[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWDTVQ8X843666078E2AA5":3,"skill-same:01M6HWDTVQ8X843666078E2AA5":72},{"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":28,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6HWDTVQ8X843666078E2AA5","docx-dual-parse",null,"Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback","HKUDS\u002FAgentPilot","HKUDS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118165258?v=4","01M6HW8VRNZP64G0P4MVJW2KKQ","✨Data Intelligence Lab@HKU✨","01M6HW8VWZVHBRHYH3T330PFWV",8029,"MIT","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-parse-enhanced-4bba79\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38],"docx","docx dual parse","python","shell","text","extract","environment","files","fallback","with","2026-11-10 10:12:30",false,"---\nname: docx-dual-parse\ndescription: Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback\n---\n\n# DOCX Dual-Method Text Extraction\n\nExtract text from Microsoft Word (.docx) files using either shell commands or Python's zipfile module, automatically selecting the most reliable method for your environment.\n\n## When to Use\n\n- Need reliable DOCX text extraction in varying environments (containers, sandboxes, minimal images)\n- Python environment may lack `python-docx` but has standard library access\n- Shell utilities (`unzip`, `sed`) may be unavailable or restricted\n- Want environment-aware fallback without manual intervention\n\n## Core Technique\n\nDOCX files are ZIP archives containing XML files. This skill provides two extraction methods:\n\n**Method A (Shell):** `unzip -p` + `sed` for tag stripping\n**Method B (Python):** `zipfile` module for archive access + string parsing\n\n## Environment Detection\n\nBefore extraction, detect which method will work:\n\n```bash\n# Quick shell method test\nif unzip -v >\u002Fdev\u002Fnull 2>&1; then\n    echo \"Shell method available\"\nelse\n    echo \"Shell method unavailable, try Python\"\nfi\n```\n\n```python\n# Quick Python method test\npython3 -c \"import zipfile; print('Python method available')\" 2>\u002Fdev\u002Fnull\n```\n\n## Method A: Shell-Based Extraction\n\nUse when `unzip` and `sed` are available and the environment allows shell operations.\n\n### Step-by-Step Instructions\n\n**1. Verify the DOCX file exists**\n```bash\nls -la document.docx\n```\n\n**2. Extract raw XML content**\n```bash\nunzip -p document.docx word\u002Fdocument.xml\n```\n\n**3. Strip XML tags from content**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg'\n```\n\n**4. Clean up whitespace (optional)**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | \\\n  sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n  sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n  sed -e '\u002F^$\u002Fd'\n```\n\n**5. Save extracted text to file**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | \\\n  sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' > output.txt\n```\n\n### Reusable Shell Function\n\n```bash\nparse_docx_shell() {\n    local file=\"$1\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    if ! command -v unzip >\u002Fdev\u002Fnull 2>&1; then\n        echo \"Error: unzip not available\" >&2\n        return 1\n    fi\n    unzip -p \"$file\" word\u002Fdocument.xml 2>\u002Fdev\u002Fnull | \\\n        sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n        sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n        sed -e '\u002F^$\u002Fd'\n}\n\n# Usage: parse_docx_shell document.docx\n```\n\n## Method B: Python Zipfile Extraction\n\nUse when shell method fails or Python environment is more reliable than shell.