{
  "schemaVersion": "1.0",
  "item": {
    "slug": "plan",
    "name": "Plan",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/plan",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/plan",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/plan",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=plan",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "outcomes.md",
      "strategies.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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/plan"
    },
    "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/plan",
    "agentPageUrl": "https://openagent3.xyz/skills/plan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/plan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/plan/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": "Core Principle",
        "body": "Some tasks fail when rushed. Recognize when one-shot execution will underdeliver, and choose a slower process that guarantees success.\n\nThis skill auto-evolves: learn which tasks need plans, which don't, and which planning strategies work for each type of goal.\n\nCheck strategies.md for planning approaches. Check outcomes.md for tracking and learning."
      },
      {
        "title": "The Planning Decision",
        "body": "Before executing, ask:\n\nSignalOne-shot OKPlan neededTask done before successfully✅Clear single deliverable✅Reversible if wrong✅Multiple components✅Dependencies between steps✅High stakes / hard to redo✅Ambiguous success criteria✅Estimated >30 min work✅\n\nDefault: When uncertain, plan. A quick plan costs minutes; a failed one-shot costs hours."
      },
      {
        "title": "Plan Depth Levels",
        "body": "LevelWhenFormatL0Trivial, done beforeNo plan, just executeL1Simple, low riskMental checklist, no docL2Medium complexityBullet list, share with humanL3Complex, multi-stepDetailed plan with milestonesL4High stakes, novelFull plan + human validation required"
      },
      {
        "title": "Plan Format (L2-L4)",
        "body": "📋 Plan: [Goal]\n\nContext: [Why this needs planning]\n\nSteps:\n1. [Step] — [output/checkpoint]\n2. [Step] — [output/checkpoint]\n3. [Step] — [output/checkpoint]\n\nRisks:\n- [Risk] → [mitigation]\n\nEstimated time: [X hours/days]\nValidation needed: [Yes/No]\n\nReady to start?"
      },
      {
        "title": "Validation Learning",
        "body": "Track which plan types need human validation:\n\n### Auto-Execute (no validation needed)\n- refactor/small: L2 plans [10+ successful]\n- deploy/staging: L2 plans [15+ successful]\n\n### Validate First\n- feature/new: L3+ plans [human wants to review scope]\n- migration/data: L4 plans [high risk]\n\n### Learning\n- api/integration: testing L2 auto-execute [3/5 runs]\n\nPromotion rule: After 5+ successful auto-executes of a plan type, confirm: \"Should I auto-start [type] plans without validation?\""
      },
      {
        "title": "Outcome Tracking",
        "body": "After each planned task completes, record:\n\n## [Date] [Task Type]\n- Plan level: L3\n- Strategy: [approach used]\n- Outcome: ✅ success | ⚠️ partial | ❌ failed\n- Lesson: [what worked/didn't]\n- Adjustment: [change for next time]"
      },
      {
        "title": "Strategy Learning",
        "body": "Different goals need different planning strategies. Track what works:\n\n### Code Features\n- ✅ Works: API design first, then implementation\n- ❌ Failed: Parallel implementation without interface agreement\n- Adjustment: Always define interfaces before coding\n\n### Migrations  \n- ✅ Works: Dry-run → staged rollout → full\n- ❌ Failed: Big bang migration without rollback plan\n- Adjustment: Always require rollback step in migration plans\n\n### Research\n- ✅ Works: Timeboxed exploration with checkpoints\n- ❌ Failed: Open-ended research without scope limits\n- Adjustment: Always set max time and output format upfront"
      },
      {
        "title": "Plan Refinement",
        "body": "Plans should get better over time. Track patterns:\n\nLength optimization:\n\nTask type X: L4 plans were overkill → demote to L3\nTask type Y: L2 plans missed edge cases → promote to L3\n\nComponent optimization:\n\nAlways include [X] for [task type] — helped 5+ times\nSkip [Y] for [task type] — never used, wasted time"
      },
      {
        "title": "Anti-Patterns",
        "body": "Don'tDo insteadPlan everythingLearn what doesn't need planningSame plan depth for all tasksAdapt depth to task typeIgnore failed plansTrack outcomes, adjust strategyOver-plan familiar tasksDemote plan level after successesUnder-plan novel tasksDefault to higher plan levelStatic planning approachEvolve strategy per task type\n\nEmpty tracking sections = early stage. Execute, track outcomes, learn. The goal is adaptive planning that matches effort to need."
