{
  "schemaVersion": "1.0",
  "item": {
    "slug": "session-handoff",
    "name": "Session Handoff",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/wpank/session-handoff",
    "canonicalUrl": "https://clawhub.ai/wpank/session-handoff",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/session-handoff",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-handoff",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/handoff-template.md",
      "references/resume-checklist.md",
      "scripts/check_staleness.py",
      "scripts/create_handoff.py"
    ],
    "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",
      "slug": "session-handoff",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T15:23:34.120Z",
      "expiresAt": "2026-05-10T15:23:34.120Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-handoff",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-handoff",
        "contentDisposition": "attachment; filename=\"session-handoff-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "session-handoff"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/session-handoff"
    },
    "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/session-handoff",
    "agentPageUrl": "https://openagent3.xyz/skills/session-handoff/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-handoff/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-handoff/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": "Session Handoff",
        "body": "Create handoff documents that enable fresh agents to continue work seamlessly."
      },
      {
        "title": "Mode Selection",
        "body": "Creating a handoff? User wants to save state, pause work, or context is full.\n→ Follow CREATE Workflow\n\nResuming from a handoff? User wants to continue previous work or load context.\n→ Follow RESUME Workflow\n\nProactive suggestion? After substantial work (5+ file edits, complex debugging, major decisions):\n\n\"Consider creating a handoff document to preserve this context. Say 'create handoff' when ready.\""
      },
      {
        "title": "Step 1: Generate Scaffold",
        "body": "Run the smart scaffold script:\n\npython scripts/create_handoff.py [task-slug]\n\nFor continuation handoffs (linking to previous work):\n\npython scripts/create_handoff.py \"auth-part-2\" --continues-from 2024-01-15-auth.md\n\nThe script creates .claude/handoffs/ directory and generates a timestamped file with pre-filled metadata (timestamp, project path, git branch, recent commits, modified files)."
      },
      {
        "title": "Step 2: Complete the Document",
        "body": "Open the generated file and fill all [TODO: ...] sections. Prioritize:\n\nCurrent State Summary - What's happening right now\nImportant Context - Critical info the next agent MUST know\nImmediate Next Steps - Clear, actionable first steps\nDecisions Made - Choices with rationale (not just outcomes)\n\nSee references/handoff-template.md for full structure."
      },
      {
        "title": "Step 3: Validate",
        "body": "python scripts/validate_handoff.py <handoff-file>\n\nChecks:\n\nNo [TODO: ...] placeholders remaining\nRequired sections present and populated\nNo potential secrets detected (API keys, passwords, tokens)\nReferenced files exist\nQuality score (0-100)\n\nDo not finalize handoffs with secrets detected or score below 70."
      },
      {
        "title": "Step 4: Confirm",
        "body": "Report to user:\n\nHandoff file location\nValidation score and warnings\nSummary of captured context\nFirst action item for next session"
      },
      {
        "title": "Step 1: Find Handoffs",
        "body": "python scripts/list_handoffs.py"
      },
      {
        "title": "Step 2: Check Staleness",
        "body": "python scripts/check_staleness.py <handoff-file>\n\nStaleness levels:\n\nFRESH: Safe to resume\nSLIGHTLY_STALE: Review changes first\nSTALE: Verify context carefully\nVERY_STALE: Consider creating fresh handoff"
      },
      {
        "title": "Step 3: Load and Verify",
        "body": "Read the handoff document completely. If part of a chain, also read the previous handoff.\n\nFollow references/resume-checklist.md:\n\nVerify project directory and git branch match\nCheck if blockers resolved\nValidate assumptions still hold\nReview modified files for conflicts"
      },
      {
        "title": "Step 4: Begin Work",
        "body": "Start with \"Immediate Next Steps\" item #1.\n\nReference as you work:\n\n\"Critical Files\" for important locations\n\"Key Patterns Discovered\" for conventions\n\"Potential Gotchas\" to avoid known issues"
      },
      {
        "title": "Handoff Chaining",
        "body": "For long-running projects, chain handoffs to maintain context lineage:\n\nhandoff-1.md (initial work)\n    ↓\nhandoff-2.md --continues-from handoff-1.md\n    ↓\nhandoff-3.md --continues-from handoff-2.md\n\nWhen resuming from a chain, read the most recent handoff first, then reference predecessors as needed."
