{
  "schemaVersion": "1.0",
  "item": {
    "slug": "autonomous-skill",
    "name": "Autonomous Skill",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/feiskyer/autonomous-skill",
    "canonicalUrl": "https://clawhub.ai/feiskyer/autonomous-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/autonomous-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=autonomous-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/run-session.sh",
      "templates/executor-prompt.md",
      "templates/initializer-prompt.md",
      "templates/task-list-template.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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/autonomous-skill"
    },
    "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/autonomous-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/autonomous-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/autonomous-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/autonomous-skill/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": "Autonomous Skill - Long-Running Task Execution",
        "body": "Execute complex, long-running tasks across multiple sessions using a dual-agent pattern (Initializer + Executor) with automatic session continuation."
      },
      {
        "title": "Directory Structure",
        "body": "All task data is stored in .autonomous/<task-name>/ under the project root:\n\nproject-root/\n└── .autonomous/\n    ├── build-rest-api/\n    │   ├── task_list.md\n    │   └── progress.md\n    ├── refactor-auth/\n    │   ├── task_list.md\n    │   └── progress.md\n    └── ...\n\nThis allows multiple autonomous tasks to run in parallel without conflicts."
      },
      {
        "title": "Workflow Overview",
        "body": "User Request → Generate Task Name → Create .autonomous/<task-name>/ → Execute Sessions"
      },
      {
        "title": "Step 1: Initialize Task Directory",
        "body": "Generate a task name from user's description and create the directory:\n\n# Generate task name (lowercase, hyphens, max 30 chars)\n# Example: \"Build a REST API for todo app\" → \"build-rest-api-todo\"\nTASK_NAME=$(echo \"$USER_TASK\" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-30 | sed 's/-$//')\n\n# Create task directory\nTASK_DIR=\".autonomous/$TASK_NAME\"\nmkdir -p \"$TASK_DIR\"\n\necho \"Task directory: $TASK_DIR\""
      },
      {
        "title": "Step 2: Analyze Current State",
        "body": "Check if this is a new task or continuation:\n\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Look for existing task list\nif [ -f \"$TASK_DIR/task_list.md\" ]; then\n  echo \"=== CONTINUATION MODE ===\"\n  echo \"Found existing task at: $TASK_DIR\"\n\n  # Show progress summary\n  TOTAL=$(grep -c '^\\- \\[' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n  DONE=$(grep -c '^\\- \\[x\\]' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n  echo \"Progress: $DONE/$TOTAL tasks completed\"\n\n  # Show recent progress notes\n  echo \"\"\n  echo \"=== Recent Progress ===\"\n  head -50 \"$TASK_DIR/task_list.md\"\nelse\n  echo \"=== NEW TASK MODE ===\"\n  echo \"Creating new task at: $TASK_DIR\"\n  mkdir -p \"$TASK_DIR\"\nfi"
      },
      {
        "title": "For NEW Tasks (Initializer Mode)",
        "body": "If task_list.md does NOT exist in the task directory:\n\nSKILL_DIR=\"${CLAUDE_PLUGIN_ROOT}/skills/autonomous-skill\"\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Read the initializer prompt template\nINITIALIZER_PROMPT=$(cat \"$SKILL_DIR/templates/initializer-prompt.md\")\n\n# Execute initializer session\nclaude -p \"Task: $USER_TASK_DESCRIPTION\nTask Directory: $TASK_DIR\n\n$INITIALIZER_PROMPT\" \\\n  --output-format stream-json \\\n  --max-turns 50 \\\n  --append-system-prompt \"You are the Initializer Agent. Create task_list.md and progress.md in $TASK_DIR directory.\""
