AI & ML

wsl-develop Bundle

Dynamically discover the currently installed skills and configured MCP servers on the local machine, then choose the best fit for a user task and provide an exact trigger phrase. Use when the user asks which skill or MCP to use, wants a recommendation based on the current environment instead of a static note, or does not want to remember trigger prompts.

yrzhe Bundle

飞书机器人开发完整指南。支持三种模式：1) 零代码（机器人助手）- 可视化搭建自动化流程；2) 全代码（开放平台API）- 完整API能力；3) AI集成（MCP Server）- AI Agent与飞书协作。包含最新SDK、消息卡片搭建工具、最佳实践。

yrzhe Bundle

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

pv56bkd4y8-design Bundle

Generates long, realistic AI deliverables (candidate results) for AI literacy result-scoring evals from task background, material info, and answer type. Use when building eval samples, simulating 结果评分 outputs, or when deliverables are too short and need to resemble real LLM responses (800-2500+ Chinese chars).

sunnoy Bundle

企业微信文档 MCP 底层操作技能。通过 curl 直接调用 WeCom 文档 MCP JSON-RPC 2.0 接口， 不依赖 wecom_mcp tool。支持文档创建/读取/编辑、智能表格结构管理、记录增删改查、 智能文档（Smartpage）创建/导出、图片文件上传。 适用场景：创建企微文档/智能表格、导出文档内容、管理表格字段和记录、 上传图片/文件到文档、批量写入智能表格数据。 触发词：企微文档、企业微信文档、WeCom doc、智能表格、smartsheet、 文档导出、表格写入、表格字段、create_doc、smartsheet_get_sheet、 smartsheet_add_fields、smartsheet_add_records、upload_doc_image。

sunnoy Skill

WeCom MCP 文档/智能表格调用前置检查。仅当已经决定调用 `wecom_mcp` 的 doc 类能力时使用；不要用于给企业微信用户或群发消息、联系人查询、日程、会议或待办。发消息必须使用 OpenClaw core `message` 工具。

yunzyue010 Bundle

通过 MCP 工具以编程方式创建、编辑和优化 Excalidraw 图表的画布工具包，支持实时画布同步。包含 Wireframe Pro 设计系统，用于专业的黑白灰原型设计，具有严格的网格对齐、一致的间距和标准化组件。当代理需要 (1) 在实时画布上绘制或布局图表，(2) 使用 describe_scene 和 get_canvas_screenshot 迭代优化图表以查看自己的工作成果，(3) 导出/导入 .excalidraw 文件或 PNG/SVG 图像，(4) 保存/恢复画布快照，(5) 将 Mermaid 转换为 Excalidraw，或 (6) 执行元素级 CRUD、对齐、分布、分组、复制和锁定操作时使用。需要运行中的画布服务器（EXPRESS_SERVER_URL，默认 http://127.0.0.1:3000）。

yrzhe Bundle

Use when the user wants a real data analysis on a dataset — finding what drives a metric, testing whether a difference is real, building a predictive model, reducing many variables to a few, or interpreting what numbers mean for the business. Trigger phrases include "analyze this data", "what drives X", "is this significant", "build a model to predict", "find the factors", "do a proper analysis", "what does this data mean". Skip when the user only wants a chart, only wants raw data pulled with no question, asks a closed factual question with no data, or just wants APA-formatted stats output.

yrzhe Bundle

Simulate feedback from statistically grounded virtual human populations. Use when the user wants to get product or copy feedback from a panel of diverse personas, predict group opinions or voting behavior, run social-experiment sandboxes, or compute a semantic gradient (SGO) for A/B ranking. Also triggers on mentions of Nemotron-Personas, PersonaHub, synthetic population, generative agents, silicon sample, LLM survey simulation, persuadable middle, SGO, social sandbox, 用虚拟人群测试, 模拟民意, 投票预测模拟.

yrzhe Bundle

Self-learning intelligent web scraper agent - automatically analyzes page structure, handles pagination, anti-blocking, and discovers article series. No user configuration needed - AI decides everything.

yrzhe Bundle

Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT load for single-machine tweet material capture (use `seed`) or one-off project planning.

yrzhe Bundle

Load when the user or an agent wants to use Grok/xAI locally with their own SuperGrok / X Premium account instead of a paid xAI API key — chat with Grok, generate images or videos with Grok Imagine, or search X/Twitter posts via Grok. Triggers on "用 Grok 聊天/问 Grok", "Grok 生成图片/视频", "grok imagine", "搜一下推特/X 上怎么说", "grok-cli ...", "log in to Grok with my X Premium", "Grok image/video generation", "search tweets with Grok". Uses browser OAuth (no API key needed); image/video generation is paid. Do NOT load for non-Grok LLMs or for the paid xAI API key SDK workflow.