      },
      {
        "title": "Storage",
        "body": "Location: .claude/handoffs/\nNaming: YYYY-MM-DD-HHMMSS-[slug].md"
      },
      {
        "title": "Quality Criteria",
        "body": "Good handoffs have:\n\nZero ambiguity about current state\nClear, numbered next steps\nRationale for decisions (not just outcomes)\nFile paths with line numbers where relevant\nNo secrets or credentials"
      },
      {
        "title": "NEVER",
        "body": "Include API keys, passwords, tokens, or credentials\nLeave TODO placeholders in finalized handoffs\nSkip the validation step\nCreate handoffs without the Important Context section\nFinalize handoffs with quality score below 70"
      }
    ],
    "body": "Session Handoff\n\nCreate handoff documents that enable fresh agents to continue work seamlessly.\n\nMode Selection\n\nCreating a handoff? User wants to save state, pause work, or context is full. → Follow CREATE Workflow\n\nResuming from a handoff? User wants to continue previous work or load context. → Follow RESUME Workflow\n\nProactive suggestion? After substantial work (5+ file edits, complex debugging, major decisions):\n\n\"Consider creating a handoff document to preserve this context. Say 'create handoff' when ready.\"\n\nCREATE Workflow\nStep 1: Generate Scaffold\n\nRun the smart scaffold script:\n\npython scripts/create_handoff.py [task-slug]\n\n\nFor continuation handoffs (linking to previous work):\n\npython scripts/create_handoff.py \"auth-part-2\" --continues-from 2024-01-15-auth.md\n\n\nThe script creates .claude/handoffs/ directory and generates a timestamped file with pre-filled metadata (timestamp, project path, git branch, recent commits, modified files).\n\nStep 2: Complete the Document\n\nOpen the generated file and fill all [TODO: ...] sections. Prioritize:\n\nCurrent State Summary - What's happening right now\nImportant Context - Critical info the next agent MUST know\nImmediate Next Steps - Clear, actionable first steps\nDecisions Made - Choices with rationale (not just outcomes)\n\nSee references/handoff-template.md for full structure.\n\nStep 3: Validate\npython scripts/validate_handoff.py <handoff-file>\n\n\nChecks:\n\nNo [TODO: ...] placeholders remaining\nRequired sections present and populated\nNo potential secrets detected (API keys, passwords, tokens)\nReferenced files exist\nQuality score (0-100)\n\nDo not finalize handoffs with secrets detected or score below 70.\n\nStep 4: Confirm\n\nReport to user:\n\nHandoff file location\nValidation score and warnings\nSummary of captured context\nFirst action item for next session\nRESUME Workflow\nStep 1: Find Handoffs\npython scripts/list_handoffs.py\n\nStep 2: Check Staleness\npython scripts/check_staleness.py <handoff-file>\n\n\nStaleness levels:\n\nFRESH: Safe to resume\nSLIGHTLY_STALE: Review changes first\nSTALE: Verify context carefully\nVERY_STALE: Consider creating fresh handoff\nStep 3: Load and Verify\n\nRead the handoff document completely. If part of a chain, also read the previous handoff.\n\nFollow references/resume-checklist.md:\n\nVerify project directory and git branch match\nCheck if blockers resolved\nValidate assumptions still hold\nReview modified files for conflicts\nStep 4: Begin Work\n\nStart with \"Immediate Next Steps\" item #1.\n\nReference as you work:\n\n\"Critical Files\" for important locations\n\"Key Patterns Discovered\" for conventions\n\"Potential Gotchas\" to avoid known issues\nHandoff Chaining\n\nFor long-running projects, chain handoffs to maintain context lineage:\n\nhandoff-1.md (initial work)\n    ↓\nhandoff-2.md --continues-from handoff-1.md\n    ↓\nhandoff-3.md --continues-from handoff-2.md\n\n\nWhen resuming from a chain, read the most recent handoff first, then reference predecessors as needed.\n\nStorage\n\nLocation: .claude/handoffs/ Naming: YYYY-MM-DD-HHMMSS-[slug].md\n\nQuality Criteria\n\nGood handoffs have:\n\nZero ambiguity about current state\nClear, numbered next steps\nRationale for decisions (not just outcomes)\nFile paths with line numbers where relevant\nNo secrets or credentials\nNEVER\nInclude API keys, passwords, tokens, or credentials\nLeave TODO placeholders in finalized handoffs\nSkip the validation step\nCreate handoffs without the Important Context section\nFinalize handoffs with quality score below 70"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/session-handoff",
    "publisherUrl": "https://clawhub.ai/wpank/session-handoff",
    "owner": "wpank",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/session-handoff",
    "downloadUrl": "https://openagent3.xyz/downloads/session-handoff",
    "agentUrl": "https://openagent3.xyz/skills/session-handoff/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-handoff/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-handoff/agent.md"
  }
}