      },
      {
        "title": "For CONTINUATION (Executor Mode)",
        "body": "If task_list.md EXISTS in the task directory:\n\nSKILL_DIR=\"${CLAUDE_PLUGIN_ROOT}/skills/autonomous-skill\"\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Read the executor prompt template\nEXECUTOR_PROMPT=$(cat \"$SKILL_DIR/templates/executor-prompt.md\")\n\n# Read current state\nTASK_LIST=$(cat \"$TASK_DIR/task_list.md\")\nPROGRESS=$(cat \"$TASK_DIR/progress.md\" 2>/dev/null || echo \"No previous progress notes\")\n\n# Execute executor session\nclaude -p \"Continue working on the task.\nTask Directory: $TASK_DIR\n\nCurrent task_list.md:\n$TASK_LIST\n\nPrevious progress notes:\n$PROGRESS\n\n$EXECUTOR_PROMPT\" \\\n  --output-format stream-json \\\n  --max-turns 100 \\\n  --append-system-prompt \"You are the Executor Agent. Complete tasks and update files in $TASK_DIR directory.\""
      },
      {
        "title": "Step 4: Auto-Continue Loop",
        "body": "After each session completes, check remaining tasks and auto-continue:\n\n#!/bin/bash\nTASK_DIR=\".autonomous/$TASK_NAME\"\nAUTO_CONTINUE_DELAY=3\nSESSION_NUM=1\n\nwhile true; do\n  echo \"\"\n  echo \"==========================================\"\n  echo \"  SESSION $SESSION_NUM - Task: $TASK_NAME\"\n  echo \"==========================================\"\n\n  # Run the appropriate agent\n  # ... execute session ...\n\n  # Check completion\n  if [ -f \"$TASK_DIR/task_list.md\" ]; then\n    TOTAL=$(grep -c '^\\- \\[' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n    DONE=$(grep -c '^\\- \\[x\\]' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n\n    echo \"\"\n    echo \"=== Progress: $DONE/$TOTAL tasks completed ===\"\n\n    if [ \"$DONE\" -eq \"$TOTAL\" ] && [ \"$TOTAL\" -gt 0 ]; then\n      echo \"\"\n      echo \"All tasks completed! Exiting.\"\n      break\n    fi\n  fi\n\n  # Auto-continue with delay\n  echo \"\"\n  echo \"Continuing in $AUTO_CONTINUE_DELAY seconds... (Press Ctrl+C to pause)\"\n  sleep $AUTO_CONTINUE_DELAY\n\n  SESSION_NUM=$((SESSION_NUM + 1))\ndone"
      },
      {
        "title": "Step 5: Report Progress",
        "body": "After execution, display a clear progress report:\n\n==========================================\n  SESSION COMPLETE - Task: build-rest-api\n==========================================\n\nTask Directory: .autonomous/build-rest-api/\n\nTasks completed this session:\n- [x] Task 5: Implement user authentication\n- [x] Task 6: Add login form validation\n\nOverall Progress: 18/50 tasks (36%)\n\nNext tasks:\n- [ ] Task 7: Create password reset flow\n- [ ] Task 8: Add session management\n\nContinuing in 3 seconds... (Press Ctrl+C to pause)"
      },
      {
        "title": "Example 1: Start New Task",
        "body": "User: Please use autonomous skill to build a REST API for a todo app\n\nResponse:\n1. Generated task name: \"build-rest-api-todo\"\n2. Created directory: .autonomous/build-rest-api-todo/\n3. Running Initializer Agent...\n4. Created task_list.md with 25 tasks\n5. Progress: 3/25 completed\n6. Auto-continuing in 3 seconds..."
      },
      {
        "title": "Example 2: Continue Existing Task",
        "body": "User: Continue the autonomous task \"build-rest-api-todo\"\n\nResponse:\n1. Found task: .autonomous/build-rest-api-todo/\n2. Current progress: 15/25 tasks\n3. Running Executor Agent...\n4. Completed tasks 16-17\n5. Progress: 17/25 completed\n6. Auto-continuing in 3 seconds..."