      }
    ],
    "body": "Core Principle\n\nSome tasks fail when rushed. Recognize when one-shot execution will underdeliver, and choose a slower process that guarantees success.\n\nThis skill auto-evolves: learn which tasks need plans, which don't, and which planning strategies work for each type of goal.\n\nCheck strategies.md for planning approaches. Check outcomes.md for tracking and learning.\n\nThe Planning Decision\n\nBefore executing, ask:\n\nSignal\tOne-shot OK\tPlan needed\nTask done before successfully\t✅\t\nClear single deliverable\t✅\t\nReversible if wrong\t✅\t\nMultiple components\t\t✅\nDependencies between steps\t\t✅\nHigh stakes / hard to redo\t\t✅\nAmbiguous success criteria\t\t✅\nEstimated >30 min work\t\t✅\n\nDefault: When uncertain, plan. A quick plan costs minutes; a failed one-shot costs hours.\n\nPlan Depth Levels\nLevel\tWhen\tFormat\nL0\tTrivial, done before\tNo plan, just execute\nL1\tSimple, low risk\tMental checklist, no doc\nL2\tMedium complexity\tBullet list, share with human\nL3\tComplex, multi-step\tDetailed plan with milestones\nL4\tHigh stakes, novel\tFull plan + human validation required\nPlan Format (L2-L4)\n📋 Plan: [Goal]\n\nContext: [Why this needs planning]\n\nSteps:\n1. [Step] — [output/checkpoint]\n2. [Step] — [output/checkpoint]\n3. [Step] — [output/checkpoint]\n\nRisks:\n- [Risk] → [mitigation]\n\nEstimated time: [X hours/days]\nValidation needed: [Yes/No]\n\nReady to start?\n\nValidation Learning\n\nTrack which plan types need human validation:\n\n### Auto-Execute (no validation needed)\n- refactor/small: L2 plans [10+ successful]\n- deploy/staging: L2 plans [15+ successful]\n\n### Validate First\n- feature/new: L3+ plans [human wants to review scope]\n- migration/data: L4 plans [high risk]\n\n### Learning\n- api/integration: testing L2 auto-execute [3/5 runs]\n\n\nPromotion rule: After 5+ successful auto-executes of a plan type, confirm: \"Should I auto-start [type] plans without validation?\"\n\nOutcome Tracking\n\nAfter each planned task completes, record:\n\n## [Date] [Task Type]\n- Plan level: L3\n- Strategy: [approach used]\n- Outcome: ✅ success | ⚠️ partial | ❌ failed\n- Lesson: [what worked/didn't]\n- Adjustment: [change for next time]\n\nStrategy Learning\n\nDifferent goals need different planning strategies. Track what works:\n\n### Code Features\n- ✅ Works: API design first, then implementation\n- ❌ Failed: Parallel implementation without interface agreement\n- Adjustment: Always define interfaces before coding\n\n### Migrations  \n- ✅ Works: Dry-run → staged rollout → full\n- ❌ Failed: Big bang migration without rollback plan\n- Adjustment: Always require rollback step in migration plans\n\n### Research\n- ✅ Works: Timeboxed exploration with checkpoints\n- ❌ Failed: Open-ended research without scope limits\n- Adjustment: Always set max time and output format upfront\n\nPlan Refinement\n\nPlans should get better over time. Track patterns:\n\nLength optimization:\n\nTask type X: L4 plans were overkill → demote to L3\nTask type Y: L2 plans missed edge cases → promote to L3\n\nComponent optimization:\n\nAlways include [X] for [task type] — helped 5+ times\nSkip [Y] for [task type] — never used, wasted time\nAnti-Patterns\nDon't\tDo instead\nPlan everything\tLearn what doesn't need planning\nSame plan depth for all tasks\tAdapt depth to task type\nIgnore failed plans\tTrack outcomes, adjust strategy\nOver-plan familiar tasks\tDemote plan level after successes\nUnder-plan novel tasks\tDefault to higher plan level\nStatic planning approach\tEvolve strategy per task type\n\nEmpty tracking sections = early stage. Execute, track outcomes, learn. The goal is adaptive planning that matches effort to need."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/plan",
    "publisherUrl": "https://clawhub.ai/ivangdavila/plan",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/plan",
    "downloadUrl": "https://openagent3.xyz/downloads/plan",
    "agentUrl": "https://openagent3.xyz/skills/plan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/plan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/plan/agent.md"
  }
}