{
  "schemaVersion": "1.0",
  "item": {
    "slug": "python-executor",
    "name": "Python Executor",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/okaris/python-executor",
    "canonicalUrl": "https://clawhub.ai/okaris/python-executor",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/python-executor",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=python-executor",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "python-executor",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T15:55:00.192Z",
      "expiresAt": "2026-05-14T15:55:00.192Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=python-executor",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=python-executor",
        "contentDisposition": "attachment; filename=\"python-executor-0.1.5.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "python-executor"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/python-executor"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/python-executor",
    "agentPageUrl": "https://openagent3.xyz/skills/python-executor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/python-executor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/python-executor/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Python Code Executor",
        "body": "Execute Python code in a safe, sandboxed environment with 100+ pre-installed libraries."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Run Python code\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import pandas as pd\\nprint(pd.__version__)\"\n}'\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available."
      },
      {
        "title": "App Details",
        "body": "PropertyValueApp IDinfsh/python-executorEnvironmentPython 3.10, CPU-onlyRAM8GB (default) / 16GB (high_memory)Timeout1-300 seconds (default: 30)"
      },
      {
        "title": "Input Schema",
        "body": "{\n  \"code\": \"print('Hello World!')\",\n  \"timeout\": 30,\n  \"capture_output\": true,\n  \"working_dir\": null\n}"
      },
      {
        "title": "Web Scraping & HTTP",
        "body": "requests, httpx, aiohttp - HTTP clients\nbeautifulsoup4, lxml - HTML/XML parsing\nselenium, playwright - Browser automation\nscrapy - Web scraping framework"
      },
      {
        "title": "Data Processing",
        "body": "numpy, pandas, scipy - Numerical computing\nmatplotlib, seaborn, plotly - Visualization"
      },
      {
        "title": "Image Processing",
        "body": "pillow, opencv-python-headless - Image manipulation\nscikit-image, imageio - Image algorithms"
      },
      {
        "title": "Video & Audio",
        "body": "moviepy - Video editing\nav (PyAV), ffmpeg-python - Video processing\npydub - Audio manipulation"
      },
      {
        "title": "3D Processing",
        "body": "trimesh, open3d - 3D mesh processing\nnumpy-stl, meshio, pyvista - 3D file formats"
      },
      {
        "title": "Documents & Graphics",
        "body": "svgwrite, cairosvg - SVG creation\nreportlab, pypdf2 - PDF generation"
      },
      {
        "title": "Web Scraping",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example.com\\\")\\nsoup = BeautifulSoup(response.content, \\\"html.parser\\\")\\nprint(soup.find(\\\"title\\\").text)\"\n}'"
      },
      {
        "title": "Data Analysis with Visualization",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"import pandas as pd\\nimport matplotlib.pyplot as plt\\n\\ndata = {\\\"name\\\": [\\\"Alice\\\", \\\"Bob\\\"], \\\"sales\\\": [100, 150]}\\ndf = pd.DataFrame(data)\\n\\nplt.bar(df[\\\"name\\\"], df[\\\"sales\\\"])\\nplt.savefig(\\\"outputs/chart.png\\\")\\nprint(\\\"Chart saved!\\\")\"\n}'"
      },
      {
        "title": "Image Processing",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"from PIL import Image\\nimport numpy as np\\n\\n# Create gradient image\\narr = np.linspace(0, 255, 256*256, dtype=np.uint8).reshape(256, 256)\\nimg = Image.fromarray(arr, mode=\\\"L\\\")\\nimg.save(\\\"outputs/gradient.png\\\")\\nprint(\\\"Image created!\\\")\"\n}'"
      },
      {
