agentscope-ai
- 289 skills
- 0 followers
- 38k repo stars
- 23 hours ago last updated
- ▌ File Sharing · agentscope-aiUse before filesync calls for project directories, global-shared inputs, non-task shared files, listing shared paths, or troubleshooting missing files. Do not use for task-level sync; taskflow delegate_task and check_task handle task directory sync internally.
- ▌ File Sharing 2 · agentscope-aiUse before direct filesync calls, reading non-task shared files, pushing mid-task progress, or troubleshooting missing shared files. Do not use for normal task acceptance or submission; taskflow ack_task and submit_task handle lifecycle sync internally.
- ▌ Organization 2 · agentscope-aiUse only when you need to look up team topology, worker phase, runtime state, or identity that is NOT available from the current message context. Do not use for standard task flows — the coordinator is the message sender, and the task room is in meta.json.room_id.
- ▌ Find Skills 2 · agentscope-ai bundleDiscover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.
- ▌ Mcporter 5 · agentscope-aiDiscover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.
- ▌ Communication · agentscope-aiUse before sending or suppressing any Leader message to Workers, Manager, or Team Admin. Always use this skill for cross-room Matrix messages, @mention decisions, task assignment notifications, structured status reports, completion reports, blocker/revision messages, questions, requester updates, or when deciding whether a same-room reply is enough.
- ▌ Communication 2 · agentscope-aiUse before sending @mentions, deciding whether to reply, TASK_COMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.
- ▌ File Sync 3 · agentscope-ai bundleSync files with centralized storage. Use when your coordinator or another Worker notifies you of file updates (config changes, task files, shared data, collaboration artifacts).
- ▌ Higress Gateway Management · agentscope-ai bundleManage the Higress AI Gateway via its Console API (consumers, routes, AI providers, MCP servers). Use when creating consumers, configuring routes, or managing AI gateway settings.
- ▌ Task Progress 2 · agentscope-aiUse when executing a task (progress logging, plan updates), when resuming a task after session reset, or when managing task history. Covers progress log format, task-history.json, and resume flow.
- ▌ Task Management 2 · agentscope-ai bundleUse before any Leader taskflow call or task-level workflow involving delegating a ready DAG or Loop node, writing task meta/spec, checking a Worker task result, handling result statuses, task directory ownership, or Worker result contracts. Always use this skill when the request mentions delegate_task, check_task, task result.md, task spec.md, BLOCKED, REVISION_NEEDED, INTERRUPTED, SUCCESS, or assigning/delegating a Worker task.
- ▌ Task Management 3 · agentscope-aiUse before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID, shared/tasks, spec.md, meta.json, result.md, deliverables, BLOCKED, REVISION_NEEDED, SUCCESS, submit_task, or ack_task.
- ▌ Find Skills 3 · agentscope-ai bundleDiscover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.
- ▌ Project Participation · agentscope-aiUse when you are invited to a Project Room or assigned a task within a multi-worker project. Covers project plan reading, task coordination with other Workers, and git author config.
- ▌ Team Coordination · agentscope-aiUse before deciding how you should organize team work: DAG vs Loop, dependency shape, task waves, quality gates, acceptance criteria, interruption, replanning, or what to do after Worker results arrive. Always use this skill for team organization strategy before you call project-management or task-management.
- ▌ Workerflow Internal Workflow · agentscope-aiUse when a QwenPaw-backed Worker needs to decide whether to do work directly, use native subagents for internal parallelism, or create a temporary QwenPaw agent with a custom AGENTS.md and skills.
- ▌ Task Progress 3 · agentscope-aiUse when executing a task (progress logging, plan updates), when resuming a task after session reset, or when managing task history. Covers progress log format, task-history.json, and resume flow.
- ▌ Project Management 2 · agentscope-ai bundleUse before any projectflow call or Team Leader workflow involving Project state, Project lifecycle, DAG planning, Loop planning, ready node checks, pause/resume/complete, project recovery, heartbeat project checks, or project-level result aggregation. Always use team-coordination first when the question is how to organize the work.
- ▌ Project Participation 2 · agentscope-aiUse when you are invited to a Project Room or assigned a task within a multi-worker project. Covers project plan reading, task coordination with other Workers, and git author config.
- ▌ Project Participation 3 · agentscope-aiUse when you are invited to a Project Room or assigned a task within a multi-worker project. Covers project plan reading, task coordination with other Workers, and git author config.