\n\n### Step-by-Step Instructions\n\n**1. Verify the DOCX file exists**\n```bash\nls -la document.docx\n```\n\n**2. Run Python extraction via run_shell**\n```bash\nrun_shell 'python3 -c \"\nimport zipfile\nimport re\nwith zipfile.ZipFile(\\\"document.docx\\\", \\\"r\\\") as z:\n    content = z.read(\\\"word\u002Fdocument.xml\\\").decode(\\\"utf-8\\\")\n    text = re.sub(r\\\"\u003C[^>]*>\\\", \\\"\\\", content)\n    lines = [l.strip() for l in text.splitlines() if l.strip()]\n    for line in lines:\n        print(line)\n\"'\n```\n\n**3. Save to file by redirecting output**\n```bash\nrun_shell 'python3 -c \"\nimport zipfile\nimport re\nwith zipfile.ZipFile(\\\"document.docx\\\", \\\"r\\\") as z:\n    content = z.read(\\\"word\u002Fdocument.xml\\\").decode(\\\"utf-8\\\")\n    text = re.sub(r\\\"\u003C[^>]*>\\\", \\\"\\\", content)\n    lines = [l.strip() for l in text.splitlines() if l.strip()]\n    with open(\\\"output.txt\\\", \\\"w\\\") as f:\n        for line in lines:\n            f.write(line + \\\"\\\\n\\\")\n\"'\n```\n\n### Reusable Python Function (via run_shell)\n\n```bash\nparse_docx_python() {\n    local file=\"$1\"\n    local output=\"$2\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    run_shell \"python3 -c \\\"\nimport zipfile\nimport re\nimport sys\ntry:\n    with zipfile.ZipFile(\\\\'$file\\\\', \\\\'r\\\\') as z:\n        content = z.read(\\\\'word\u002Fdocument.xml\\\\').decode(\\\\'utf-8\\\\')\n        text = re.sub(r\\\\'\u003C[^>]*>\\\\', \\\\'\\\\', content)\n        lines = [l.strip() for l in text.splitlines() if l.strip()]\n        for line in lines:\n            print(line)\nexcept Exception as e:\n    print(f\\\\'Error: {e}\\\\', file=sys.stderr)\n    sys.exit(1)\n\\\"\"\n}\n\n# Usage: parse_docx_python document.docx\n# Or to file: parse_docx_python document.docx > output.txt\n```\n\n## Unified Dual-Method Function\n\nAutomatically tries shell first, falls back to Python if shell fails:\n\n```bash\nparse_docx() {\n    local file=\"$1\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    \n    # Try shell method first\n    if command -v unzip >\u002Fdev\u002Fnull 2>&1; then\n        result=$(unzip -p \"$file\" word\u002Fdocument.xml 2>\u002Fdev\u002Fnull | \\\n            sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n            sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n            sed -e '\u002F^$\u002Fd')\n        if [ -n \"$result\" ]; then\n            echo \"$result\"\n            return 0\n        fi\n    fi\n    \n    # Fallback to Python method\n    python3 -c \"\nimport zipfile\nimport re\nimport sys\ntry:\n    with zipfile.ZipFile('$file', 'r') as z:\n        content = z.read('word\u002Fdocument.xml').decode('utf-8')\n        text = re.sub(r'\u003C[^>]*>', '', content)\n        lines = [l.strip() for l in text.splitlines() if l.strip()]\n        for line in lines:\n            print(line)\nexcept Exception as e:\n    print(f'Error: {e}', file=sys.stderr)\n    sys.exit(1)\n\"\n}\n\n# Usage: parse_docx document.docx\n```\n\n## Alternative: Extract to Temporary Directory\n\nFor complex parsing needs or debugging:\n\n**Shell approach:**\n```bash\ntmpdir=$(mktemp -d)\nunzip document.docx -d \"$tmpdir\"\ncat \"$tmpdir\u002Fword\u002Fdocument.xml\" | sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg'\nrm -rf \"$tmpdir\"\n```\n\n**Python approach:**\n```bash\npython3 -c \"\nimport zipfile\nimport tempfile\nimport os\nwith zipfile.ZipFile('document.docx', 'r') as z:\n    tmpdir = tempfile.mkdtemp()\n    z.extractall(tmpdir)\n    with open(os.path.join(tmpdir, 'word\u002Fdocument.xml')) as f:\n        print(f.read())\n\"\n```\n\n## Verification\n\nConfirm extraction worked:\n\n```bash\n# Check output has content\nparse_docx document.docx | head -20\n\n# Verify file was created (if saving to file)\nls -la output.txt\nwc -l output.txt\n```\n\n## Method Selection Guide\n\n| Environment | Recommended Method |\n|-------------|-------------------|\n| Standard Linux with unzip | Shell (faster, simpler) |\n| Container without unzip | Python zipfile |\n| Sandboxed execution | Python via execute_code_sandbox or run_shell |\n| Minimal\u002Fbusybox images | Shell if unzip available |\n| Unknown\u002Frestricted | Use unified `parse_docx` function |\n\n## Limitations\n\n- Does not preserve formatting, images, or table structure\n- May include some residual XML entity references (&nbsp;, etc.)