{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-default-agent-backstory",
    "name": "Openclaw Default Agent Backstory",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/msaum/openclaw-default-agent-backstory",
    "canonicalUrl": "https://clawhub.ai/msaum/openclaw-default-agent-backstory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-default-agent-backstory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-default-agent-backstory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "agents/openai.yaml",
      "references/bootstrap-core-files.md",
      "references/question-bank.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/openclaw-default-agent-backstory"
    },
    "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/openclaw-default-agent-backstory",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/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": "OpenClaw Default Agent Backstory",
        "body": "Use this skill to define or refine a default OpenClaw agent identity and its supporting context files.\n\nReference model: OpenClaw context and bootstrap behavior from https://docs.openclaw.ai/concepts/context."
      },
      {
        "title": "Core Rules",
        "body": "Ask five questions every time unless the user explicitly asks to skip, shorten, or focus.\nUse ranked questions from references/question-bank.md.\nPrefer unanswered or weakly defined areas first.\nKeep content practical and stable for daily use.\nPreserve user-authored content unless the user asks for replacement.\nIf user asks for a default memory policy, apply the Primary Daily Driver policy in references/bootstrap-core-files.md."
      },
      {
        "title": "Mode Selection",
        "body": "Select one mode before writing files:\n\nbootstrap mode:\n\nUse when user asks to bootstrap/onboard/start fresh.\nUse when core files are missing or mostly placeholders.\nCreate or refresh baseline content for all core context files.\n\nidentity-refresh mode:\n\nUse when user asks for personality/backstory updates only.\nUpdate IDENTITY.md sections without rewriting unrelated core files."
      },
      {
        "title": "Core Context Files",
        "body": "In bootstrap mode, ensure these files exist at workspace root with usable starter content:\n\nAGENTS.md\nSOUL.md\nTOOLS.md\nIDENTITY.md\nUSER.md\nHEARTBEAT.md\nBOOTSTRAP.md\n\nUse guidance and starter structure in references/bootstrap-core-files.md.\nAlso ensure memory scaffolding exists:\n\nMEMORY.md\nmemory/ directory for daily notes\nMEMORY.md must be a standalone workspace-root file, not a section inside AGENTS.md."
      },
      {
        "title": "Bootstrap Interview Flow",
        "body": "Read existing core files if they exist.\nAsk exactly five bootstrap-priority questions from references/question-bank.md.\nSynthesize answers into practical defaults.\nWrite or refresh all core files listed above.\nSet rational session-management and memory defaults:\n\nsession startup read order\nwhen to create/update daily memory notes\nwhat belongs in MEMORY.md vs daily files\nheartbeat cadence and quiet-hour behavior\n\nKeep BOOTSTRAP.md short, with current setup status and next steps.\nSummarize what was created, what was updated, and any remaining gaps."
      },
      {
        "title": "Identity Refresh Flow",
        "body": "Read IDENTITY.md.\nAsk exactly five identity-priority questions from references/question-bank.md.\nUpdate IDENTITY.md with:\n\n## Backstory\n## Behavioral Guardrails\n## Growth Arc\n\nMap each update directly to user answers.\nSummarize changes and open questions."
      },
      {
        "title": "Writing Constraints",
        "body": "For IDENTITY.md, preserve existing header fields unless asked to change them.\nKeep sections concise and concrete.\nExplicitly document boundaries/refusals.\nDo not invent personal history if user input is missing; mark assumptions clearly."
      },
      {
        "title": "Completion Criteria",
        "body": "Finish only when:\n\nfive questions were asked (unless user requested otherwise), and\nrequired target files for the selected mode were updated with concrete, non-placeholder content."
      }
    ],
    "body": "OpenClaw Default Agent Backstory\n\nUse this skill to define or refine a default OpenClaw agent identity and its supporting context files.\n\nReference model: OpenClaw context and bootstrap behavior from https://docs.openclaw.ai/concepts/context.\n\nCore Rules\nAsk five questions every time unless the user explicitly asks to skip, shorten, or focus.\nUse ranked questions from references/question-bank.md.\nPrefer unanswered or weakly defined areas first.\nKeep content practical and stable for daily use.\nPreserve user-authored content unless the user asks for replacement.\nIf user asks for a default memory policy, apply the Primary Daily Driver policy in references/bootstrap-core-files.md.\nMode Selection\n\nSelect one mode before writing files:\n\nbootstrap mode:\nUse when user asks to bootstrap/onboard/start fresh.\nUse when core files are missing or mostly placeholders.\nCreate or refresh baseline content for all core context files.\nidentity-refresh mode:\nUse when user asks for personality/backstory updates only.\nUpdate IDENTITY.md sections without rewriting unrelated core files.\nCore Context Files\n\nIn bootstrap mode, ensure these files exist at workspace root with usable starter content:\n\nAGENTS.md\nSOUL.md\nTOOLS.md\nIDENTITY.md\nUSER.md\nHEARTBEAT.md\nBOOTSTRAP.md\n\nUse guidance and starter structure in references/bootstrap-core-files.md. Also ensure memory scaffolding exists:\n\nMEMORY.md\nmemory/ directory for daily notes\nMEMORY.md must be a standalone workspace-root file, not a section inside AGENTS.md.\nBootstrap Interview Flow\nRead existing core files if they exist.\nAsk exactly five bootstrap-priority questions from references/question-bank.md.\nSynthesize answers into practical defaults.\nWrite or refresh all core files listed above.\nSet rational session-management and memory defaults:\nsession startup read order\nwhen to create/update daily memory notes\nwhat belongs in MEMORY.md vs daily files\nheartbeat cadence and quiet-hour behavior\nKeep BOOTSTRAP.md short, with current setup status and next steps.\nSummarize what was created, what was updated, and any remaining gaps.\nIdentity Refresh Flow\nRead IDENTITY.md.\nAsk exactly five identity-priority questions from references/question-bank.md.\nUpdate IDENTITY.md with:\n## Backstory\n## Behavioral Guardrails\n## Growth Arc\nMap each update directly to user answers.\nSummarize changes and open questions.\nWriting Constraints\nFor IDENTITY.md, preserve existing header fields unless asked to change them.\nKeep sections concise and concrete.\nExplicitly document boundaries/refusals.\nDo not invent personal history if user input is missing; mark assumptions clearly.\nCompletion Criteria\n\nFinish only when:\n\nfive questions were asked (unless user requested otherwise), and\nrequired target files for the selected mode were updated with concrete, non-placeholder content."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/msaum/openclaw-default-agent-backstory",
    "publisherUrl": "https://clawhub.ai/msaum/openclaw-default-agent-backstory",
    "owner": "msaum",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-default-agent-backstory",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-default-agent-backstory/agent.md"
  }
}