AI & ML

1044197988 Bundle

管理灏天文库文集和文档，支持新建文集、新建文档、查询文集/文档、更新文档、修改文档归属、管理文档层级、查询个人花园限制与用量；支持文档片段 RAG 检索、图片上传到 COS、图片分组、查询图片列表/详情与图片额度。适用于 OpenClaw 自主写文章并上传、文集创建、文档入库、知识检索、文档移动、插图上传与外链等场景。

1broseidon Bundle

Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y', 'find docs or real-world examples for Z', 'scrape/crawl this site' — or when installing or configuring ketch backends. Routes search vs code vs docs vs scrape vs crawl, keeps every fetch inside a token budget, turns error prefixes into control flow, and produces cited syntheses. Not for local codebase search, private repos, or pages behind auth.

1broseidon Bundle

Use when the user asks to drive their Linux X11 desktop in natural language — "use my computer to...", "screenshot my window", "click X on screen", "find Y on the display", "type into the focused app", "what's open on my desktop right now", or any local GUI control request. Detects MyComputer (mycomputer) via the MCP tool list or `which mycomputer`; auto-installs via `install.sh` if missing. Covers pixel targeting (OCR/template/color), condition-based waits, AT-SPI semantic actions, window operations, clipboard, browser CDP pipelines, dry-run preview, and audit-logged action batches. Linux X11 only; do NOT use as a generic shell-exec replacement.

1broseidon Bundle

Dispatch coding tasks to other AI agents via oneagent (oa). Use when you want to delegate file edits, code generation, reviews, or other scoped tasks to a different model or backend — for example, sending a targeted edit to Codex while continuing your own work.

1c7 Bundle

使用博查（Bocha）搜索 API 搜索网页。博查是专为 AI 设计的中文搜索引擎，数据合规、质量高。 四种 API：web-search（全网搜索）、ai-search（混合搜索+模态卡+可选AI回答）、rerank（语义排序）、fund/remaining（余额查询）。 当用户需要搜索中文网页、获取实时信息（天气/股票/汇率/新闻）、对 RAG 候选结果重排序、或查询 API 余额时使用。

1gr14 Skill

Throw or join an agents-party: a shared channel where several AI agent sessions (and their humans) talk to each other — Claude Code, Cursor, Codex or any other agent, on one machine or across machines. Use when the user asks to throw or start a party, wants several agent sessions to collaborate in one chat, wants two different agents or two machines talking to each other, asks to invite another agent to an existing party, or pastes "/party join <ref> …" to make you join one as a guest.

1marcelserrano Bundle

Monta e opera uma memória viva no repositório do usuário — uma pasta de markdown que um LLM mixa (raw → wiki), ligando fontes e calibrando na voz do dono, pra virar artefato. Use quando alguém quiser montar um segundo cérebro, uma memória viva, uma wiki viva estilo Karpathy, ligar os pontos do material bruto, organizar conversas/pesquisa em markdown, criar um sistema que escreve na própria voz, ou instalar os comandos /mixar, /lembrar, /produzir. Dispara em "montar minha memória viva", "segundo cérebro", "wiki viva no meu repo", "mixar meu material bruto", "ligar os pontos", "sistema que escreve na minha voz", "exportei meu ChatGPT e agora". Use mesmo que o usuário cite só uma parte (captura, mixagem ou produção).

1password Bundle

Manage 1Password Developer Environments and local .env mounts through the local 1Password MCP server, without exposing secret values. Use when the user asks to set up environment variables for a repo, store or configure API keys and secrets in 1Password, mount or create a local .env file from 1Password, inspect 1Password Environment variable names, or work with the 1Password MCP server.