- ▌ PDF · agentscope-ai bundleUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
- ▌ PDF 2 · agentscope-ai bundle当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。
- ▌ DOCX · agentscope-ai bundleUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
- ▌ DOCX 2 · agentscope-ai bundle当用户需要创建、读取、编辑或处理 Word 文档(.docx)时,使用此技能。触发场景包括提到“Word 文档”、“.docx”,或要求生成带目录、标题、页码、信头等格式的专业文档;也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注,以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物,也应使用此技能。不要用于 PDF、电子表格、Google Docs,或与文档生成无关的一般编程任务。
- ▌ PPTX · agentscope-ai bundleUse this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
- ▌ PPTX 2 · agentscope-ai bundle当涉及到 .pptx 文件的任何操作时使用此技能——无论是作为输入、输出还是两者兼有。包括:创建幻灯片、演示文稿或路演材料;读取、解析或提取任何 .pptx 文件中的文本(即使提取的内容将用于其他地方,如邮件或摘要);编辑、修改或更新现有演示文稿;合并或拆分幻灯片文件;处理模板、布局、演讲者备注或批注。当用户提到“演示文稿”、”幻灯片“、”PPT“或引用 .pptx 文件名时触发,无论他们之后打算如何使用内容。如果需要打开、创建或操作 .pptx 文件,就使用此技能。
- ▌ XLSX · agentscope-ai bundleUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
- ▌ XLSX 2 · agentscope-ai bundle当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要:打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件(例如添加列、计算公式、格式化、制图、清理混乱数据);从头创建新的电子表格或从其他数据源创建;或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及(如"我下载目录里的 xlsx")——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件(格式错误的行、错位的表头、垃圾数据)清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets API 集成时不触发,即使涉及表格数据也不触发。
- ▌ Browser · agentscope-aiDrive a live browser with async Python against QwenPaw's builtin Browser SDK. The full reference is below; re-load this browser skill after context compaction.
- ▌ Browser 2 · agentscope-ai用异步 Python 调用 QwenPaw 内置 Browser SDK 驱动真实浏览器。完整参考在下方;上下文压缩后请重新加载此 browser skill。
- ▌ Mailbox 2 · agentscope-ai当用户需要任何邮箱/邮件操作时使用此技能——包括查看、阅读、搜索、发送、回复、转发、整理或删除邮件,管理会话线程,绑定个人邮箱或注册新邮箱。此技能是邮件任务的统一且唯一入口,通过 qwenpawmail-mcp 编排操作,当前支持 9 个个人邮箱域名。
- ▌ Make Skill · agentscope-ai bundleCreate a focused workspace Skill from reusable decisions, knowledge, templates, or workflows in the current conversation. Use for /make-skill with a focus argument and requests such as save this workflow or turn this into a skill; do not use for one-off summaries or ordinary file creation.
- ▌ Make Skill 2 · agentscope-ai bundle将当前对话中可复用的决策、知识、模板或工作流创建为聚焦的 workspace Skill。适用于带 focus 参数的 /make-skill,以及“保存这个流程”“把它做成 skill”等请求;不适用于一次性总结或普通文件创建。
- ▌
- ▌ Computer Use · agentscope-aiUse computer_use for live Windows or macOS GUI work that structured tools cannot complete. Discover an approved app and window, act from fresh observations, and verify every requested result.
- ▌ Tushare Data · agentscope-ai bundle面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
- ▌ Reme Memory 2 · agentscope-aiUse ReMe as file-native long-term memory in Claude Code. RECALL — search ReMe before answering questions about past conversations, preferences, project history, or decisions.