      },
      {
        "title": "Example 3: List All Tasks",
        "body": "# List all autonomous tasks\nls -la .autonomous/\n\n# Show progress for specific task\ncat .autonomous/build-rest-api-todo/task_list.md"
      },
      {
        "title": "Key Files",
        "body": "For each task in .autonomous/<task-name>/:\n\nFilePurposetask_list.mdMaster task list with checkbox progressprogress.mdSession-by-session progress notes"
      },
      {
        "title": "Important Notes",
        "body": "Task Isolation: Each task has its own directory, no conflicts\nTask Naming: Auto-generated from description (lowercase, hyphens)\nTask List is Sacred: Never delete or modify descriptions, only mark [x]\nOne Task at a Time per Session: Focus on completing tasks thoroughly\nAuto-Continue: Sessions auto-continue with 3s delay; Ctrl+C to pause"
      },
      {
        "title": "Troubleshooting",
        "body": "IssueSolutionTask not foundCheck .autonomous/ for existing tasksMultiple tasksSpecify task name explicitlySession stuckCheck progress.md in task directoryNeed to restartDelete task directory and start fresh"
      }
    ],
    "body": "Autonomous Skill - Long-Running Task Execution\n\nExecute complex, long-running tasks across multiple sessions using a dual-agent pattern (Initializer + Executor) with automatic session continuation.\n\nDirectory Structure\n\nAll task data is stored in .autonomous/<task-name>/ under the project root:\n\nproject-root/\n└── .autonomous/\n    ├── build-rest-api/\n    │   ├── task_list.md\n    │   └── progress.md\n    ├── refactor-auth/\n    │   ├── task_list.md\n    │   └── progress.md\n    └── ...\n\n\nThis allows multiple autonomous tasks to run in parallel without conflicts.\n\nWorkflow Overview\nUser Request → Generate Task Name → Create .autonomous/<task-name>/ → Execute Sessions\n\nStep 1: Initialize Task Directory\n\nGenerate a task name from user's description and create the directory:\n\n# Generate task name (lowercase, hyphens, max 30 chars)\n# Example: \"Build a REST API for todo app\" → \"build-rest-api-todo\"\nTASK_NAME=$(echo \"$USER_TASK\" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-30 | sed 's/-$//')\n\n# Create task directory\nTASK_DIR=\".autonomous/$TASK_NAME\"\nmkdir -p \"$TASK_DIR\"\n\necho \"Task directory: $TASK_DIR\"\n\nStep 2: Analyze Current State\n\nCheck if this is a new task or continuation:\n\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Look for existing task list\nif [ -f \"$TASK_DIR/task_list.md\" ]; then\n  echo \"=== CONTINUATION MODE ===\"\n  echo \"Found existing task at: $TASK_DIR\"\n\n  # Show progress summary\n  TOTAL=$(grep -c '^\\- \\[' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n  DONE=$(grep -c '^\\- \\[x\\]' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n  echo \"Progress: $DONE/$TOTAL tasks completed\"\n\n  # Show recent progress notes\n  echo \"\"\n  echo \"=== Recent Progress ===\"\n  head -50 \"$TASK_DIR/task_list.md\"\nelse\n  echo \"=== NEW TASK MODE ===\"\n  echo \"Creating new task at: $TASK_DIR\"\n  mkdir -p \"$TASK_DIR\"\nfi\n\nStep 3: Choose Agent Mode\nFor NEW Tasks (Initializer Mode)\n\nIf task_list.md does NOT exist in the task directory:\n\nSKILL_DIR=\"${CLAUDE_PLUGIN_ROOT}/skills/autonomous-skill\"\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Read the initializer prompt template\nINITIALIZER_PROMPT=$(cat \"$SKILL_DIR/templates/initializer-prompt.md\")\n\n# Execute initializer session\nclaude -p \"Task: $USER_TASK_DESCRIPTION\nTask Directory: $TASK_DIR\n\n$INITIALIZER_PROMPT\" \\\n  --output-format stream-json \\\n  --max-turns 50 \\\n  --append-system-prompt \"You are the Initializer Agent. Create task_list.md and progress.md in $TASK_DIR directory.\"\n\nFor CONTINUATION (Executor Mode)\n\nIf task_list.md EXISTS in the task directory:\n\nSKILL_DIR=\"${CLAUDE_PLUGIN_ROOT}/skills/autonomous-skill\"\nTASK_DIR=\".autonomous/$TASK_NAME\"\n\n# Read the executor prompt template\nEXECUTOR_PROMPT=$(cat \"$SKILL_DIR/templates/executor-prompt.md\")\n\n# Read current state\nTASK_LIST=$(cat \"$TASK_DIR/task_list.md\")\nPROGRESS=$(cat \"$TASK_DIR/progress.md\" 2>/dev/null || echo \"No previous progress notes\")\n\n# Execute executor session\nclaude -p \"Continue working on the task.