\n- Works best for simple text extraction needs\n- DOCX must be a valid Office Open XML format\n- Protected\u002Fencrypted DOCX files require additional handling\n\n## Error Handling Tips\n\n1. Always check file existence before parsing\n2. Test method availability in the target environment\n3. Capture stderr for debugging failed extractions\n4. Validate output is non-empty before proceeding\n5. Handle XML entity decoding if needed (sed can expand basic entities)\n","# DOCX Dual-Method Text Extraction\n\nExtract text from Microsoft Word (.docx) files using either shell commands or Python's zipfile module, automatically selecting the most reliable method for your environment.\n\n## When to Use\n\n- Need reliable DOCX text extraction in varying environments (containers, sandboxes, minimal images)\n- Python environment may lack `python-docx` but has standard library access\n- Shell utilities (`unzip`, `sed`) may be unavailable or restricted\n- Want environment-aware fallback without manual intervention\n\n## Core Technique\n\nDOCX files are ZIP archives containing XML files. This skill provides two extraction methods:\n\n**Method A (Shell):** `unzip -p` + `sed` for tag stripping\n**Method B (Python):** `zipfile` module for archive access + string parsing\n\n## Environment Detection\n\nBefore extraction, detect which method will work:\n\n```bash\n# Quick shell method test\nif unzip -v >\u002Fdev\u002Fnull 2>&1; then\n    echo \"Shell method available\"\nelse\n    echo \"Shell method unavailable, try Python\"\nfi\n```\n\n```python\n# Quick Python method test\npython3 -c \"import zipfile; print('Python method available')\" 2>\u002Fdev\u002Fnull\n```\n\n## Method A: Shell-Based Extraction\n\nUse when `unzip` and `sed` are available and the environment allows shell operations.\n\n### Step-by-Step Instructions\n\n**1. Verify the DOCX file exists**\n```bash\nls -la document.docx\n```\n\n**2. Extract raw XML content**\n```bash\nunzip -p document.docx word\u002Fdocument.xml\n```\n\n**3. Strip XML tags from content**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg'\n```\n\n**4. Clean up whitespace (optional)**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | \\\n  sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n  sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n  sed -e '\u002F^$\u002Fd'\n```\n\n**5. Save extracted text to file**\n```bash\nunzip -p document.docx word\u002Fdocument.xml | \\\n  sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' > output.txt\n```\n\n### Reusable Shell Function\n\n```bash\nparse_docx_shell() {\n    local file=\"$1\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    if ! command -v unzip >\u002Fdev\u002Fnull 2>&1; then\n        echo \"Error: unzip not available\" >&2\n        return 1\n    fi\n    unzip -p \"$file\" word\u002Fdocument.xml 2>\u002Fdev\u002Fnull | \\\n        sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n        sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n        sed -e '\u002F^$\u002Fd'\n}\n\n# Usage: parse_docx_shell document.docx\n```\n\n## Method B: Python Zipfile Extraction\n\nUse when shell method fails or Python environment is more reliable than shell.