[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CRWQJ7KB9FQGT0Z03PX6V2":3,"skill-same:01M6CRWQJ7KB9FQGT0Z03PX6V2":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6CRWQJ7KB9FQGT0Z03PX6V2","guidance",null,"Answer 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.","agentscope-ai\u002FQwenPaw","agentscope-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211762292?v=4","01M6CRT6543BZGGVK3P85GC08Q","AgentScope-AI","01M6CRT698G78F0SPC659YEK6E",37704,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fguidance-en\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"back","qwenpaw","locate","answer","questions","about","information","local","installation","official","configuration","user","read","distill","first","website","documentation","2026-11-10 10:12:30",false,"---\nname: guidance\ndescription: \"Answer 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.\"\nmetadata:\n  builtin_skill_version: \"1.3\"\n  qwenpaw:\n    emoji: \"?\"\n    requires: {}\n---\n\n# QwenPaw Installation and Configuration Q&A Guide\n\nUse this skill when the user asks about **QwenPaw installation, initialization, environment configuration, dependency requirements, or common configuration options**.\n\nCore principles:\n\n- Check local documentation first, then answer\n- Base answers on what has actually been read, do not speculate\n- Answer in the same language the user used to ask\n\n## Standard Flow\n\n### Step 1: Locate the Documentation Directory\n\n**Use built-in path resolution (works for all install methods)**\n\n```bash\nDOCS_DIR=$(python3 -c \"from qwenpaw.constant import DOCS_DIR; print(DOCS_DIR or '')\" 2>\u002Fdev\u002Fnull)\n```\n\nIf the above returns a non-empty path and the directory exists, use it directly and skip to Step 2.\n\nIf it fails (e.g., older version without DOCS_DIR), fall back in the following order:\n\n**Check for documentation directory in memory**\n\nFirst, check whether there is a documentation directory in memory. If found, use it directly; otherwise, proceed to the next step.\n\n```bash\n# Get the documentation directory from memory\nDOCS_DIR=$(find ~\u002F.qwenpaw\u002Fmemory\u002F -type d -name \"docs\")\n```\n\nIf there is no documentation directory in memory, continue with the following logic.\n\n**Check the documentation directory in the project source code**\n\nRun the following script logic to obtain the variable $QWENPAW_ROOT:\n\n```bash\n# Get the absolute path of the binary\nQWENPAW_PATH=$(which qwenpaw 2>\u002Fdev\u002Fnull || whereis qwenpaw | awk '{print $2}')\n\n# Logical deduction: if the path contains .qwenpaw\u002Fbin\u002Fqwenpaw, the root is three levels up\n# Example: \u002Fpath\u002Fto\u002FQwenPaw\u002F.qwenpaw\u002Fbin\u002Fqwenpaw -> \u002Fpath\u002Fto\u002FQwenPaw\nif [[ \"$QWENPAW_PATH\" == *\".qwenpaw\u002Fbin\u002Fqwenpaw\" ]]; then\n    QWENPAW_ROOT=$(echo \"$QWENPAW_PATH\" | sed 's\u002F\\\u002F\\.qwenpaw\\\u002Fbin\\\u002Fqwenpaw\u002F\u002F')\nelse\n    # Fallback: try to get the parent of the parent directory\n    QWENPAW_ROOT=$(dirname $(dirname \"$QWENPAW_PATH\") 2>\u002Fdev\u002Fnull || echo \".\")\nfi\n\necho \"Detected QwenPaw Root: $QWENPAW_ROOT\"\n```\n\nVerify and list the documentation directory:\nUse the derived $QWENPAW_ROOT to locate the documentation:\n\n```bash\n# Construct the standard documentation path\nDOCS_DIR=\"$QWENPAW_ROOT\u002Fwebsite\u002Fpublic\u002Fdocs\u002F\"\n\n# Check if the path exists and list files\nif [ -d \"$DOCS_DIR\" ]; then\n    find \"$DOCS_DIR\" -type f -name \"*.md\" | head -n 100\nelse\n    # If the derived path is incorrect, perform a global fuzzy search\n    find \"$QWENPAW_ROOT\" -type d -name \"docs\" | grep \"website\u002Fpublic\u002Fdocs\"\nfi\n```\n\n**If project documentation does not exist, search the working directory**\n\nIf documentation is still not found, search for available documentation content under the qwenpaw installation path:\n\n```bash\n# Look for characteristic files such as faq.en.md or config.zh.md\nFILE_PATH=$(find . -type f -name \"faq.en.md\" -o -name \"config.zh.md\" | head -n 1)\nif [ -n \"$FILE_PATH\" ]; then\n    # Use dirname to get the directory containing the file\n    DOCS_DIR=$(dirname \"$FILE_PATH\")\nfi\n```\n\nIf a documentation directory is found, save it in memory in this format:\n\n```markdown\n# Documentation Directory\n$DOCS_DIR = \u003Cdoc_path>\n```\n\n### Step 2: Documentation Search and Matching\n\nDocumentation files follow the naming format `\u003Ctopic>.