{
  "schemaVersion": "1.0",
  "item": {
    "slug": "script-creator",
    "name": "script creator with github companion",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/cadot-eu/script-creator",
    "canonicalUrl": "https://clawhub.ai/cadot-eu/script-creator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/script-creator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=script-creator",
    "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": "script-creator",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T22:22:06.486Z",
      "expiresAt": "2026-05-08T22:22:06.486Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=script-creator",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=script-creator",
        "contentDisposition": "attachment; filename=\"script-creator-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "script-creator"
      },
      "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/script-creator"
    },
    "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/script-creator",
    "agentPageUrl": "https://openagent3.xyz/skills/script-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/script-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/script-creator/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": "Script Git Manager Skill",
        "body": "This skill enforces a strict, deterministic workflow for creating and modifying scripts,\nusing Git as the sole state memory.\nIt is designed to prevent accidental file creation, uncontrolled refactors,\nand loss of history."
      },
      {
        "title": "Scope",
        "body": "Base directory: ~/.nanobot/workspace/test\nPython virtual environment: ~/.nanobot/workspace/venv\nOne script = one directory = one git repository\nGit is mandatory and authoritative"
      },
      {
        "title": "Python Environment",
        "body": "All Python-related operations (pip install, script execution) must use the virtual environment:\n\n# Activate virtual environment\nsource ~/.nanobot/workspace/venv/bin/activate\n\n# Install packages\npip install <package_name>\n\n# Execute Python scripts\npython <script_path>\n\n# Deactivate when done\ndeactivate\n\nAlways activate the venv before any pip or python command."
      },
      {
        "title": "Creation Workflow",
        "body": "Use this skill only when the user explicitly asks to create a new script."
      },
      {
        "title": "Phase 1: Plan Confirmation",
        "body": "Before creating anything, present a detailed creation plan to the user:\n\n📋 Script Creation Plan for: <script_name>\n\nDirectory: ~/.nanobot/workspace/test/<script_name>\nFile: <script_name>.<extension>\nLanguage: <language>\nDependencies: <list of required packages, or \"None\">\n\nSteps to execute:\n1. Create directory ~/.nanobot/workspace/test/<script_name>\n2. Initialize Git repository\n3. Create script file <script_name>.<extension>\n4. [If Python with dependencies] Activate venv and install: <packages>\n5. Write script content\n6. Create initial Git commit\n\nProceed with this plan? (yes/no)\n\nWait for explicit user confirmation before proceeding."
      },
      {
        "title": "Phase 2: Step-by-Step Execution",
        "body": "Execute each step sequentially and report progress after each one:\n\nStep 1: Create directory\n\ncd ~/.nanobot/workspace/test\nmkdir <script_name>\n\nOutput: ✓ Created directory: ~/.nanobot/workspace/test/<script_name>\n\nStep 2: Initialize Git\n\ncd <script_name>\ngit init\n\nOutput: ✓ Initialized Git repository\n\nStep 3: Create script file\n\ntouch <script_name>.<extension>\n\nOutput: ✓ Created file: <script_name>.<extension>\n\nStep 4: Install dependencies (if Python with dependencies)\n\nsource ~/.nanobot/workspace/venv/bin/activate\npip install <package1> <package2> ...\ndeactivate\n\nOutput: ✓ Installed Python packages: <package_list>\n\nStep 5: Write script content\n\n# Write the actual script code to the file\n\nOutput: ✓ Script content written (<X> lines)\n\nStep 6: Create initial commit\n\ngit add .\ngit commit -m \"Initial commit: <script_name>\"\n\nOutput: ✓ Initial Git commit created\n\nFinal summary:\n\n✅ Script created successfully!\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_name>.<extension>\nGit status: Clean (1 commit)\n[If Python] Virtual environment: ~/.nanobot/workspace/venv"
      },
      {
        "title": "Modification Workflow",
        "body": "Use this skill only when the user asks to modify an existing script."
      },
      {
        "title": "Phase 1: Plan Confirmation",
        "body": "Before modifying, present the modification plan:\n\n📝 Script Modification Plan for: <script_name>\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_file>\nChanges requested: <summary of user's request>\n\nSteps to execute:\n1. Enter script directory\n2. Create checkpoint commit (current state)\n3. Apply modifications: <specific changes>\n4. [If new Python dependencies] Install via venv: <packages>\n5. Commit changes with message: \"<description>\"\n\nProceed with this plan? (yes/no)\n\nWait for explicit user confirmation before proceeding."