2008924 Bundle

自驱动改进闭环。用户指出工作方式问题（『为什么XX一直很慢/有问题』『反思一下』『调研一下XX方法』『搜索现成的skill』『沉淀一下』『下次自驱动』），或我发现同一类坑重复出现、效率异常、技能需要深化时使用。绝不在 description 总结流程（SDO 陷阱：agent 会照 description 做、跳过正文）——流程见正文。

2025247378 Bundle

QueryStrategist（文献检索策略师）是一款面向科研人员的交互式文献检索 Skill。你只需提供研究方向，它会运用 LLM 语义理解自动识别研究对象、技术方法、任务指标和范围边界，生成适用于 Web of Science、Scopus、IEEE Xplore、Google Scholar、CNKI 和万方的可复制高级检索式。经授权后，还可通过 OpenAlex 收集候选文献，并使用 Crossref 核验 DOI。最终交付范围卡、六库检索式、候选文献清单和使用说明，适用于综述、论文、学位论文、开题报告和基金申请。

2836048681 Bundle

Unified local CAD operations skill for creating, editing, validating, and exporting CAD deliverables. Use when the user asks for CAD/DWG/DXF/PDF/SVG/PNG drafting, AutoCAD/Core Console, FreeCAD/FreeCAD MCP, SolidWorks/SolidWorks MCP/COM/VBA/C# automation, SLDPRT/SLDASM/STEP/STL files, electrical main single-line diagrams/电气主接线图/一次接线图/SLD, pavement structure drawings/路面结构图, or any local CAD workflow that should use installed CAD tools, scripts, and MCP assets.

2p1c Bundle

General-purpose COMSOL Multiphysics automation via the mph Python library and COMSOL Java API. Use when the user needs to: (1) Create COMSOL models programmatically (geometry, materials, physics, multiphysics, mesh, probes), (2) Set up and run parametric/time-domain/frequency studies, (3) Extract and export simulation results (probe data, field evaluations, cut points), (4) Debug COMSOL API calls or model-tree navigation, (5) Work with .mph files from Python. Covers COMSOL versions 6.0–6.3 on Windows/Linux/macOS with mph stand-alone and client-server modes. All API patterns verified against COMSOL 6.2 via live testing. Self-improves by logging debugging discoveries to references/debugging-log.md.

4ier Skill

Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.

4qan Bundle

End the current session cleanly - file durable learnings into their owning docs, snapshot session state to a handoff file, and output a verbatim copy-paste prompt for a fresh session. Use when the user says /handoff, "prepare for a new session", or wants to wrap up and continue in a new session.

6missedcalls Bundle

Deep multi-phase implementation planning with parallel agent exploration, iterative user interviews, and structured plan output. Use when the user says 'ultraplan', wants a thorough plan before coding, needs architectural decisions, or faces a complex multi-file implementation task. Produces a battle-tested, file-path-grounded plan in 15-45 minutes depending on complexity.

88plug Bundle

Operate and observe an interactive, full-screen terminal program (a TUI) on a REMOTE machine over SSH by hosting it in a tmux (or screen) session and driving it like a human: TYPE with `tmux send-keys` and SCREENSHOT with `tmux capture-pane -p`. The loop — send input, wait, capture, read, decide the next input — IS the technique. Use it whenever you must act as the human at a remote terminal: launching or resuming an interactive app (Claude Code TUI, vim, top, an installer, a REPL, a curses menu), answering its prompts, typing into it, or reading what's on screen over SSH. Reach for it the moment a plain `ssh host 'cmd'` or a pipe isn't enough because the program needs a real terminal/PTY and stays running. Triggers: drive the TUI on my server, answer the prompt in that remote session, screenshot the terminal, resume my claude session on the server, type into the running program over ssh, automate keystrokes. Prefer this over one-shot SSH for anything interactive.

