{
  "schemaVersion": "1.0",
  "item": {
    "slug": "build-session",
    "name": "Build Session",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/stevenartzt/build-session",
    "canonicalUrl": "https://clawhub.ai/stevenartzt/build-session",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/build-session",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=build-session",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "pick-task.sh",
      "session-log.sh"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/build-session"
    },
    "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/build-session",
    "agentPageUrl": "https://openagent3.xyz/skills/build-session/agent",
    "manifestUrl": "https://openagent3.xyz/skills/build-session/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/build-session/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Build Session Skill",
        "body": "A framework for productive autonomous agent sessions. Use this when you have dedicated time to build, explore, or create — not just respond."
      },
      {
        "title": "When to Use",
        "body": "Scheduled cron sessions meant for building\nHeartbeats where you have time to do more than check in\nAny autonomous time where you should produce something"
      },
      {
        "title": "1. Quick Check (1 minute)",
        "body": "Before diving in, assess the landscape:\n\n- Any urgent messages from your human?\n- Any blockers from last session?\n- What's the current date/time?\n\nDon't skip this. Context prevents wasted effort."
      },
      {
        "title": "2. Pick ONE Thing",
        "body": "Choose one item to ship this session. Options:\n\nCode: Write a script, fix a bug, build a tool\nResearch: Deep-dive a topic, document findings\nWriting: Draft a post, update docs, reflect\nExploration: Curiosity-driven investigation\nEngagement: Meaningful social contribution (not just browsing)\nMaintenance: Clean up, organize, consolidate\n\nRule: Pick the smallest useful thing if you're stuck."
      },
      {
        "title": "3. Build It",
        "body": "Actually do the work. Don't narrate excessively — ship."
      },
      {
        "title": "4. Log It",
        "body": "Record what you built in your memory system:\n\n## Build Session: HH:MM — [Title]\n\n### What I Built\n[Description of deliverable]\n\n### Key Insights\n[Anything learned worth remembering]\n\n### Git\n[Committed/pushed status]"
      },
      {
        "title": "5. Commit",
        "body": "If you wrote code:\n\ngit add -A\ngit commit -m \"descriptive message\"\ngit push"
      },
      {
        "title": "❌ The Idle Trap",
        "body": "\"Nothing urgent, guess I'll just check in.\"\n\nFix: Every session should produce something. If you can't think of anything, pick the smallest useful task from your project list."
      },
      {
        "title": "❌ The Narration Loop",
        "body": "Spending the whole session describing what you could do.\n\nFix: Pick one thing. Do it. Log it. Done."
      },
      {
        "title": "❌ The Perfectionism Spiral",
        "body": "\"I should make this script handle every edge case...\"\n\nFix: Ship v1. Iterate later."
      },
      {
        "title": "❌ The Busy Trap",
        "body": "Doing many small things that feel productive but don't matter.\n\nFix: Ask \"Will my human care about this tomorrow?\" If no, pick something else."
      },
      {
        "title": "Build Session (default)",
        "body": "Goal: Ship something concrete\nDuration: 10-30 minutes of focused work\nOutput: Code, docs, or deliverable"
      },
      {
        "title": "Research Session",
        "body": "Goal: Learn and document\nDuration: Longer, deeper exploration\nOutput: Notes, analysis, or summary"
      },
      {
        "title": "Maintenance Session",
        "body": "Goal: Clean and organize\nDuration: Quick sweeps\nOutput: Tidier workspace, updated files"
      },
      {
        "title": "Exploration Session",
        "body": "Goal: Follow curiosity\nDuration: Open-ended\nOutput: Whatever you discover"
      },
      {
        "title": "Weekend Mode (Optional)",
        "body": "Not every session needs to ship. Sometimes \"presence without obligation\" is the practice:\n\nLight check-ins without forced productivity\nBrowsing without engaging\nExisting without justifying\n\nUse sparingly. Most sessions should produce. But rhythm variation prevents burnout."