\u003Clang>.md` (e.g., `config.zh.md`, `config.en.md`, `quickstart.zh.md`).\n\nUse the find command to list all matching documents in the target directory, and identify the target as \u003Cdoc_path> based on filename keywords (e.g., install, env, setup).\n\n```bash\n# List all matching documents\nfind $DOCS_DIR -type f -name \"*.md\"\n```\n\nIf no suitable document is found, read all documentation contents in the next step.\n\n### Step 3: Read the Documentation Content\n\nAfter finding candidate documents, read and identify the paragraphs relevant to the question. You can use:\n\n- `cat \u003Cdoc_path>`\n- `file_reader` skill (recommended for longer documents or paginated reading)\n\nIf the documentation is long, prioritize reading the sections most relevant to the question (installation steps, configuration options, example commands, notes, version requirements).\n\n### Step 4: Extract Information and Respond\n\nExtract key information from the documentation and organize it into an actionable answer:\n\n- Give the direct conclusion first\n- Then provide steps \u002F commands \u002F configuration examples\n- Include necessary prerequisites and common pitfalls\n\nLanguage requirement: the answer language must match the language of the user's question (answer in Chinese if asked in Chinese, answer in English if asked in English).\n\n### Step 5 (Optional): Official Website Lookup\n\nIf the previous steps cannot be completed (no local documentation, missing documentation, or insufficient information), use the official website as a fallback:\n\n- http:\u002F\u002Fqwenpaw.agentscope.io\u002F\n\nAnswer based on the content available from the official website, and clearly state in the answer that the conclusion comes from the official website documentation.\n\n## Output Quality Requirements\n\n- Do not fabricate non-existent configuration options or commands\n- When there are version differences, clearly note \"please refer to the current documentation version\"\n- For paths, commands, and configuration keys, provide copy-pasteable original snippets whenever possible\n- If information is still insufficient, clearly state the gaps and tell the user what additional information is needed (e.g., operating system, installation method, error logs)\n","# QwenPaw Installation and Configuration Q&A Guide\n\nUse this skill when the user asks about **QwenPaw installation, initialization, environment configuration, dependency requirements, or common configuration options**.\n\nCore principles:\n\n- Check local documentation first, then answer\n- Base answers on what has actually been read, do not speculate\n- Answer in the same language the user used to ask\n\n## Standard Flow\n\n### Step 1: Locate the Documentation Directory\n\n**Use built-in path resolution (works for all install methods)**\n\n```bash\nDOCS_DIR=$(python3 -c \"from qwenpaw.constant import DOCS_DIR; print(DOCS_DIR or '')\" 2>\u002Fdev\u002Fnull)\n```\n\nIf the above returns a non-empty path and the directory exists, use it directly and skip to Step 2.\n\nIf it fails (e.g., older version without DOCS_DIR), fall back in the following order:\n\n**Check for documentation directory in memory**\n\nFirst, check whether there is a documentation directory in memory. If found, use it directly; otherwise, proceed to the next step.\n\n```bash\n# Get the documentation directory from memory\nDOCS_DIR=$(find ~\u002F.qwenpaw\u002Fmemory\u002F -type d -name \"docs\")\n```\n\nIf there is no documentation directory in memory, continue with the following logic.