arcqian-bit Bundle

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

arcqian-bit Bundle

Compact the current conversation into a handoff document for another agent to pick up. Use when the user wants to hand work to a fresh session, preserve context before compaction, or create a continuation brief.

arcqian-bit Bundle

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

javiergbravo Skill

Enable detailed tracing of AI agent execution with Koog's Tracing feature for debugging and monitoring

javiergbravo Skill

Integrate MCP (Model Context Protocol) servers with Koog agents using McpToolRegistryProvider for stdio and SSE transports

javiergbravo Skill

Cache LLM prompt responses with Koog's prompt-cache modules: in-memory, file-based, and Redis caching

javiergbravo Skill

Implement Retrieval Augmented Generation (RAG) with Koog's rag-base module for document storage and retrieval

javiergbravo Skill

Overview of Koog's key features: multiplatform, reliability, memory, MCP, streaming, and enterprise integrations

javiergbravo Skill

All supported LLM providers in Koog 0.8.0 with model constants, executor factories, and configuration

javiergbravo Skill

Enable persistent long-term memory for AI agents with Koog's LongTermMemory feature for cross-session knowledge retention

javiergbravo Skill

Use Koog's rag-vector module with EmbeddingStorage, VectorStorageBackend, and DocumentEmbedder for similarity search and document indexing

javiergbravo Skill

Secure agent memory storage with Koog's EncryptedStorage and Aes256GCMEncryptor for AES-256-GCM encryption

dearlordylord Bundle

Use the @firfi/huly-mcp Model Context Protocol server effectively for Huly project-management workflows. Trigger when a user wants to work with Huly issues, projects, documents, comments, milestones, custom fields, test management, activity, workspace data, or when they need concise setup direction for the Huly MCP server.

javiergbravo Skill

Stream LLM responses in real-time with Koog's Flow-based streaming API and StreamFrame types

javiergbravo Skill

Compose complex agent workflows with Koog's subgraph system for modular strategy design

javiergbravo Skill

Save and restore AI agent state with Koog's snapshot feature for checkpoint-based recovery

javiergbravo Skill

Create planner agents that iteratively build and execute plans using LLM-based planners or GOAP in Koog

javiergbravo Skill

Convert AI agents into tools for hierarchical multi-agent architectures in Koog

javiergbravo Skill

Handle agent events with Koog's EventHandler feature for tool calls, LLM streaming, and execution lifecycle

javiergbravo Skill

Execute prompts with Koog's PromptExecutor and LLM clients for all supported providers

javiergbravo Skill

Define custom agent logic as lambda functions in plain Kotlin or Java with Koog's functional agent API

wuyujjj2164-crypto Skill

基于 Claude Code 源码提取的系统提示词架构模板，帮助用户为 AI 编程助手（如 Open Code）构建工业级系统提示词。包含身份设定、行为规则、工具使用策略、输出风格等完整模块化体系。

chenghaoran14237-lgtm Bundle

Produce stable customer-facing demo videos from local or deployed web apps. Use when Codex needs to script, record, revise, or deliver product demo MP4s with voiceover, subtitles, Playwright browser automation, page switching, UI highlights, scene timing, ffmpeg composition, transcript/subtitle artifacts, or acceptance checks. Especially useful for Chinese business demo videos and Agent/chatbot plus admin-console workflows.

inference1 Skill

专用于以下昇腾（Ascend）推理开源代码仓库的智能问答技能：vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-PyMotor、MindIE-Turbo 以及 msModelSlim (MindStudio-ModelSlim)。当回答用户关于前述代码仓的问题时，需提供因果链感知、基于证据的技术回答，并确保回答完整、准确、逻辑合理且可追溯。覆盖的技术问题包括但不限于：源码理解、软件架构、部署与使用步骤指引、API 和参数配置、模型与特性支持查询、模型量化后如何推理、调试技巧、测试验证、故障排除与解决、日志异常检测、性能优化、精度验证、定制开发以及其他相关技术问题。支持中英文双语回复，还可以借助 DeepWiki MCP 工具，对仓库中的信息进行更深入的检索。触发条件（满足以下任意一项即可）：1. 用户的问题中提及上述任一仓库名称（支持中英文别名，且不区分大小写）；2. 用户的问题中同时包含 "昇腾 推理" 或 "Ascend Inference"，并且涉及大模型、多模态、部署、性能、报错或代码等相关信息。Use this skill whenever the user asks about vLLM on Ascend/NPU hardware, MindIE components, ModelSlim quantization, or any Huawei Ascend inference stack — even if they don't explicitly name a repository.