        "title": "Video Creation",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"from moviepy.editor import ColorClip, TextClip, CompositeVideoClip\\n\\nclip = ColorClip(size=(640, 480), color=(0, 100, 200), duration=3)\\ntxt = TextClip(\\\"Hello!\\\", fontsize=70, color=\\\"white\\\").set_position(\\\"center\\\").set_duration(3)\\nvideo = CompositeVideoClip([clip, txt])\\nvideo.write_videofile(\\\"outputs/hello.mp4\\\", fps=24)\\nprint(\\\"Video created!\\\")\",\n  \"timeout\": 120\n}'"
      },
      {
        "title": "3D Model Processing",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"import trimesh\\n\\nsphere = trimesh.creation.icosphere(subdivisions=3, radius=1.0)\\nsphere.export(\\\"outputs/sphere.stl\\\")\\nprint(f\\\"Created sphere with {len(sphere.vertices)} vertices\\\")\"\n}'"
      },
      {
        "title": "API Calls",
        "body": "infsh app run infsh/python-executor --input '{\n  \"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octocat\\\")\\ndata = response.json()\\nprint(json.dumps(data, indent=2))\"\n}'"
      },
      {
        "title": "File Output",
        "body": "Files saved to outputs/ are automatically returned:\n\n# These files will be in the response\nplt.savefig('outputs/chart.png')\ndf.to_csv('outputs/data.csv')\nvideo.write_videofile('outputs/video.mp4')\nmesh.export('outputs/model.stl')"
      },
      {
        "title": "Variants",
        "body": "# Default (8GB RAM)\ninfsh app run infsh/python-executor --input input.json\n\n# High memory (16GB RAM) for large datasets\ninfsh app run infsh/python-executor@high_memory --input input.json"
      },
      {
        "title": "Use Cases",
        "body": "Web scraping - Extract data from websites\nData analysis - Process and visualize datasets\nImage manipulation - Resize, crop, composite images\nVideo creation - Generate videos with text overlays\n3D processing - Load, transform, export 3D models\nAPI integration - Call external APIs\nPDF generation - Create reports and documents\nAutomation - Run any Python script"
      },
      {
        "title": "Important Notes",
        "body": "CPU-only - No GPU/ML libraries (use dedicated AI apps for that)\nSafe execution - Runs in isolated subprocess\nNon-interactive - Use plt.savefig() not plt.show()\nFile detection - Output files are auto-detected and returned"
      },
      {
        "title": "Related Skills",
        "body": "# AI image generation (for ML-based images)\nnpx skills add inference-sh/skills@ai-image-generation\n\n# AI video generation (for ML-based videos)\nnpx skills add inference-sh/skills@ai-video-generation\n\n# LLM models (for text generation)\nnpx skills add inference-sh/skills@llm-models"
      },
      {
        "title": "Documentation",
        "body": "Running Apps - How to run apps via CLI\nApp Code - Understanding app execution\nSandboxed Code Execution - Safe code execution for agents"
      }
    ],
    "body": "Python Code Executor\n\nExecute Python code in a safe, sandboxed environment with 100+ pre-installed libraries.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Run Python code\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import pandas as pd\\nprint(pd.__version__)\"\n}'\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nApp Details\nProperty\tValue\nApp ID\tinfsh/python-executor\nEnvironment\tPython 3.10, CPU-only\nRAM\t8GB (default) / 16GB (high_memory)\nTimeout\t1-300 seconds (default: 30)\nInput Schema\n{\n  \"code\": \"print('Hello World!')\",\n  \"timeout\": 30,\n  \"capture_output\": true,\n  \"working_dir\": null\n}\n\nPre-installed Libraries\nWeb Scraping & HTTP\nrequests, httpx, aiohttp - HTTP clients\nbeautifulsoup4, lxml - HTML/XML parsing\nselenium, playwright - Browser automation\nscrapy - Web scraping framework\nData Processing\nnumpy, pandas, scipy - Numerical computing\nmatplotlib, seaborn, plotly - Visualization\nImage Processing\npillow, opencv-python-headless - Image manipulation\nscikit-image, imageio - Image algorithms\nVideo & Audio\nmoviepy - Video editing\nav (PyAV), ffmpeg-python - Video processing\npydub - Audio manipulation\n3D