{
  "schemaVersion": "1.0",
  "item": {
    "slug": "planning-files",
    "name": "Planning With Files",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/wpank/planning-files",
    "canonicalUrl": "https://clawhub.ai/wpank/planning-files",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/planning-files",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=planning-files",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "templates/progress.md",
      "templates/task_plan.md",
      "templates/findings.md",
      "scripts/init-session.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": "2026-04-30T16:55:25.780Z",
      "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/planning-files"
    },
    "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/planning-files",
    "agentPageUrl": "https://openagent3.xyz/skills/planning-files/agent",
    "manifestUrl": "https://openagent3.xyz/skills/planning-files/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/planning-files/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": "Planning with Files",
        "body": "Use persistent markdown files as your \"working memory on disk.\" Based on context engineering principles from Manus."
      },
      {
        "title": "OpenClaw / Moltbot / Clawbot",
        "body": "npx clawhub@latest install planning-with-files"
      },
      {
        "title": "WHAT This Skill Does",
        "body": "Treats the filesystem as persistent memory to overcome context window limitations. Three files track your state:\n\nFilePurposeUpdate Frequencytask_plan.mdPhases, progress, decisionsAfter each phasefindings.mdResearch, discoveries, decisionsAfter ANY discoveryprogress.mdSession log, test results, errorsThroughout session"
      },
      {
        "title": "WHEN to Use",
        "body": "Use for:\n\nMulti-step tasks (3+ steps)\nResearch tasks requiring web search\nBuilding/creating projects from scratch\nTasks spanning >5 tool calls\nAnything requiring organization across multiple files\nTasks where losing context would cause rework\n\nSkip for:\n\nSimple questions\nSingle-file edits\nQuick lookups\nTasks completable in 1-2 actions\n\nKeywords: complex task, multi-step, research, build project, create application, plan, organize"
      },
      {
        "title": "The Core Pattern",
        "body": "Context Window = RAM (volatile, limited)\nFilesystem = Disk (persistent, unlimited)\n\n→ Anything important gets written to disk."
      },
      {
        "title": "Phase 1: Create Planning Files",
        "body": "Before starting ANY complex task, create all three files in your project root:\n\nCreate task_plan.md — Copy from templates/task_plan.md\nCreate findings.md — Copy from templates/findings.md\nCreate progress.md — Copy from templates/progress.md"
      },
      {
        "title": "Phase 2: Execute with Discipline",
        "body": "Follow these rules during execution:\n\nThe 2-Action Rule:\n\nAfter every 2 view/browser/search operations, IMMEDIATELY save findings to text files.\n\nVisual/multimodal content doesn't persist — write it down before it's lost.\n\nRead Before Decide:\nBefore major decisions, read your plan file. This keeps goals in your attention window after many tool calls.\n\nUpdate After Act:\nAfter completing any phase:\n\nMark phase status: in_progress → complete\nLog any errors encountered\nNote files created/modified\n\nLog ALL Errors:\nEvery error goes in the plan file. This prevents repetition."
