{
  "schemaVersion": "1.0",
  "item": {
    "slug": "plans-methodology",
    "name": "Plans Methodology",
    "source": "tencent",
    "type": "skill",
    "category": "其他",
    "sourceUrl": "https://clawhub.ai/cramtek/plans-methodology",
    "canonicalUrl": "https://clawhub.ai/cramtek/plans-methodology",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/plans-methodology",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=plans-methodology",
    "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",
      "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/plans-methodology"
    },
    "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/plans-methodology",
    "agentPageUrl": "https://openagent3.xyz/skills/plans-methodology/agent",
    "manifestUrl": "https://openagent3.xyz/skills/plans-methodology/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/plans-methodology/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": "Plans Methodology",
        "body": "Structured work tracking for individuals or multi-agent teams. Each agent maintains plans/ in their workspace."
      },
      {
        "title": "Directory Structure",
        "body": "plans/\n  README.md\n  draft/          # Being defined, not yet approved\n  approved/       # Ready for execution\n  in_progress/    # Currently executing\n  completed/      # Done\n  archived/       # Historical reference\n\nEach plan is a folder: YYYY-MM-DD-plan-name/"
      },
      {
        "title": "Plan Contents",
        "body": "YYYY-MM-DD-plan-name/\n  specs/              # Problem statements, requirements\n  proposal.md         # Why: justification, impact, risks\n  design.md           # How: architecture, flows, decisions\n  tasks.md            # What: checkboxes, owners, phases"
      },
      {
        "title": "proposal.md",
        "body": "# Proposal: [Plan Name]\n\n## Status\nDraft | Submitted | Approved | Rejected\n\n## Parent Plan\n[agent]/plans/[state]/[plan-name] (if child plan)\n\n## Problem\nWhat problem are we solving?\n\n## Proposed Solution\nHigh-level approach.\n\n## Impact\nWhat changes? What improves?\n\n## Cost / Effort\nTime, resources, dependencies.\n\n## Risks\nWhat could go wrong?\n\n## Decision\nApproved by [name] on [date] | Rejected because [reason]"
      },
      {
        "title": "design.md",
        "body": "# Design: [Plan Name]\n\n## Overview\nWhat are we building/doing?\n\n## Architecture / Approach\nHow does it work? Diagrams, flows, decisions.\n\n## Dependencies\nWhat do we need? Other plans, external services, other agents.\n\n## Constraints\nLimitations, rules, non-negotiables.\n\n## Open Questions\nThings still to be decided."
      },
      {
        "title": "tasks.md",
        "body": "# Tasks: [Plan Name]\n\n## Summary\nBrief overview.\n\n## Tasks\n\n### Phase 1: [Name]\n- [x] Task description -> Owner\n  Completed YYYY-MM-DD. Notes.\n- [ ] Task description -> Owner\n  Details, acceptance criteria.\n- [ ] Delegate to [Agent]: [what] -> [Agent]\n  Child plan: [agent]/plans/[state]/[plan-name]"
      },
      {
        "title": "Lifecycle",
        "body": "Draft - Specs written, proposal drafted\nApproved - Proposal approved, design and tasks written\nIn Progress - Execution started\nCompleted - All tasks done\nArchived - Kept for reference\n\nMove the plan folder between state directories to change state."
      },
      {
        "title": "When to Create a Plan",
        "body": "Create when: multi-agent coordination needed, significant effort, multiple phases, needs approval, or progress tracking desired.\n\nSkip for: quick tasks, simple lookups, routine operations."
      },
      {
        "title": "Approval Authority",
        "body": "Define your own hierarchy. Typical pattern:\n\nOwner/CEO approves strategic plans\nLead agent can approve plans aligned with established vision\nSub-agents submit proposals to their lead for approval\n\nDocument your approval chain in your workspace's plans/README.md."
      },
      {
        "title": "Delegation",
        "body": "When delegating work to another agent:\n\nParent plan's tasks.md references the child plan path\nChild plan's proposal.md references the parent plan path\n\nExample in parent tasks.md:\n\n- [ ] Delegate to [Agent]: implement feature X\n  Child plan: [agent]/plans/in_progress/2026-02-20-feature-x\n\nExample in child proposal.md:\n\n## Parent Plan\n[lead-agent]/plans/in_progress/2026-02-20-parent-plan"
      },
      {
        "title": "On Session Start",
        "body": "Check plans/in_progress/ for active plans\nCheck plans/draft/ for plans awaiting action\nContinue where you left off"
      },
      {
        "title": "Granularity Tips",
        "body": "Not everything needs a plan. Use for significant, multi-step work.\nA single agent working on a quick fix does not need a plan.\nPlans shine when coordination, tracking, or approval is involved.\nKeep plan documents concise. Verbose plans get ignored."