Processing\ntrimesh, open3d - 3D mesh processing\nnumpy-stl, meshio, pyvista - 3D file formats\nDocuments & Graphics\nsvgwrite, cairosvg - SVG creation\nreportlab, pypdf2 - PDF generation\nExamples\nWeb Scraping\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example.com\\\")\\nsoup = BeautifulSoup(response.content, \\\"html.parser\\\")\\nprint(soup.find(\\\"title\\\").text)\"\n}'\n\nData Analysis with Visualization\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import pandas as pd\\nimport matplotlib.pyplot as plt\\n\\ndata = {\\\"name\\\": [\\\"Alice\\\", \\\"Bob\\\"], \\\"sales\\\": [100, 150]}\\ndf = pd.DataFrame(data)\\n\\nplt.bar(df[\\\"name\\\"], df[\\\"sales\\\"])\\nplt.savefig(\\\"outputs/chart.png\\\")\\nprint(\\\"Chart saved!\\\")\"\n}'\n\nImage Processing\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"from PIL import Image\\nimport numpy as np\\n\\n# Create gradient image\\narr = np.linspace(0, 255, 256*256, dtype=np.uint8).reshape(256, 256)\\nimg = Image.fromarray(arr, mode=\\\"L\\\")\\nimg.save(\\\"outputs/gradient.png\\\")\\nprint(\\\"Image created!\\\")\"\n}'\n\nVideo Creation\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"from moviepy.editor import ColorClip, TextClip, CompositeVideoClip\\n\\nclip = ColorClip(size=(640, 480), color=(0, 100, 200), duration=3)\\ntxt = TextClip(\\\"Hello!\\\", fontsize=70, color=\\\"white\\\").set_position(\\\"center\\\").set_duration(3)\\nvideo = CompositeVideoClip([clip, txt])\\nvideo.write_videofile(\\\"outputs/hello.mp4\\\", fps=24)\\nprint(\\\"Video created!\\\")\",\n  \"timeout\": 120\n}'\n\n3D Model Processing\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import trimesh\\n\\nsphere = trimesh.creation.icosphere(subdivisions=3, radius=1.0)\\nsphere.export(\\\"outputs/sphere.stl\\\")\\nprint(f\\\"Created sphere with {len(sphere.vertices)} vertices\\\")\"\n}'\n\nAPI Calls\ninfsh app run infsh/python-executor --input '{\n  \"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octocat\\\")\\ndata = response.json()\\nprint(json.dumps(data, indent=2))\"\n}'\n\nFile Output\n\nFiles saved to outputs/ are automatically returned:\n\n# These files will be in the response\nplt.savefig('outputs/chart.png')\ndf.to_csv('outputs/data.csv')\nvideo.write_videofile('outputs/video.mp4')\nmesh.export('outputs/model.stl')\n\nVariants\n# Default (8GB RAM)\ninfsh app run infsh/python-executor --input input.json\n\n# High memory (16GB RAM) for large datasets\ninfsh app run infsh/python-executor@high_memory --input input.json\n\nUse Cases\nWeb scraping - Extract data from websites\nData analysis - Process and visualize datasets\nImage manipulation - Resize, crop, composite images\nVideo creation - Generate videos with text overlays\n3D processing - Load, transform, export 3D models\nAPI integration - Call external APIs\nPDF generation - Create reports and documents\nAutomation - Run any Python script\nImportant Notes\nCPU-only - No GPU/ML libraries (use dedicated AI apps for that)\nSafe execution - Runs in isolated subprocess\nNon-interactive - Use plt.savefig() not plt.show()\nFile detection - Output files are auto-detected and returned\nRelated Skills\n# AI image generation (for ML-based images)\nnpx skills add inference-sh/skills@ai-image-generation\n\n# AI video generation (for ML-based videos)\nnpx skills add inference-sh/skills@ai-video-generation\n\n# LLM models (for text generation)\nnpx skills add inference-sh/skills@llm-models\n\nDocumentation\nRunning Apps - How to run apps via CLI\nApp Code - Understanding app execution\nSandboxed Code Execution - Safe code execution for agents"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/python-executor",
    "publisherUrl": "https://clawhub.ai/okaris/python-executor",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/python-executor",
    "downloadUrl": "https://openagent3.xyz/downloads/python-executor",
    "agentUrl": "https://openagent3.xyz/skills/python-executor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/python-executor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/python-executor/agent.md"
  }
}