Build and debug Python applications using AgentScope 2.x. Consult this skill for AgentScope APIs, agent tools, multi-agent orchestration, and agent service deployment.
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新
免费在 GitHub 公开
QA_source_index
Maps 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.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（1）
- SKILL.md3.9 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Documentation and Source Code Quick Reference
When answering questions about installation, configuration, or behavioral principles, first classify by keyword, then open 1–2 paths most likely to contain the answer from the table below, avoiding aimless directory traversal.
Usage Steps
- Extract the topic from the user's question (match against the left column or synonyms in the table below).
- Resolve
$QWENPAW_ROOT: usewhich qwenpawto get the executable path. If it is…/.qwenpaw/bin/qwenpaw, the source root is three levels up (consistent with the guidance skill); otherwise, determine it from the user-provided installation path. - Read documentation first:
website/public/docs/<topic>.<language>.md(use the same language as the user:zh/en/ru, etc.). If that is insufficient, read the source entry points listed in the table.
Topic / Keywords → Preferred Documentation and Source Code
| Topic or Keywords (examples) | Preferred Documentation (website/public/docs/) | Common Source Entry Points (relative to $QWENPAW_ROOT) |
|---|---|---|
| Installation, dependencies, getting started | quickstart, intro | src/qwenpaw/cli/, pyproject.toml |
| Configuration, config.json, environment variables | config | src/qwenpaw/config/config.py, src/qwenpaw/constant.py |
| Skills, SKILL, skill_pool, built-in skills | skills | src/qwenpaw/agents/skills_manager.py, src/qwenpaw/agents/skills/ |
| MCP, plugins | mcp | src/qwenpaw/app/routers/ (grep mcp as needed) |
| Multi-agent, workspace, agent, built-in QA | multi-agent | src/qwenpaw/app/routers/agents.py, src/qwenpaw/app/migration.py, src/qwenpaw/constant.py (BUILTIN_QA_AGENT_ID, etc.) |
| Memory, MEMORY, memory_search | memory | src/qwenpaw/agents/memory/memory_manager.py, src/qwenpaw/agents/tools/memory_search.py |
| Console, frontend | console | console/ |
| CLI, subcommands, init | cli | src/qwenpaw/cli/ (e.g., init_cmd.py) |
| Channels, sessions | channels | Search for channels keyword under src/qwenpaw |
| Context, window | context | config docs + related logic in src/qwenpaw/agents/ |
| Models, API Key | models | src/qwenpaw/config/config.py |
| Heartbeat, HEARTBEAT | heartbeat | Search for heartbeat / HEARTBEAT under src/qwenpaw |
| Desktop client | desktop | desktop/ (if present in the repository) |
| Security | security | Read security.<lang>.md first |
| Errors, FAQ | faq | Read faq.<lang>.md first, then examine source code as needed |
| Commands and slash commands | commands | CLI/command registration modules under src/qwenpaw (search as needed) |
Conventions
- Full documentation path:
$QWENPAW_ROOT/website/public/docs/<topic>.<language>.md(fall back to.en.mdif the corresponding language file does not exist). - The source entry points in the table are starting points; use
read_fileor targetedgrepto narrow down to specific symbols — do not read through an entire large directory listing at once.
Notes
- This skill does not replace
read_file: after identifying candidate paths, you should immediately read and verify the content. - If a path does not exist locally (e.g., an installation tree without source code), use the installed documentation package or the root directory provided by the user, and clearly state which path you are relying on.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
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。
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新
Use 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.
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新
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。
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新
Use 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.
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
中文简介正在准备中。当前显示原文说明。
agentscope-ai/skills1302026年9月10日 更新