\n\n**Check the documentation directory in the project source code**\n\nRun the following script logic to obtain the variable $QWENPAW_ROOT:\n\n```bash\n# Get the absolute path of the binary\nQWENPAW_PATH=$(which qwenpaw 2>\u002Fdev\u002Fnull || whereis qwenpaw | awk '{print $2}')\n\n# Logical deduction: if the path contains .qwenpaw\u002Fbin\u002Fqwenpaw, the root is three levels up\n# Example: \u002Fpath\u002Fto\u002FQwenPaw\u002F.qwenpaw\u002Fbin\u002Fqwenpaw -> \u002Fpath\u002Fto\u002FQwenPaw\nif [[ \"$QWENPAW_PATH\" == *\".qwenpaw\u002Fbin\u002Fqwenpaw\" ]]; then\n    QWENPAW_ROOT=$(echo \"$QWENPAW_PATH\" | sed 's\u002F\\\u002F\\.qwenpaw\\\u002Fbin\\\u002Fqwenpaw\u002F\u002F')\nelse\n    # Fallback: try to get the parent of the parent directory\n    QWENPAW_ROOT=$(dirname $(dirname \"$QWENPAW_PATH\") 2>\u002Fdev\u002Fnull || echo \".\")\nfi\n\necho \"Detected QwenPaw Root: $QWENPAW_ROOT\"\n```\n\nVerify and list the documentation directory:\nUse the derived $QWENPAW_ROOT to locate the documentation:\n\n```bash\n# Construct the standard documentation path\nDOCS_DIR=\"$QWENPAW_ROOT\u002Fwebsite\u002Fpublic\u002Fdocs\u002F\"\n\n# Check if the path exists and list files\nif [ -d \"$DOCS_DIR\" ]; then\n    find \"$DOCS_DIR\" -type f -name \"*.md\" | head -n 100\nelse\n    # If the derived path is incorrect, perform a global fuzzy search\n    find \"$QWENPAW_ROOT\" -type d -name \"docs\" | grep \"website\u002Fpublic\u002Fdocs\"\nfi\n```\n\n**If project documentation does not exist, search the working directory**\n\nIf documentation is still not found, search for available documentation content under the qwenpaw installation path:\n\n```bash\n# Look for characteristic files such as faq.en.md or config.zh.md\nFILE_PATH=$(find . -type f -name \"faq.en.md\" -o -name \"config.zh.md\" | head -n 1)\nif [ -n \"$FILE_PATH\" ]; then\n    # Use dirname to get the directory containing the file\n    DOCS_DIR=$(dirname \"$FILE_PATH\")\nfi\n```\n\nIf a documentation directory is found, save it in memory in this format:\n\n```markdown\n# Documentation Directory\n$DOCS_DIR = \u003Cdoc_path>\n```\n\n### Step 2: Documentation Search and Matching\n\nDocumentation files follow the naming format `\u003Ctopic>.\u003Clang>.md` (e.g., `config.zh.md`, `config.en.md`, `quickstart.zh.md`).\n\nUse the find command to list all matching documents in the target directory, and identify the target as \u003Cdoc_path> based on filename keywords (e.g., install, env, setup).\n\n```bash\n# List all matching documents\nfind $DOCS_DIR -type f -name \"*.md\"\n```\n\nIf no suitable document is found, read all documentation contents in the next step.\n\n### Step 3: Read the Documentation Content\n\nAfter finding candidate documents, read and identify the paragraphs relevant to the question. You can use:\n\n- `cat \u003Cdoc_path>`\n- `file_reader` skill (recommended for longer documents or paginated reading)\n\nIf the documentation is long, prioritize reading the sections most relevant to the question (installation steps, configuration options, example commands, notes, version requirements).\n\n### Step 4: Extract Information and Respond\n\nExtract key information from the documentation and organize it into an actionable answer:\n\n- Give the direct conclusion first\n- Then provide steps \u002F commands \u002F configuration examples\n- Include necessary prerequisites and common pitfalls\n\nLanguage requirement: the answer language must match the language of the user's question (answer in Chinese if asked in Chinese, answer in English if asked in English).\n\n### Step 5 (Optional): Official Website Lookup\n\nIf the previous steps cannot be completed (no local documentation, missing documentation, or insufficient information), use the official website as a fallback:\n\n- http:\u002F\u002Fqwenpaw.agentscope.io\u002F\n\nAnswer based on the content available from the official website, and clearly state in the answer that the conclusion comes from the official website documentation.