      }
    ],
    "body": "Plans Methodology\n\nStructured work tracking for individuals or multi-agent teams. Each agent maintains plans/ in their workspace.\n\nDirectory Structure\nplans/\n  README.md\n  draft/          # Being defined, not yet approved\n  approved/       # Ready for execution\n  in_progress/    # Currently executing\n  completed/      # Done\n  archived/       # Historical reference\n\n\nEach plan is a folder: YYYY-MM-DD-plan-name/\n\nPlan Contents\nYYYY-MM-DD-plan-name/\n  specs/              # Problem statements, requirements\n  proposal.md         # Why: justification, impact, risks\n  design.md           # How: architecture, flows, decisions\n  tasks.md            # What: checkboxes, owners, phases\n\nproposal.md\n# Proposal: [Plan Name]\n\n## Status\nDraft | Submitted | Approved | Rejected\n\n## Parent Plan\n[agent]/plans/[state]/[plan-name] (if child plan)\n\n## Problem\nWhat problem are we solving?\n\n## Proposed Solution\nHigh-level approach.\n\n## Impact\nWhat changes? What improves?\n\n## Cost / Effort\nTime, resources, dependencies.\n\n## Risks\nWhat could go wrong?\n\n## Decision\nApproved by [name] on [date] | Rejected because [reason]\n\ndesign.md\n# Design: [Plan Name]\n\n## Overview\nWhat are we building/doing?\n\n## Architecture / Approach\nHow does it work? Diagrams, flows, decisions.\n\n## Dependencies\nWhat do we need? Other plans, external services, other agents.\n\n## Constraints\nLimitations, rules, non-negotiables.\n\n## Open Questions\nThings still to be decided.\n\ntasks.md\n# Tasks: [Plan Name]\n\n## Summary\nBrief overview.\n\n## Tasks\n\n### Phase 1: [Name]\n- [x] Task description -> Owner\n  Completed YYYY-MM-DD. Notes.\n- [ ] Task description -> Owner\n  Details, acceptance criteria.\n- [ ] Delegate to [Agent]: [what] -> [Agent]\n  Child plan: [agent]/plans/[state]/[plan-name]\n\nLifecycle\nDraft - Specs written, proposal drafted\nApproved - Proposal approved, design and tasks written\nIn Progress - Execution started\nCompleted - All tasks done\nArchived - Kept for reference\n\nMove the plan folder between state directories to change state.\n\nWhen to Create a Plan\n\nCreate when: multi-agent coordination needed, significant effort, multiple phases, needs approval, or progress tracking desired.\n\nSkip for: quick tasks, simple lookups, routine operations.\n\nApproval Authority\n\nDefine your own hierarchy. Typical pattern:\n\nOwner/CEO approves strategic plans\nLead agent can approve plans aligned with established vision\nSub-agents submit proposals to their lead for approval\n\nDocument your approval chain in your workspace's plans/README.md.\n\nDelegation\n\nWhen delegating work to another agent:\n\nParent plan's tasks.md references the child plan path\nChild plan's proposal.md references the parent plan path\n\nExample in parent tasks.md:\n\n- [ ] Delegate to [Agent]: implement feature X\n  Child plan: [agent]/plans/in_progress/2026-02-20-feature-x\n\n\nExample in child proposal.md:\n\n## Parent Plan\n[lead-agent]/plans/in_progress/2026-02-20-parent-plan\n\nOn Session Start\nCheck plans/in_progress/ for active plans\nCheck plans/draft/ for plans awaiting action\nContinue where you left off\nGranularity Tips\nNot everything needs a plan. Use for significant, multi-step work.\nA single agent working on a quick fix does not need a plan.\nPlans shine when coordination, tracking, or approval is involved.\nKeep plan documents concise. Verbose plans get ignored."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/cramtek/plans-methodology",
    "publisherUrl": "https://clawhub.ai/cramtek/plans-methodology",
    "owner": "cramtek",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/plans-methodology",
    "downloadUrl": "https://openagent3.xyz/downloads/plans-methodology",
    "agentUrl": "https://openagent3.xyz/skills/plans-methodology/agent",
    "manifestUrl": "https://openagent3.xyz/skills/plans-methodology/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/plans-methodology/agent.md"
  }
}