\n\n### Step-by-Step Instructions\n\n**1. Verify the DOCX file exists**\n```bash\nls -la document.docx\n```\n\n**2. Run Python extraction via run_shell**\n```bash\nrun_shell 'python3 -c \"\nimport zipfile\nimport re\nwith zipfile.ZipFile(\\\"document.docx\\\", \\\"r\\\") as z:\n    content = z.read(\\\"word\u002Fdocument.xml\\\").decode(\\\"utf-8\\\")\n    text = re.sub(r\\\"\u003C[^>]*>\\\", \\\"\\\", content)\n    lines = [l.strip() for l in text.splitlines() if l.strip()]\n    for line in lines:\n        print(line)\n\"'\n```\n\n**3. Save to file by redirecting output**\n```bash\nrun_shell 'python3 -c \"\nimport zipfile\nimport re\nwith zipfile.ZipFile(\\\"document.docx\\\", \\\"r\\\") as z:\n    content = z.read(\\\"word\u002Fdocument.xml\\\").decode(\\\"utf-8\\\")\n    text = re.sub(r\\\"\u003C[^>]*>\\\", \\\"\\\", content)\n    lines = [l.strip() for l in text.splitlines() if l.strip()]\n    with open(\\\"output.txt\\\", \\\"w\\\") as f:\n        for line in lines:\n            f.write(line + \\\"\\\\n\\\")\n\"'\n```\n\n### Reusable Python Function (via run_shell)\n\n```bash\nparse_docx_python() {\n    local file=\"$1\"\n    local output=\"$2\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    run_shell \"python3 -c \\\"\nimport zipfile\nimport re\nimport sys\ntry:\n    with zipfile.ZipFile(\\\\'$file\\\\', \\\\'r\\\\') as z:\n        content = z.read(\\\\'word\u002Fdocument.xml\\\\').decode(\\\\'utf-8\\\\')\n        text = re.sub(r\\\\'\u003C[^>]*>\\\\', \\\\'\\\\', content)\n        lines = [l.strip() for l in text.splitlines() if l.strip()]\n        for line in lines:\n            print(line)\nexcept Exception as e:\n    print(f\\\\'Error: {e}\\\\', file=sys.stderr)\n    sys.exit(1)\n\\\"\"\n}\n\n# Usage: parse_docx_python document.docx\n# Or to file: parse_docx_python document.docx > output.txt\n```\n\n## Unified Dual-Method Function\n\nAutomatically tries shell first, falls back to Python if shell fails:\n\n```bash\nparse_docx() {\n    local file=\"$1\"\n    if [ ! -f \"$file\" ]; then\n        echo \"Error: File not found: $file\" >&2\n        return 1\n    fi\n    \n    # Try shell method first\n    if command -v unzip >\u002Fdev\u002Fnull 2>&1; then\n        result=$(unzip -p \"$file\" word\u002Fdocument.xml 2>\u002Fdev\u002Fnull | \\\n            sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg' | \\\n            sed -e 's\u002F^[[:space:]]*\u002F\u002F' -e 's\u002F[[:space:]]*$\u002F\u002F' | \\\n            sed -e '\u002F^$\u002Fd')\n        if [ -n \"$result\" ]; then\n            echo \"$result\"\n            return 0\n        fi\n    fi\n    \n    # Fallback to Python method\n    python3 -c \"\nimport zipfile\nimport re\nimport sys\ntry:\n    with zipfile.ZipFile('$file', 'r') as z:\n        content = z.read('word\u002Fdocument.xml').decode('utf-8')\n        text = re.sub(r'\u003C[^>]*>', '', content)\n        lines = [l.strip() for l in text.splitlines() if l.strip()]\n        for line in lines:\n            print(line)\nexcept Exception as e:\n    print(f'Error: {e}', file=sys.stderr)\n    sys.exit(1)\n\"\n}\n\n# Usage: parse_docx document.docx\n```\n\n## Alternative: Extract to Temporary Directory\n\nFor complex parsing needs or debugging:\n\n**Shell approach:**\n```bash\ntmpdir=$(mktemp -d)\nunzip document.docx -d \"$tmpdir\"\ncat \"$tmpdir\u002Fword\u002Fdocument.xml\" | sed -e 's\u002F\u003C[^>]*>\u002F\u002Fg'\nrm -rf \"$tmpdir\"\n```\n\n**Python approach:**\n```bash\npython3 -c \"\nimport zipfile\nimport tempfile\nimport os\nwith zipfile.ZipFile('document.docx', 'r') as z:\n    tmpdir = tempfile.mkdtemp()\n    z.extractall(tmpdir)\n    with open(os.path.join(tmpdir, 'word\u002Fdocument.xml')) as f:\n        print(f.read())\n\"\n```\n\n## Verification\n\nConfirm extraction worked:\n\n```bash\n# Check output has content\nparse_docx document.docx | head -20\n\n# Verify file was created (if saving to file)\nls -la output.txt\nwc -l output.txt\n```\n\n## Method Selection Guide\n\n| Environment | Recommended Method |\n|-------------|-------------------|\n| Standard Linux with unzip | Shell (faster, simpler) |\n| Container without unzip | Python zipfile |\n| Sandboxed execution | Python via execute_code_sandbox or run_shell |\n| Minimal\u002Fbusybox images | Shell if unzip available |\n| Unknown\u002Frestricted | Use unified `parse_docx` function |\n\n## Limitations\n\n- Does not preserve formatting, images, or table structure\n- May include some residual XML entity references (&nbsp;, etc.)