      },
      {
        "title": "Phase 3: Handle Errors Systematically",
        "body": "The 3-Strike Protocol:\n\nATTEMPT 1: Diagnose & Fix\n  → Read error carefully\n  → Identify root cause\n  → Apply targeted fix\n\nATTEMPT 2: Alternative Approach\n  → Same error? Try different method\n  → Different tool? Different library?\n  → NEVER repeat exact same failing action\n\nATTEMPT 3: Broader Rethink\n  → Question assumptions\n  → Search for solutions\n  → Consider updating the plan\n\nAFTER 3 FAILURES: Escalate to User\n  → Explain what you tried\n  → Share the specific error\n  → Ask for guidance\n\nCritical: if action_failed: next_action != same_action"
      },
      {
        "title": "Phase 4: Verify Completion",
        "body": "Use the 5-Question Reboot Test. If you can answer these, your context is solid:\n\nQuestionAnswer SourceWhere am I?Current phase in task_plan.mdWhere am I going?Remaining phasesWhat's the goal?Goal statement in planWhat have I learned?findings.mdWhat have I done?progress.md"
      },
      {
        "title": "Quick Reference: Read vs Write",
        "body": "SituationActionReasonJust wrote a fileDON'T readContent still in contextViewed image/PDFWrite findings NOWMultimodal → text before lostBrowser returned dataWrite to fileScreenshots don't persistStarting new phaseRead plan/findingsRe-orient if context staleError occurredRead relevant fileNeed current state to fixResuming after gapRead all planning filesRecover state"
      },
      {
        "title": "Session Recovery",
        "body": "When starting a new session, check for previous work:\n\n# Check if planning files exist\nls task_plan.md findings.md progress.md 2>/dev/null\n\n# If they exist, read them all before continuing\ncat task_plan.md findings.md progress.md\n\nIf planning files exist from a previous session:\n\nRead all three files to recover context\nRun git diff --stat to see what changed\nUpdate planning files with any missing context\nContinue from where you left off"
      },
      {
        "title": "Templates",
        "body": "Copy these to start:\n\ntemplates/task_plan.md — Phase tracking\ntemplates/findings.md — Research storage\ntemplates/progress.md — Session logging"
      },
      {
        "title": "Scripts",
        "body": "Helper scripts for automation:\n\nscripts/init-session.sh — Initialize all planning files\nscripts/check-complete.sh — Verify all phases complete"
      },
      {
        "title": "References",
        "body": "references/manus-principles.md — Context engineering principles from Manus"
      },
      {
        "title": "Anti-Patterns",
        "body": "Don'tDo InsteadUse TodoWrite for persistenceCreate task_plan.md fileState goals once and forgetRe-read plan before decisionsHide errors and retry silentlyLog errors to plan fileStuff everything in contextStore large content in filesStart executing immediatelyCreate plan file FIRSTRepeat failed actionsTrack attempts, mutate approachCreate files in skill directoryCreate files in your project"
      },
      {
        "title": "NEVER Do",
        "body": "NEVER start a complex task without task_plan.md — this is non-negotiable\nNEVER repeat a failed action exactly — track what you tried, mutate the approach\nNEVER ignore errors — log every error with resolution attempts\nNEVER rely on memory after >10 tool calls — re-read your plan\nNEVER skip the 2-Action Rule for visual content — multimodal data gets lost\nNEVER proceed past 3 failures without escalating — ask the user for help\nNEVER create planning files in the skill directory — they go in your project root"
      }
    ],
    "body": "Planning with Files\n\nUse persistent markdown files as your \"working memory on disk.\" Based on context engineering principles from Manus.\n\nInstallation\nOpenClaw / Moltbot / Clawbot\nnpx clawhub@latest install planning-with-files\n\nWHAT This Skill Does\n\nTreats the filesystem as persistent memory to overcome context window limitations. Three files track your state:\n\nFile\tPurpose\tUpdate Frequency\ntask_plan.md\tPhases, progress, decisions\tAfter each phase\nfindings.md\tResearch, discoveries, decisions\tAfter ANY discovery\nprogress.md\tSession log, test results, errors\tThroughout session\nWHEN to Use\n\nUse for:\n\nMulti-step tasks (3+ steps)\nResearch tasks requiring web search\nBuilding/creating projects from scratch\nTasks spanning >5 tool calls\nAnything requiring organization across multiple files\nTasks where losing context would cause rework\n\nSkip for:\n\nSimple questions\nSingle-file edits\nQuick lookups\nTasks completable in 1-2 actions\n\nKeywords: complex task, multi-step, research, build project, create application, plan, organize\n\nThe Core Pattern\nContext Window = RAM (volatile, limited)\nFilesystem = Disk (persistent, unlimited)\n\n→ Anything important gets written to disk.