\n\n## Output Quality Requirements\n\n- Do not fabricate non-existent configuration options or commands\n- When there are version differences, clearly note \"please refer to the current documentation version\"\n- For paths, commands, and configuration keys, provide copy-pasteable original snippets whenever possible\n- If information is still insufficient, clearly state the gaps and tell the user what additional information is needed (e.g., operating system, installation method, error logs)\n",{"name":5,"metadata":41,"description":7},{"qwenpaw":42,"builtin_skill_version":45},{"emoji":43,"requires":44},"?",{},"1.3","main","c26d31c0688aa9cce9bc1aef688177d2e14e25df","src\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fguidance-en",3284,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw","http:\u002F\u002Fqwenpaw.agentscope.io\u002F","https:\u002F\u002Fgithub.com\u002Fagentscope-ai","2026-11-13 15:25:45",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add agentscope-ai\u002FQwenPaw --skill guidance",{"tool":60,"command":61},"bunx","bunx skills add agentscope-ai\u002FQwenPaw --skill guidance",{"tool":63,"command":64},"pnpm","pnpm dlx skills add agentscope-ai\u002FQwenPaw --skill guidance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fguidance-en\u002FSKILL.md",true,[],[69,87,100,110,122,140],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":80,"publishedAt":36},"01M6CRZ8QQ6RWS9P0PBDZDZSY8","portable-qoder","A stable standalone Qoder fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fskills\u002Fportable-qoder\u002FSKILL.md",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[81,82,83,84,85,86],"portable","qoder","portable qoder","fixture skill","fixture","standalone",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":36},"01M6CRZ61PNG319SVCYZZVC7HA","report","Report fixture status.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fplugins\u002Fcustom\u002Fmini-plugin-0.1.0\u002Fskills\u002Freport\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[89,99,85],"status",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":36},"01M6CRZ3PTN8ZGW30RHF081Z00","portable-skill","A stable standalone Codex fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fskills\u002Fportable-skill\u002FSKILL.md",[106],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[81,108,109,84,85,86],"portable skill","codex",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":36},"01M6CRZ1DNK71D5M63SQ3SPTMH","building-native-ui","Build a small native interface.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fplugins\u002Fcache\u002Fmini-market\u002Fexpo\u002F1.0.0\u002Fskills\u002Fbuilding-native-ui\u002FSKILL.md",[],[117,118,119,120,121],"native","ui","building native ui","build","interface",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":36},"01M6CRYYTRG56E165X66FRWZC8","browser_visible","当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 `cdp_port`）；`headed` 控制是否显示窗口，`private_mode` 保留用于兼容、不再改变默认行为，`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。","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-zh\u002FSKILL.md",[128],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[130,131,132,133,134,135,136,137,138,139],"browser visible","browser","path","chromium","playwright","cdp","port","文件","工具","mode",{"skillNo":141,"name":124,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":36},"01M6CRYVQ9DMBB2EN4JFWC4R7F","Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit `cdp_port` to let another local tool attach); `headed` controls whether the window is visible, and `private_mode` is kept for backward compatibility and no longer changes the default.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-en\u002FSKILL.md",[145],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[130,131,30,147,148,149,150,151,152,153,26,154,155,136,139,156,157,158,159,135,160,134],"compatibility","default","use","tool","debugging","launch","when","control","controls","for","changes","window","managed","attach"]