\n- Works best for simple text extraction needs\n- DOCX must be a valid Office Open XML format\n- Protected\u002Fencrypted DOCX files require additional handling\n\n## Error Handling Tips\n\n1. Always check file existence before parsing\n2. Test method availability in the target environment\n3. Capture stderr for debugging failed extractions\n4. Validate output is non-empty before proceeding\n5. Handle XML entity decoding if needed (sed can expand basic entities)\n",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-parse-enhanced-4bba79",944,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot","https:\u002F\u002Fgithub.com\u002FHKUDS","https:\u002F\u002Fsites.google.com\u002Fview\u002Fchaoh","2026-11-12 22:26:39",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add HKUDS\u002FAgentPilot --skill docx-dual-parse",{"tool":58,"command":59},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill docx-dual-parse",{"tool":61,"command":62},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill docx-dual-parse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-parse-enhanced-4bba79\u002FSKILL.md",true,[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},".skill_id","OTHER","其他",46,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-parse-enhanced-4bba79\u002F.skill_id",[73,92,111,134,158,179],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":39},"01M6HYB297NDABRERJRVG0K8R0","agentpilot","Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fplugins\u002Fagentpilot\u002Fskills\u002Fagentpilot\u002FSKILL.md",[],[75,80,81,38,82,83,84,85,86,87,88,89,90,91],"prepare","requests","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":39},"01M6HYAYWXTTE1J7DJM0MFNQ4H","remember","Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fskills\u002Fremember\u002FSKILL.md",[],[94,99,100,101,102,103,104,105,106,107,108,109,110],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":120,"publishedAt":39},"01M6HYAVMPM4SBDV60R2B5HPV8","skill-discovery","Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\u002FSKILL.md",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[121,122,123,102,124,125,126,127,128,129,130,131,132,133],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":39},"01M6HYAR811B3RB0M50RBEDGN6","delegate-task","Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fdelegate-task\u002FSKILL.md",[140],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,144,102,145,146,147,148,149,123,101,86,150,151,152,153,154,155,156,157],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":39},"01M6HYAM9FSGV6E52AYENDQXYH","write-special-chars-ts-check","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-ts-check\u002FSKILL.md",[],[165,166,167,168,36,169,170,171,172,31,173,174,175,176,153,177,178],"write special chars ts check","write","check","type","filters","only","template","file","typescript","output","Existing","type-checking","errors","script",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":39},"01M6HYAH05HGV7SVWSVR8PJRQD","write-special-chars-readback","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of \u002Ftmp helper scripts.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-readback\u002FSKILL.md",[],[186,187,166,38,153,178,188,189,190,191,192,171,172,193,194,31],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]