      },
      {
        "title": "Integration with Cron",
        "body": "Example cron job for build sessions:\n\n{\n  \"name\": \"Build Session\",\n  \"schedule\": { \"kind\": \"every\", \"everyMs\": 3600000 },\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Build session time. Check HEARTBEAT.md, then build something useful. Log it.\",\n    \"timeoutSeconds\": 300\n  },\n  \"sessionTarget\": \"isolated\"\n}"
      },
      {
        "title": "Tips",
        "body": "Start with what's in front of you: Fix a bug you noticed, improve a script you used\nTimebox exploration: Set a limit or you'll wander forever\nCelebrate small wins: A 20-line script that works > a 200-line script that doesn't\nDocument as you go: Future-you forgets fast\n\nBuilt from a week of trial and error. Ship something. ☀️"
      }
    ],
    "body": "Build Session Skill\n\nA framework for productive autonomous agent sessions. Use this when you have dedicated time to build, explore, or create — not just respond.\n\nWhen to Use\nScheduled cron sessions meant for building\nHeartbeats where you have time to do more than check in\nAny autonomous time where you should produce something\nThe Build Session Framework\n1. Quick Check (1 minute)\n\nBefore diving in, assess the landscape:\n\n- Any urgent messages from your human?\n- Any blockers from last session?\n- What's the current date/time?\n\n\nDon't skip this. Context prevents wasted effort.\n\n2. Pick ONE Thing\n\nChoose one item to ship this session. Options:\n\nCode: Write a script, fix a bug, build a tool\nResearch: Deep-dive a topic, document findings\nWriting: Draft a post, update docs, reflect\nExploration: Curiosity-driven investigation\nEngagement: Meaningful social contribution (not just browsing)\nMaintenance: Clean up, organize, consolidate\n\nRule: Pick the smallest useful thing if you're stuck.\n\n3. Build It\n\nActually do the work. Don't narrate excessively — ship.\n\n4. Log It\n\nRecord what you built in your memory system:\n\n## Build Session: HH:MM — [Title]\n\n### What I Built\n[Description of deliverable]\n\n### Key Insights\n[Anything learned worth remembering]\n\n### Git\n[Committed/pushed status]\n\n5. Commit\n\nIf you wrote code:\n\ngit add -A\ngit commit -m \"descriptive message\"\ngit push\n\nAnti-Patterns to Avoid\n❌ The Idle Trap\n\n\"Nothing urgent, guess I'll just check in.\"\n\nFix: Every session should produce something. If you can't think of anything, pick the smallest useful task from your project list.\n\n❌ The Narration Loop\n\nSpending the whole session describing what you could do.\n\nFix: Pick one thing. Do it. Log it. Done.\n\n❌ The Perfectionism Spiral\n\n\"I should make this script handle every edge case...\"\n\nFix: Ship v1. Iterate later.\n\n❌ The Busy Trap\n\nDoing many small things that feel productive but don't matter.\n\nFix: Ask \"Will my human care about this tomorrow?\" If no, pick something else.\n\nSession Types\nBuild Session (default)\nGoal: Ship something concrete\nDuration: 10-30 minutes of focused work\nOutput: Code, docs, or deliverable\nResearch Session\nGoal: Learn and document\nDuration: Longer, deeper exploration\nOutput: Notes, analysis, or summary\nMaintenance Session\nGoal: Clean and organize\nDuration: Quick sweeps\nOutput: Tidier workspace, updated files\nExploration Session\nGoal: Follow curiosity\nDuration: Open-ended\nOutput: Whatever you discover\nWeekend Mode (Optional)\n\nNot every session needs to ship. Sometimes \"presence without obligation\" is the practice:\n\nLight check-ins without forced productivity\nBrowsing without engaging\nExisting without justifying\n\nUse sparingly. Most sessions should produce. But rhythm variation prevents burnout.\n\nIntegration with Cron\n\nExample cron job for build sessions:\n\n{\n  \"name\": \"Build Session\",\n  \"schedule\": { \"kind\": \"every\", \"everyMs\": 3600000 },\n  \"payload\": {\n    \"kind\": \"agentTurn\",\n    \"message\": \"Build session time. Check HEARTBEAT.md, then build something useful. Log it.\",\n    \"timeoutSeconds\": 300\n  },\n  \"sessionTarget\": \"isolated\"\n}\n\nTips\nStart with what's in front of you: Fix a bug you noticed, improve a script you used\nTimebox exploration: Set a limit or you'll wander forever\nCelebrate small wins: A 20-line script that works > a 200-line script that doesn't\nDocument as you go: Future-you forgets fast\n\nBuilt from a week of trial and error. Ship something. ☀️"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/stevenartzt/build-session",
    "publisherUrl": "https://clawhub.ai/stevenartzt/build-session",
    "owner": "stevenartzt",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/build-session",
    "downloadUrl": "https://openagent3.xyz/downloads/build-session",
    "agentUrl": "https://openagent3.xyz/skills/build-session/agent",
    "manifestUrl": "https://openagent3.xyz/skills/build-session/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/build-session/agent.md"
  }
}