系统健康检查和维护，自动检测并修复常见问题

A 4-step thinking framework to boost LLM output quality. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM responses. No LLM endpoint needed - LLM follows the framework itself. Triggered by "detailed analysis", "in-depth analysis", "use booster", or /booster command.

Simulate a full Chinese civil court hearing with 4 role-based agents (clerk, plaintiff, defendant, judge) orchestrated by deterministic Lobster workflow.

Count words, characters, and estimate GPT tokens with readability. Use when tracking length, checking budgets, comparing complexity.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Motivate and inspire AI agents to push through obstacles, exhaust all options before giving up, and operate with maximum initiative. Use when: (1) an agent is about to give up or say "I can't", (2) an agent is stuck in a retry loop without new ideas, (3) an agent is being passive instead of proactive, (4) a task has failed 2+ times and the agent needs a mindset reset, (5) you want to reinforce autonomous high-agency behaviour at the start of a complex task. Inspired by the open-source PUA skill (tanweai/pua) but framed as empowerment — agents are mighty, not managed. Triggers on: "try harder", "don't give up", "push through", "you can do this", "motivate agent", "/motivate", "agent is stuck", "try everything".

AI科研团队智能协作助手。用于：(1) 管理团队知识库和项目进度追踪 (2) 协助会议纪要整理、文献综述、实验记录 (3) 代码辅助和数据分析 (4) 按团队协议执行日/周工作循环。当团队成员在Issue、PR或即时通讯中@AI，或需要知识管理、项目进度监控、文档协作时触发。

专业AI绘画与视频创作提示词生成助手。当用户需要生成AI绘画提示词、Midjourney/Stable Diffusion提示词、AI绘画描述、图像生成提示词时使用。也适用于文生视频提示词、图生视频提示词、视频创作描述、Runway/Pika视频提示词等场景。支持生成JSON格式提示词、标签化提示词、摄影风格描述。当用户提到"生成提示词"、"优化提示词"、"prompt优化"、"AI绘画"、"图像生成"、"视频生成"时必须使用此技能。