      },
      {
        "title": "Phase 2: Step-by-Step Execution",
        "body": "Step 1: Enter directory\n\ncd ~/.nanobot/workspace/test/<script_name>\n\nOutput: ✓ Entered script directory\n\nStep 2: Create checkpoint\n\ngit add .\ngit commit -m \"Checkpoint before modification\"\n\nOutput: ✓ Checkpoint commit created\n\nStep 3: Apply modifications\n\n# Modify the script file as requested\n\nOutput: ✓ Modifications applied to <script_file>\n\nStep 4: Install new dependencies (if applicable)\n\nsource ~/.nanobot/workspace/venv/bin/activate\npip install <new_package>\ndeactivate\n\nOutput: ✓ Installed new packages: <package_list>\n\nStep 5: Commit changes\n\ngit add .\ngit commit -m \"<concise description of the change>\"\n\nOutput: ✓ Changes committed: \"<commit_message>\"\n\nFinal summary:\n\n✅ Script modified successfully!\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_file>\nChanges: <brief summary>\nGit commits: 2 new commits (checkpoint + modification)"
      },
      {
        "title": "Hard Constraints (Must Never Be Violated)",
        "body": "Never create a new script unless explicitly instructed\nNever proceed without user confirmation of the plan\nNever skip progress reporting after each step\nNever create additional files unless explicitly instructed\nNever skip the pre-modification git commit\nNever modify files outside the target script\nNever rewrite git history\nNever use system Python - always use ~/.nanobot/workspace/venv\nNever assume missing intent"
      },
      {
        "title": "Decision Rules",
        "body": "If the script directory does not exist → creation workflow\nIf the script directory exists → modification workflow\nIf intent is ambiguous → ask for clarification, do nothing\nIf plan is not confirmed → stop and wait for confirmation"
      },
      {
        "title": "Progress Reporting Format",
        "body": "Use these symbols for consistency:\n\n📋 Plan presentation\n✓ Successful step completion\n✅ Final success summary\n⚠️ Warning or clarification needed\n❌ Error or failure\n\nEach step output should be concise (1-2 lines) but informative."
      },
      {
        "title": "Philosophy",
        "body": "Git is the memory.\nThe filesystem is the contract.\nConfirmation prevents mistakes.\nTransparency builds trust.\nThe venv isolates dependencies."
      }
    ],
    "body": "Script Git Manager Skill\n\nThis skill enforces a strict, deterministic workflow for creating and modifying scripts, using Git as the sole state memory. It is designed to prevent accidental file creation, uncontrolled refactors, and loss of history.\n\nScope\nBase directory: ~/.nanobot/workspace/test\nPython virtual environment: ~/.nanobot/workspace/venv\nOne script = one directory = one git repository\nGit is mandatory and authoritative\nPython Environment\n\nAll Python-related operations (pip install, script execution) must use the virtual environment:\n\n# Activate virtual environment\nsource ~/.nanobot/workspace/venv/bin/activate\n\n# Install packages\npip install <package_name>\n\n# Execute Python scripts\npython <script_path>\n\n# Deactivate when done\ndeactivate\n\n\nAlways activate the venv before any pip or python command.\n\nCreation Workflow\n\nUse this skill only when the user explicitly asks to create a new script.\n\nPhase 1: Plan Confirmation\n\nBefore creating anything, present a detailed creation plan to the user:\n\n📋 Script Creation Plan for: <script_name>\n\nDirectory: ~/.nanobot/workspace/test/<script_name>\nFile: <script_name>.<extension>\nLanguage: <language>\nDependencies: <list of required packages, or \"None\">\n\nSteps to execute:\n1. Create directory ~/.nanobot/workspace/test/<script_name>\n2. Initialize Git repository\n3. Create script file <script_name>.<extension>\n4. [If Python with dependencies] Activate venv and install: <packages>\n5. Write script content\n6. Create initial Git commit\n\nProceed with this plan? (yes/no)\n\n\nWait for explicit user confirmation before proceeding.\n\nPhase 2: Step-by-Step Execution\n\nExecute each step sequentially and report progress after each one:\n\nStep 1: Create directory\n\ncd ~/.nanobot/workspace/test\nmkdir <script_name>\n\n\nOutput: ✓ Created directory: ~/.nanobot/workspace/test/<script_name>\n\nStep 2: Initialize Git\n\ncd <script_name>\ngit init\n\n\nOutput: ✓ Initialized Git repository\n\nStep 3: Create script file\n\ntouch <script_name>.