- ▌ Harness 2 · agentscope-ai bundleFour-layer skill composition, skill marketplaces, the self-learning loop
- ▌
- ▌ Cron 2 · agentscope-ai仅在需要未来定时执行或周期执行任务时,使用本 skill。使用 qwenpaw cron list/create/get/state/pause/resume/delete/run 管理任务,并始终显式传入 --agent-id。
- ▌ News 2 · agentscope-ai为用户从指定新闻网站查找最新新闻。提供政治、财经、社会、国际、科技、体育和娱乐类别的权威 URL。使用 browser_use 打开每个 URL 并通过 snapshot 获取内容,然后为用户总结。
- ▌
- ▌ Himalaya 2 · agentscope-ai bundle通过 IMAP/SMTP 管理邮件的命令行工具。使用 `himalaya` 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML(MIME Meta Language)撰写邮件。
- ▌ Browser Cdp 2 · agentscope-ai当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 `cdp_port`,或让多个 agent / 工具共享同一个浏览器时,使用本 skill。当前 browser_use 默认已使用 managed CDP 启动浏览器;如果用户不希望暴露浏览器历史、Cookies 等敏感信息,推荐改用 `private_mode=true` 的隐私模式。
- ▌ File Reader · agentscope-ai仅用于读取和总结文本类文件。文本格式优先使用 read_file;需要做类型探测时使用 execute_shell_command。PDF、Office、图片和压缩包由其他技能处理。
- ▌ Browser Visible 2 · agentscope-ai当用户需要控制 browser_use 的浏览器启动方式时,使用本 skill。当前 browser_use 默认使用 managed CDP 启动本地 Chrome/Chromium;`headed` 控制是否显示窗口,`private_mode` 控制是否禁用 CDP、改走 Playwright,`browser_args` 传入额外的 Chromium 启动参数,`executable_path` 指定自定义浏览器可执行文件路径。
- ▌
- ▌ QA Source Index 2 · agentscope-ai将用户问题中的主题、关键词映射到 QwenPaw 官方文档路径与常见源码入口,减少盲目搜索。适用于内置 QA Agent 在回答安装、配置、技能、MCP、多智能体、记忆、CLI 等问题时快速选定要读的文件。
- ▌ Reme Memory · agentscope-aiSet up and use ReMe as a file-native long-term memory system through the reme CLI. Use when an Agent needs to detect whether ReMe is installed or running, install and configure ReMe, start or verify its local service, retrieve prior context, or write and consolidate durable memory.
- ▌ Serper Search · agentscope-aiSearch the public web through Serper instead of the built-in WebSearch tool. Use when an agent needs current information, general web sources, or URLs not available from local files and project APIs. SERPER_API_KEY is available in the environment.
- ▌
- ▌ Dingtalk Message · agentscope-ai bundle钉钉消息发送技能。支持企业内部机器人(批量单聊/群聊)和 Webhook 自定义机器人两种接入方式,支持多机器人管理,支持文本、Markdown、链接、ActionCard、FeedCard等多种消息类型。
- ▌ Agentscope Java · agentscope-ai bundleExpert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
- ▌ Harness · agentscope-ai bundle一个 skill 就是一份写好的能力包:一个目录里放一份 `SKILL.md`(说明用途、给 agent 看的指令),可以再带一些参考文档、脚本或样例。写好后丢给 agent,它会在合适的时候自己用。
- ▌ Log Parser · agentscope-ai bundleUse this skill when the task involves inspecting, searching, or extracting information from application log files. Suitable for tasks like "my application is crashing and I need to find the errors", "scan these logs for warnings", "extract all exceptions from this log file", or "find slow requests in my server logs". Triggered by debugging, incident investigation, or log analysis needs.
- ▌ Data Report · agentscope-ai bundleUse this skill when the task involves analyzing data to compute statistics, aggregations, or summaries, and presenting the results as a report. Suitable for tasks like "summarize this dataset", "calculate averages and totals", "generate a weekly sales report", or "show me trends in this data". Do NOT use for simple format conversion between file types.
- ▌ Image Resize · agentscope-ai bundleUse this skill when the task involves resizing, scaling, or compressing image files. Suitable for tasks like "resize these photos to 800px wide", "compress images to reduce file size", or "batch scale all JPEGs in a folder". Only relevant for image processing tasks — do NOT use for data files, text, or non-image tasks.
- ▌ Git Changelog · agentscope-ai bundleUse this skill when the task involves generating a changelog, release notes, or commit summary from a Git repository's history. Suitable for tasks like "generate a changelog for v2.0", "summarize what changed since last release", or "create release notes from git commits". Requires access to a Git repository.
- ▌ Data Transform · agentscope-ai bundleUse this skill when the task involves converting or reformatting structured data between file formats such as CSV, JSON, XML, or YAML. Suitable for tasks like "convert this CSV to JSON", "reformat my data file", or "change the file format of this dataset". Do NOT use for statistical analysis, aggregation, or report generation.
- ▌
- ▌
- ▌ Summarizer · agentscope-aiUse when the user asks for a summary, TL;DR, or condensed version of any content.
- ▌ Data Analysis · agentscope-aiStatistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.
- ▌ Apply Patch · agentscope-aiApply multi-file or tricky edits atomically with git apply instead of many fragile edit_file calls. Use when changing several files at once or when edit_file fails to match.