\n\nWorkflow\nPhase 1: Create Planning Files\n\nBefore starting ANY complex task, create all three files in your project root:\n\nCreate task_plan.md — Copy from templates/task_plan.md\nCreate findings.md — Copy from templates/findings.md\nCreate progress.md — Copy from templates/progress.md\nPhase 2: Execute with Discipline\n\nFollow these rules during execution:\n\nThe 2-Action Rule:\n\nAfter every 2 view/browser/search operations, IMMEDIATELY save findings to text files.\n\nVisual/multimodal content doesn't persist — write it down before it's lost.\n\nRead Before Decide: Before major decisions, read your plan file. This keeps goals in your attention window after many tool calls.\n\nUpdate After Act: After completing any phase:\n\nMark phase status: in_progress → complete\nLog any errors encountered\nNote files created/modified\n\nLog ALL Errors: Every error goes in the plan file. This prevents repetition.\n\nPhase 3: Handle Errors Systematically\n\nThe 3-Strike Protocol:\n\nATTEMPT 1: Diagnose & Fix\n  → Read error carefully\n  → Identify root cause\n  → Apply targeted fix\n\nATTEMPT 2: Alternative Approach\n  → Same error? Try different method\n  → Different tool? Different library?\n  → NEVER repeat exact same failing action\n\nATTEMPT 3: Broader Rethink\n  → Question assumptions\n  → Search for solutions\n  → Consider updating the plan\n\nAFTER 3 FAILURES: Escalate to User\n  → Explain what you tried\n  → Share the specific error\n  → Ask for guidance\n\n\nCritical: if action_failed: next_action != same_action\n\nPhase 4: Verify Completion\n\nUse the 5-Question Reboot Test. If you can answer these, your context is solid:\n\nQuestion\tAnswer Source\nWhere am I?\tCurrent phase in task_plan.md\nWhere am I going?\tRemaining phases\nWhat's the goal?\tGoal statement in plan\nWhat have I learned?\tfindings.md\nWhat have I done?\tprogress.md\nQuick Reference: Read vs Write\nSituation\tAction\tReason\nJust wrote a file\tDON'T read\tContent still in context\nViewed image/PDF\tWrite findings NOW\tMultimodal → text before lost\nBrowser returned data\tWrite to file\tScreenshots don't persist\nStarting new phase\tRead plan/findings\tRe-orient if context stale\nError occurred\tRead relevant file\tNeed current state to fix\nResuming after gap\tRead all planning files\tRecover state\nSession Recovery\n\nWhen starting a new session, check for previous work:\n\n# Check if planning files exist\nls task_plan.md findings.md progress.md 2>/dev/null\n\n# If they exist, read them all before continuing\ncat task_plan.md findings.md progress.md\n\n\nIf planning files exist from a previous session:\n\nRead all three files to recover context\nRun git diff --stat to see what changed\nUpdate planning files with any missing context\nContinue from where you left off\nTemplates\n\nCopy these to start:\n\ntemplates/task_plan.md — Phase tracking\ntemplates/findings.md — Research storage\ntemplates/progress.md — Session logging\nScripts\n\nHelper scripts for automation:\n\nscripts/init-session.sh — Initialize all planning files\nscripts/check-complete.sh — Verify all phases complete\nReferences\nreferences/manus-principles.md — Context engineering principles from Manus\nAnti-Patterns\nDon't\tDo Instead\nUse TodoWrite for persistence\tCreate task_plan.md file\nState goals once and forget\tRe-read plan before decisions\nHide errors and retry silently\tLog errors to plan file\nStuff everything in context\tStore large content in files\nStart executing immediately\tCreate plan file FIRST\nRepeat failed actions\tTrack attempts, mutate approach\nCreate files in skill directory\tCreate files in your project\nNEVER Do\nNEVER start a complex task without task_plan.md — this is non-negotiable\nNEVER repeat a failed action exactly — track what you tried, mutate the approach\nNEVER ignore errors — log every error with resolution attempts\nNEVER rely on memory after >10 tool calls — re-read your plan\nNEVER skip the 2-Action Rule for visual content — multimodal data gets lost\nNEVER proceed past 3 failures without escalating — ask the user for help\nNEVER create planning files in the skill directory — they go in your project root"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/planning-files",
    "publisherUrl": "https://clawhub.ai/wpank/planning-files",
    "owner": "wpank",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/planning-files",
    "downloadUrl": "https://openagent3.xyz/downloads/planning-files",
    "agentUrl": "https://openagent3.xyz/skills/planning-files/agent",
    "manifestUrl": "https://openagent3.xyz/skills/planning-files/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/planning-files/agent.md"
  }
}