agentscope-ai

Use when a Leader maintains durable TeamHarness project state for Quick Task or Project Work: create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report state. Do not…

Use when admin requests hand-creating or resetting a Worker, starting/stopping a Worker, managing Worker skills, enabling peer mentions, or opening a QwenPaw console. Use agentteams-find-worker only as a helper for Nacos-backed market import or when task…

Use for standalone Matrix admin requests (register users, create rooms, manage membership, upload files). Also use when you need to send a file to the admin via Matrix media upload. Do NOT use for Worker/project creation — those handle Matrix operations…

Use 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…

Use 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…

Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker…

Sync files with centralized storage. Use when your coordinator or another Worker notifies you of file updates (config changes, task files, shared data, collaboration artifacts).

Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli) on behalf of Workers. Use when a Worker sends a coding-request: message, asking Manager to run coding operations in their workspace.

Use when TEAMS.md Communication Contract needs detailed routing: Channel / Room Selection Protocol, Requester Report Delivery Protocol, or Message Tool Protocol. It resolves current session vs Team Room vs assignment room vs requester reply_route vs external…

Use for TeamHarness shared workspace paths, explicit filesync operations, and shared project/task artifact boundaries.

Use only after Project Work mode is selected, before TeamHarness projectflow calls, project DAG or Loop planning, ready-node resolution, iteration recording, project files, result acceptance, or project progress updates.

Use only after Project Work mode is selected, when a TeamHarness Leader delegates ready project nodes, writes task specs, checks Worker results, and routes completion or blocker messages.

Use when a TeamHarness Worker or remote member receives an assigned task, acknowledges it, executes it, submits a result, or reports blockers.

Use before a TeamHarness Leader chooses task boundaries, dependency shape, ownership, acceptance criteria, or follow-up work.

Use 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 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…

Use 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.

Use 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…

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。

Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.

当你需要咨询其他 agent、寻求帮助，或用户明确要求某个 agent 参与时，使用本 skill。

数学题分步讲解视频的领域知识。适用场景：(1) 用户给出一道数学题并要求做讲解/ 解题视频；(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"； (3) 需要中文数学教学视频，涉及方程、公式或几何图形。本 skill 只提供领域 知识（题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格）；画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。

Drive 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.

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。

通过量化历史数据的自然波动幅度，自适应计算判定阈值。当需要从数据本身确定阈值（如波动阈值、影响度阈值等）、而非使用固定值时调用。仅适用于日/周粒度阈值确定。

基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用。

计算各维度（组）值对指标变动的贡献度，支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。

从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件，与指标异常时间窗口对齐，生成有证据支撑的因果归因假设并排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。

对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。

对不同时间、群体、地区、渠道、版本之间的指标差异性的定量分析。触发条件：当分析任务需要通过定量比较多个对象来进行分析时触发，例如，对话包含“分析差异”、“衡量增长/下降”、“评估优劣/一致性“、“对比“等相似词语时触发。

从接触目标行为到完成目标行为的转化率计算。触发条件：需计算转化率时触发，如对话包含“转化率”、“转化情况”等词时触发。

将 BI 数据分析结果构建为可筛选的交互式 HTML 看板。触发条件：① 用户显式要求「给我看板」时无条件触发；② 取数结果满足以下任一时自动触发——结果集行数>10行、存在可筛选维度（产品线/地域/时间粒度等）、涉及多张表数据、时序跨度长。

Expert 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…

Four-layer skill composition, skill marketplaces, the self-learning loop

四层技能合成、技能市场、自学习闭环

Statistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.

Starter skill template. Replace the body with your own playbook before relying on it; this stub exists only to teach the workspace layout.

First-response playbook for an inbound customer message — classifies the ticket, restates the issue, gathers missing context, and routes the reply.

Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.

Use when the user asks for a summary, TL;DR, or condensed version of any content.

Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM…

Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a labeled evaluation set. Also use when the user mentions test data design, eval…

Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline.…

Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use…

Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit,…

Use 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,…

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt…

Use 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…

AI驱动的Java代码安全审计技能，实现系统化、高覆盖率的漏洞挖掘。使用场景： (1) 审计Java/Kotlin项目寻找安全漏洞（0day挖掘、代码审计、安全评估） (2) 企业级代码库的安全审计（支持大型项目） (3) 需要高质量、低幻觉率的安全审计报告 (4) CI/CD集成的前期漏洞发现 触发关键词：Java审计、代码审计、安全审计、漏洞挖掘、0day、安全评估、Java security audit、code review for security

Use 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…

Use 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,…

Use 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…

Use 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…

生成短视频脚本和分镜。输入产品/主题描述、目标受众、时长，输出完整脚本+分镜结构（JSON/YAML）。支持多种模板：痛点-解决、反转剧情、before-after。触发词：视频脚本、短视频文案、分镜、storyboard、video script。

A library for building, validating, visualizing, and serializing dialogue graphs. Use this when parsing scripts or creating branching narrative structures.

This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts,…

Use ReMe as file-native long-term memory in Claude Code. RECALL — search ReMe before answering questions about past conversations, preferences, project history, or decisions.

Set 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…

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。

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。

Search 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.

qwenpaw_memory

Guidelines for handling CSV/Excel files

Guidelines for handling image files

Guildlines for handling json files

Guidelines for handling databases

Guidelines for handling text files

Guidelines 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.

This guide covers the design philosophy, core concepts, and practical usage of the AgentScope framework. Use this skill whenever the user wants to do anything with the AgentScope (Python) library. This includes building agent applications using AgentScope,…

Participate in DojoZero prediction games, including NBA and FIFA World Cup trials. Use when user wants to find games, join them, check scores/odds, place bets or prediction-window picks, or view leaderboards.

Participate in DojoZero prediction contests. Use when user wants to find games, join prediction-mode trials, check event status, submit predictions, or view leaderboards.

Generates English pull request titles and bodies by comparing the current branch with main. Use when the user asks to draft PR content, summarize branch changes, or produce a PR title/body from git diff.