- ▌ Code Search · agentscope-aiSearch a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
- ▌ Triage Ticket · agentscope-aiFirst-response playbook for an inbound customer message — classifies the ticket, restates the issue, gathers missing context, and routes the reply.
- ▌ Git Checkpoint · agentscope-aiUse git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
- ▌ Verify Changes · agentscope-aiVerify code changes by running the project's typecheck, build, lint, and targeted tests, then fix and re-run until clean. Use after editing any source file.
- ▌ SQL Analysis · agentscope-aiAnswer a quantitative business question by writing a SQL query against the data warehouse, validating it, and presenting the result. Use when the user asks "how many...", "what's the trend of...", "compare X vs Y over...", "what's our top N...", or anything that resolves to a query against tabular data. Produces a small result table plus the underlying query.
- ▌ Chart Rendering · agentscope-aiVisualise the result of an analysis as a chart (line, bar, area, scatter, etc.). Use when the user asks to "plot...", "chart...", "show me the trend of...", "visualise...", or when a numerical result has more than ~10 rows and would be easier to read as a picture. Produces an image file plus the script that generated it.
- ▌ Synthesize Report · agentscope-aiProduces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
- ▌ Cron · agentscope-aiUse this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.
- ▌ News · agentscope-aiLook up the latest news for the user from specified news sites. Provides authoritative URLs for politics, finance, society, world, tech, sports, and entertainment. Use browser_use to open each URL and snapshot to get content, then summarize for the user.
- ▌ Guidance · agentscope-aiAnswer user questions about QwenPaw installation and configuration: first locate and read local documentation, then distill the answer; if local information is insufficient, fall back to the official website documentation.
- ▌ Himalaya · agentscope-ai bundleCLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
- ▌ Nano Memory · agentscope-aiGuidelines and workflows for the agent to maintain persistent memory using native file tools (read_file, write_file, edit_file) and standard OS commands for searching.
- ▌
- ▌ Browser Cdp · agentscope-aiUse this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a `cdp_port`, or share a single browser across multiple agents/tools. By default, browser_use already launches the browser using managed CDP; if the user does not want to expose browser history, cookies, or other sensitive data, recommend using `private_mode=true` instead.
- ▌ Agentscope Skill · agentscope-ai bundleBuild and debug Python applications using AgentScope 2.x. Consult this skill for AgentScope APIs, agent tools, multi-agent orchestration, and agent service deployment.
- ▌ Browser Visible · agentscope-aiUse this skill when the user needs to control the browser launch mode for browser_use. By default, browser_use launches the local Chrome/Chromium using managed CDP; `headed` controls whether the window is visible, and `private_mode` controls whether CDP is disabled in favor of Playwright.
- ▌ Channel Message · agentscope-ai当需要主动向用户、会话或频道单向发送消息时,使用本 skill。通常仅在用户明确要求向某个 channel / 会话发送消息,或需要主动通知时使用。先用 qwenpaw chats list 查询 session,再用 qwenpaw channels send 推送消息。
- ▌ Chat With Agent · agentscope-aiUse this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.
- ▌ QA Source Index · agentscope-aiMaps topics and keywords from user questions to QwenPaw official documentation paths and common source code entry points, reducing blind searching. Intended for the built-in QA Agent to quickly identify which files to read when answering questions about installation, configuration, skills, MCP, multi-agent, memory, CLI, etc.
- ▌ Dingtalk Channel Connect · agentscope-ai使用可视浏览器自动完成 QwenPaw 的钉钉频道接入。适用于用户提到钉钉、DingTalk、开发者后台、Client ID、Client Secret、机器人、Stream 模式、绑定或配置 channel 的场景;支持遇到登录页时暂停,等待用户登录后继续。
- ▌ Multi Agent Collaboration · agentscope-ai当需要其他 agent 的专长、上下文或协作支持,或用户明确要求调用其他 agent 时,使用本 skill。先查询可用 agents,再用 qwenpaw agents chat 进行双向沟通。
- ▌ Mailbox · agentscope-aiUse this skill whenever the user needs ANY mailbox/email operation — checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox. This skill is the single entry point for email tasks and orchestrates qwenpawmail-mcp for nine supported personal-mail domains.
- ▌ RAG Eval · agentscope-ai bundleUse when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.
- ▌ Redteam · agentscope-ai bundleUse when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.
- ▌ Mmx CLI · agentscope-aiGenerate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when the user needs to create AI-generated multimedia content, produce narrated audio from text, compose music, or search the web through MiniMax AI services.