\nTask Directory: $TASK_DIR\n\nCurrent task_list.md:\n$TASK_LIST\n\nPrevious progress notes:\n$PROGRESS\n\n$EXECUTOR_PROMPT\" \\\n  --output-format stream-json \\\n  --max-turns 100 \\\n  --append-system-prompt \"You are the Executor Agent. Complete tasks and update files in $TASK_DIR directory.\"\n\nStep 4: Auto-Continue Loop\n\nAfter each session completes, check remaining tasks and auto-continue:\n\n#!/bin/bash\nTASK_DIR=\".autonomous/$TASK_NAME\"\nAUTO_CONTINUE_DELAY=3\nSESSION_NUM=1\n\nwhile true; do\n  echo \"\"\n  echo \"==========================================\"\n  echo \"  SESSION $SESSION_NUM - Task: $TASK_NAME\"\n  echo \"==========================================\"\n\n  # Run the appropriate agent\n  # ... execute session ...\n\n  # Check completion\n  if [ -f \"$TASK_DIR/task_list.md\" ]; then\n    TOTAL=$(grep -c '^\\- \\[' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n    DONE=$(grep -c '^\\- \\[x\\]' \"$TASK_DIR/task_list.md\" 2>/dev/null || echo \"0\")\n\n    echo \"\"\n    echo \"=== Progress: $DONE/$TOTAL tasks completed ===\"\n\n    if [ \"$DONE\" -eq \"$TOTAL\" ] && [ \"$TOTAL\" -gt 0 ]; then\n      echo \"\"\n      echo \"All tasks completed! Exiting.\"\n      break\n    fi\n  fi\n\n  # Auto-continue with delay\n  echo \"\"\n  echo \"Continuing in $AUTO_CONTINUE_DELAY seconds... (Press Ctrl+C to pause)\"\n  sleep $AUTO_CONTINUE_DELAY\n\n  SESSION_NUM=$((SESSION_NUM + 1))\ndone\n\nStep 5: Report Progress\n\nAfter execution, display a clear progress report:\n\n==========================================\n  SESSION COMPLETE - Task: build-rest-api\n==========================================\n\nTask Directory: .autonomous/build-rest-api/\n\nTasks completed this session:\n- [x] Task 5: Implement user authentication\n- [x] Task 6: Add login form validation\n\nOverall Progress: 18/50 tasks (36%)\n\nNext tasks:\n- [ ] Task 7: Create password reset flow\n- [ ] Task 8: Add session management\n\nContinuing in 3 seconds... (Press Ctrl+C to pause)\n\nUsage Examples\nExample 1: Start New Task\nUser: Please use autonomous skill to build a REST API for a todo app\n\nResponse:\n1. Generated task name: \"build-rest-api-todo\"\n2. Created directory: .autonomous/build-rest-api-todo/\n3. Running Initializer Agent...\n4. Created task_list.md with 25 tasks\n5. Progress: 3/25 completed\n6. Auto-continuing in 3 seconds...\n\nExample 2: Continue Existing Task\nUser: Continue the autonomous task \"build-rest-api-todo\"\n\nResponse:\n1. Found task: .autonomous/build-rest-api-todo/\n2. Current progress: 15/25 tasks\n3. Running Executor Agent...\n4. Completed tasks 16-17\n5. Progress: 17/25 completed\n6. Auto-continuing in 3 seconds...\n\nExample 3: List All Tasks\n# List all autonomous tasks\nls -la .autonomous/\n\n# Show progress for specific task\ncat .autonomous/build-rest-api-todo/task_list.md\n\nKey Files\n\nFor each task in .autonomous/<task-name>/:\n\nFile\tPurpose\ntask_list.md\tMaster task list with checkbox progress\nprogress.md\tSession-by-session progress notes\nImportant Notes\nTask Isolation: Each task has its own directory, no conflicts\nTask Naming: Auto-generated from description (lowercase, hyphens)\nTask List is Sacred: Never delete or modify descriptions, only mark [x]\nOne Task at a Time per Session: Focus on completing tasks thoroughly\nAuto-Continue: Sessions auto-continue with 3s delay; Ctrl+C to pause\nTroubleshooting\nIssue\tSolution\nTask not found\tCheck .autonomous/ for existing tasks\nMultiple tasks\tSpecify task name explicitly\nSession stuck\tCheck progress.md in task directory\nNeed to restart\tDelete task directory and start fresh"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/feiskyer/autonomous-skill",
    "publisherUrl": "https://clawhub.ai/feiskyer/autonomous-skill",
    "owner": "feiskyer",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/autonomous-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/autonomous-skill",
    "agentUrl": "https://openagent3.xyz/skills/autonomous-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/autonomous-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/autonomous-skill/agent.md"
  }
}