Skills 导航

Strategy to get recommended by ChatGPT, Claude, Perplexity, and Gemini. Use when someone wants help with LLM SEO, AI search optimization, AEO, or GEO.

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

AI 记忆栈架构 - 符合 2026 前沿的 AI 记忆系统。微调+RAG+ 上下文三层设计，mirrors 人类记忆工作方式。

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

|

> [!WARNING]

>

一键配置 OpenClaw 与企业微信 AI Bot 的对接

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".

>

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

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

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, L system prompts and models of ai tools, python, ai, bolt, cluely, copilot, cursor. Use when you need system prompts and models of ai tools capabilities. Triggers on: system prompts and models of ai tools.

Train and run text classification models using keyword-based and TF-IDF methods. Use when you need to categorize, label, or classify text data into predefined groups.

Use Chanjing AI creation APIs to submit image or video generation tasks across multiple models, inspect task status, poll async results, and explicitly download generated assets when requested.

用于排查“定时任务成功执行但结果全为 0 / 未检索到样本 / 明明有数据却日报为空”这类问题，尤其适合 Discord、Obsidian、cron、agentTurn、prompt 驱动任务、日整理、复盘脚本、采样漏扫、thread starter 漏计、主频道消息未纳入、Snowflake 字符串比较、时区时间窗边界等场景。只要用户提到“任务跑通了但产物为空”“怀疑不是分类错而是采样漏了”“想确认 prompt job 是否没有固定源码”“想定位检索链路断点”，就应触发此技能。

Stop waiting for prompts. Keep working. - Automaton Edition

>

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

AI绘画与AI视频制作的提示词生成助手。支持文生图、图生图、文生视频、图生视频、首尾帧视频等多种生成模式的提示词构建。当用户需要生成AI绘画或视频提示词时使用，包括：人物设定、环境场景、发型设计、姿势摆拍、地理位置、镜头运镜、构图视角等参数化提示词生成。支持中式风格、古风、汉服、中国风等传统美学元素。适用于即梦AI、BizyAir、Midjourney、Stable Diffusion等AI绘画/视频工具。

Use when YOU are dispatching tasks to subagents (Agent tool, openclaw, parallel workers). You become the supervisor by default. This skill guides how to monitor, intervene, and verify your subagents.

Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.