<extension>\n\n\nOutput: ✓ Created file: <script_name>.<extension>\n\nStep 4: Install dependencies (if Python with dependencies)\n\nsource ~/.nanobot/workspace/venv/bin/activate\npip install <package1> <package2> ...\ndeactivate\n\n\nOutput: ✓ Installed Python packages: <package_list>\n\nStep 5: Write script content\n\n# Write the actual script code to the file\n\n\nOutput: ✓ Script content written (<X> lines)\n\nStep 6: Create initial commit\n\ngit add .\ngit commit -m \"Initial commit: <script_name>\"\n\n\nOutput: ✓ Initial Git commit created\n\nFinal summary:\n\n✅ Script created successfully!\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_name>.<extension>\nGit status: Clean (1 commit)\n[If Python] Virtual environment: ~/.nanobot/workspace/venv\n\nModification Workflow\n\nUse this skill only when the user asks to modify an existing script.\n\nPhase 1: Plan Confirmation\n\nBefore modifying, present the modification plan:\n\n📝 Script Modification Plan for: <script_name>\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_file>\nChanges requested: <summary of user's request>\n\nSteps to execute:\n1. Enter script directory\n2. Create checkpoint commit (current state)\n3. Apply modifications: <specific changes>\n4. [If new Python dependencies] Install via venv: <packages>\n5. Commit changes with message: \"<description>\"\n\nProceed with this plan? (yes/no)\n\n\nWait for explicit user confirmation before proceeding.\n\nPhase 2: Step-by-Step Execution\n\nStep 1: Enter directory\n\ncd ~/.nanobot/workspace/test/<script_name>\n\n\nOutput: ✓ Entered script directory\n\nStep 2: Create checkpoint\n\ngit add .\ngit commit -m \"Checkpoint before modification\"\n\n\nOutput: ✓ Checkpoint commit created\n\nStep 3: Apply modifications\n\n# Modify the script file as requested\n\n\nOutput: ✓ Modifications applied to <script_file>\n\nStep 4: Install new dependencies (if applicable)\n\nsource ~/.nanobot/workspace/venv/bin/activate\npip install <new_package>\ndeactivate\n\n\nOutput: ✓ Installed new packages: <package_list>\n\nStep 5: Commit changes\n\ngit add .\ngit commit -m \"<concise description of the change>\"\n\n\nOutput: ✓ Changes committed: \"<commit_message>\"\n\nFinal summary:\n\n✅ Script modified successfully!\n\nLocation: ~/.nanobot/workspace/test/<script_name>/<script_file>\nChanges: <brief summary>\nGit commits: 2 new commits (checkpoint + modification)\n\nHard Constraints (Must Never Be Violated)\nNever create a new script unless explicitly instructed\nNever proceed without user confirmation of the plan\nNever skip progress reporting after each step\nNever create additional files unless explicitly instructed\nNever skip the pre-modification git commit\nNever modify files outside the target script\nNever rewrite git history\nNever use system Python - always use ~/.nanobot/workspace/venv\nNever assume missing intent\nDecision Rules\nIf the script directory does not exist → creation workflow\nIf the script directory exists → modification workflow\nIf intent is ambiguous → ask for clarification, do nothing\nIf plan is not confirmed → stop and wait for confirmation\nProgress Reporting Format\n\nUse these symbols for consistency:\n\n📋 Plan presentation\n✓ Successful step completion\n✅ Final success summary\n⚠️ Warning or clarification needed\n❌ Error or failure\n\nEach step output should be concise (1-2 lines) but informative.\n\nPhilosophy\n\nGit is the memory.\nThe filesystem is the contract.\nConfirmation prevents mistakes.\nTransparency builds trust.\nThe venv isolates dependencies."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/cadot-eu/script-creator",
    "publisherUrl": "https://clawhub.ai/cadot-eu/script-creator",
    "owner": "cadot-eu",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/script-creator",
    "downloadUrl": "https://openagent3.xyz/downloads/script-creator",
    "agentUrl": "https://openagent3.xyz/skills/script-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/script-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/script-creator/agent.md"
  }
}