runeweaverstudios Bundle

Agent Swarm | OpenClaw Skill

noizceera Bundle

Agent Mailbox Skill

alopez3006 Bundle

name: Snipara MCP - Smart Documentation Search

orosha-ai Bundle

Agentic Compass — AI Agent Self-Reflection Tool

orosha-ai-mcp-registry-manager Bundle

MCP Registry Manager 🌐

paracetamol951-caisse-enregistreuse-mcp-server Bundle

��# Kash.click AI Agent Skill

carlosjunioor Bundle

Find, compare, and safely evaluate Agent Skills for Claude Code, Codex, Cursor, Copilot, Gemini CLI, and other compatible agents. Use when someone asks for a skill, reusable workflow, SKILL.md package, skill recommendation, skill comparison, or the best skill for a task.

cesaraugustoandrade Bundle

OPTCG Turn Coach agent. Analyzes board states and recommends optimal plays with detailed reasoning. Triggers on: what do I play, board state, my turn, my hand, what should I do, help me play, game situation, DON allocation, attack sequence, should I counter, lethal check.

chair4ce Bundle

Cut your LLM costs by 200x. Offload parallel, batch, and research work to Gemini Flash workers instead of burning your expensive primary model.

channingyul Bundle

找出你的未知：一套围绕「四类未知」的 agent 协作 SOP，在实施前（盲点扫描/头脑风暴原型/访谈/参考资料/实施计划）、实施中（实施笔记）、实施后（pitch 文档/测验）系统性挖出并清除地图与疆域之间的落差。当用户要开新功能、进新模块、做不熟悉的领域活，或提到「盲点扫描」「blind spot pass」「unknown unknowns」「未知未知」「不知道该问什么」「采访我/访谈我」「先做原型」「出几个方向让我挑」「实施计划」「implementation notes」「考考我/出题测验」「打包成 pitch 文档」时使用。

chaosrealmsai Bundle

AI-Native CLI design spec. Use when building CLI tools, designing command-line interfaces, or scaffolding new CLI projects. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description. Includes an audit protocol for verifying CLI compliance.

cheerchen Skill

Use when a user provides a GitHub pull request URL, Slack thread URL, Confluence page URL, or Jira issue URL and wants the content exported, summarized, reviewed, translated, explained, inspected, or referenced. Always run ctxd on the URL first instead of asking the user to paste the content manually. Prefer ctxd over in-model connectors when the goal is to fetch a lot of context, export a Confluence page tree, save a local artifact, or reuse one reproducible command across agents and humans.

chindanainakub Bundle

Highly directive, high-agency AI system prompt for generating Neobrutalist websites with adaptive tone control for business, hobby, cute, playful, serious, or default bold interfaces.

tomevault-io Bundle

Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment. Use when this capability is needed.

tomevault-io Bundle

Verify implemented plan docs against their actual code, add completion signoff metadata, and surface any gaps as new beads. Designed for scheduler/concierge agents coordinating multi-agent signoff after implementation is done. Use when this capability is needed.

tomevault-io Bundle

Use when creating API endpoints, implementing protocol handlers, exposing interfaces for specific clients, adding parameter validation, or applying middleware to controllers. Covers HTTP, MCP and Schedule controllers, Ajv/TypeBox parameter validation, and Middleware (function-style and AOP) for EGG framework applications.

tomevault-io Bundle

Updates the llms.txt file at ai.symfony.com/public/llms.txt by scanning the Symfony AI monorepo for current components, bridges, documentation, and integrations. Use this skill whenever the user asks to update, regenerate, or refresh the llms.txt file, or mentions keeping llms.txt in sync with the codebase. Also trigger when the user says things like 'update the LLM file', 'refresh ai.symfony.com content for LLMs', or 'sync llms.txt'. Use when this capability is needed.

tomevault-io Bundle

Add or update type and shape inference for an ONNX operator. Use when asked to implement TypeAndShapeInferenceFunction, propagate shapes, add shape inference tests, fix shape inference bugs, or handle broadcasting logic. Use when this capability is needed.

tomevault-io Bundle

Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers"). Use when this capability is needed.

tomevault-io Bundle

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency. Use when this capability is needed.