跳到主要内容

QA_source_index 精选

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.

自动化 Codex CLIMCP 客户端 Apache-2.0 3.6 万
在 GitHub 打开

安装方式

cp -r src/qwenpaw/agents/skills/QA_source_index-en ~/.claude/skills/qa-source-index-en

把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同,Claude Code 默认是 ~/.claude/skills/

整仓一次性获取:git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git

依赖与权限

  • 需要 API Key —— 使用前需配置相应的密钥环境变量
  • 无需联网
  • 依赖外部命令:python3
  • 以上为按正文与 frontmatter 自动推断的信号,仅供参考;安装前建议先阅读原文。

SKILL.md 正文

来源 agentscope-ai/QwenPaw@02b6a6d · 许可 Apache-2.0 · 内容未修改

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

  1. Extract the topic from the user's question (match against the left column or synonyms in the table below).
  2. Resolve $QWENPAW_ROOT: use which qwenpaw to 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.
  3. Resolve $DOCS_DIR first (cross-install compatible): run python3 -c "from qwenpaw.constant import DOCS_DIR; print(DOCS_DIR or '')" 2>/dev/null. If it returns a valid path, use it directly. Otherwise, fallback to $QWENPAW_ROOT/website/public/docs/.
  4. Read documentation first: $DOCS_DIR/<topic>.<language>.md (use the same language as the user: zh / en.). 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 ($DOCS_DIR/)Common Source Entry Points (relative to $QWENPAW_ROOT)
Installation, dependencies, getting startedquickstart, introsrc/qwenpaw/cli/, pyproject.toml
Configuration, config.json, environment variablesconfigsrc/qwenpaw/config/config.py, src/qwenpaw/constant.py
Skills, SKILL, skill_pool, built-in skillsskillssrc/qwenpaw/agents/skill_system/, src/qwenpaw/agents/skills/
MCP, pluginsmcpsrc/qwenpaw/app/routers/ (grep mcp as needed)
Multi-agent, workspace, agent, built-in QAmulti-agentsrc/qwenpaw/app/routers/agents.py, src/qwenpaw/app/migration.py, src/qwenpaw/constant.py (BUILTIN_QA_AGENT_ID, etc.)
Memory, MEMORY, memory_searchmemorysrc/qwenpaw/agents/memory/memory_manager.py, src/qwenpaw/agents/tools/memory_search.py
Console, frontendconsoleconsole/
CLI, subcommands, initclisrc/qwenpaw/cli/ (e.g., init_cmd.py)
Channels, sessionschannelsSearch for channels keyword under src/qwenpaw
Context, windowcontextconfig docs + related logic in src/qwenpaw/agents/
Models, API Keymodelssrc/qwenpaw/config/config.py
Heartbeat, HEARTBEATheartbeatSearch for heartbeat / HEARTBEAT under src/qwenpaw
Desktop clientdesktopdesktop/ (if present in the repository)
SecuritysecurityRead security.<lang>.md first
Errors, FAQfaqRead faq.<lang>.md first, then examine source code as needed
Commands and slash commandscommandsCLI/command registration modules under src/qwenpaw (search as needed)

Conventions

  • Full documentation path: $DOCS_DIR/<topic>.<language>.md (fall back to .en.md if the corresponding language file does not exist). Prefer DOCS_DIR from qwenpaw.constant; fallback to $QWENPAW_ROOT/website/public/docs/.
  • The source entry points in the table are starting points; use read_file or targeted grep to 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.

质量与来源

所属仓库
agentscope-ai/QwenPaw
仓库星标
3.6 万
最近更新
今天
采集时间
今天
commit
02b6a6d088e3
内容指纹
sha256:da0b9d22e29ba0b
文件路径
src/qwenpaw/agents/skills/QA_source_index-en/SKILL.md

同仓库其它 Skill

查看全部 48 个
edu-math-tutorial
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。
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
professional-media-prompts
为 Creator 编译制作级视觉资产图、电影分镜图和参考生视频 Prompt。适用于 角色身份板/设定图、关键帧或多宫格分镜、短片动作节拍、R2V/I2V/T2V 提示词, 尤其适合要求角色一致性、镜头语言、参考图职责、Seedance 时间段或声音设计的 任务。不用于纯素材剪辑、只查询模型参数,或只评价已经生成的成片。
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
visual-asset-design
为角色/场景/道具设计视觉资产、编写或修复 VisualVariant 与阵容图的生成 Prompt 时使用。涵盖参考图布局(艺术身份板/序列关键帧/环境研究板/道具研究 板)、构图与镜头语言、图片审核误判规避、实体 continuity 与以主图为参考 的跨 Variant 衍生设计。不用于视频 Prompt 编译(见 professional-media-prompts)、 纯素材剪辑或只评价已生成产物。
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
alicloud_cli
阿里云 CLI 中文文档镜像检索与命令辅助:先走章节索引,再下钻正文页面,给出命令前必须有本地文档证据。
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
terraform-cli-setup
Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装,确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置,凭证在实际使用时由 terraform-skill 引导。
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code architecture decisions
精选 agentscope-ai/QwenPaw 3.6 万 原文
Codex CLIMCP 客户端
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI
presentation-structure
Knowledge about the presentation slide format, weight system, navigation, and section structure
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI
presentation-styling
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API
精选 shanraisshan/claude-code-best-practice 6.7 万 原文
Claude CodeCodex CLIGemini CLI