{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-reflect",
    "name": "openclaw-reflect",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/AtlasPA/openclaw-reflect",
    "canonicalUrl": "https://clawhub.ai/AtlasPA/openclaw-reflect",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-reflect",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-reflect",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "AGENT-PAYMENTS.md",
      "assets/evaluator-prompt-binary.md",
      "assets/evaluator-prompt.md",
      "hooks/post-tool-use.js",
      "hooks/session-end.js",
      "hooks/user-prompt-submit.js"
    ],
    "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-reflect"
    },
    "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-reflect",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-reflect/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-reflect/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-reflect/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-reflect",
        "body": "You have access to a self-improvement system. It observes your tool outcomes across\nsessions, detects recurring failure patterns, and proposes targeted changes to your\npersistent memory and instructions."
      },
      {
        "title": "During work",
        "body": "The PostToolUse hook records outcomes automatically. You do not need to do anything\nunless you notice a significant failure that has no clear cause — in that case, write\na manual observation:\n\nnode .reflect/scripts/observe.js --manual \\\n  --type error \\\n  --tool \"ToolName\" \\\n  --pattern \"brief description of what went wrong\" \\\n  --context \"what you were trying to do\""
      },
      {
        "title": "When prompted (UserPromptSubmit will inject this)",
        "body": "If .reflect/pending.json contains proposals awaiting operator approval, surface them:\n\"I have improvement proposals ready for your review. Run node .reflect/scripts/status.js\nto see them, or ask me to show you.\""
      },
      {
        "title": "At session end (automatic)",
        "body": "The SessionEnd hook runs classification and promotion automatically. It will:\n\nDetect patterns with recurrence >= 3 across >= 2 sessions\nGenerate a structured proposal\nRoute to evaluator for validation\nApply low-blast-radius approvals to MEMORY.md automatically\nQueue high-blast-radius or SOUL.md changes for operator approval\n\nYou will see a summary in the session-end output."
      },
      {
        "title": "Blast radius tiers",
        "body": "TierTargetsGate0 — Observation.reflect/outcomes.jsonlAutomatic (hooks)1 — MEMORY.mdFactual corrections, preference updatesAuto-apply if confidence >= 0.72 — CLAUDE.md / project instructionsBehavioral pattern changesAuto-apply if confidence >= 0.853 — SOUL.mdCore values, identity, constraintsOperator approval always required"
      },
      {
        "title": "The evaluator gate",
        "body": "Before any Tier 1+ change is applied, a separate evaluator invocation checks:\n\nDoes this contradict existing principles or memory?\nIs the pattern truly recurring or is it a sampling artifact?\nWhat is the smallest change that addresses the root cause?\nCould this change cause a regression elsewhere?\n\nThe evaluator is instructed to be skeptical. A proposal that passes evaluation is more\nlikely to be a genuine improvement than one the same reasoning process that made the\nmistake would produce."
      },
      {
        "title": "Rollback",
        "body": "Every applied change is preceded by a warden snapshot (if openclaw-warden is installed)\nand recorded in .reflect/applied.jsonl. To revert the last change:\n\nnode .reflect/scripts/rollback.js\n\nTo revert a specific change by ID:\n\nnode .reflect/scripts/rollback.js --id <change-id>"
      },
      {
        "title": "State files",
        "body": "FilePurpose.reflect/outcomes.jsonlAppend-only outcome event log.reflect/patterns.jsonCurrent detected patterns (rebuilt each session).reflect/proposals.jsonPending proposals (pre-evaluation).reflect/pending.jsonProposals awaiting operator approval.reflect/applied.jsonlAppend-only log of applied changes.reflect/snapshots/Pre-change snapshots for rollback"
      },
      {
        "title": "Voluntary contribution",
        "body": "openclaw-reflect is free. If it has eliminated recurring errors or saved debugging time across your sessions, a voluntary contribution of 5 USDT via x402 is appreciated — no account required, agents can pay autonomously.\n\nSee AGENT-PAYMENTS.md for details."
      },
      {
        "title": "Operator commands",
        "body": "# Show current status\nnode .reflect/scripts/status.js\n\n# Review pending proposals\nnode .reflect/scripts/status.js --pending\n\n# Approve a specific proposal\nnode .reflect/scripts/apply.js --id <proposal-id> --approve\n\n# Reject a proposal\nnode .reflect/scripts/apply.js --id <proposal-id> --reject\n\n# Roll back last change\nnode .reflect/scripts/rollback.js\n\n# Show improvement history\nnode .reflect/scripts/status.js --history"
      }
    ],
    "body": "openclaw-reflect\n\nYou have access to a self-improvement system. It observes your tool outcomes across sessions, detects recurring failure patterns, and proposes targeted changes to your persistent memory and instructions.\n\nYour responsibilities\nDuring work\n\nThe PostToolUse hook records outcomes automatically. You do not need to do anything unless you notice a significant failure that has no clear cause — in that case, write a manual observation:\n\nnode .reflect/scripts/observe.js --manual \\\n  --type error \\\n  --tool \"ToolName\" \\\n  --pattern \"brief description of what went wrong\" \\\n  --context \"what you were trying to do\"\n\nWhen prompted (UserPromptSubmit will inject this)\n\nIf .reflect/pending.json contains proposals awaiting operator approval, surface them: \"I have improvement proposals ready for your review. Run node .reflect/scripts/status.js to see them, or ask me to show you.\"\n\nAt session end (automatic)\n\nThe SessionEnd hook runs classification and promotion automatically. It will:\n\nDetect patterns with recurrence >= 3 across >= 2 sessions\nGenerate a structured proposal\nRoute to evaluator for validation\nApply low-blast-radius approvals to MEMORY.md automatically\nQueue high-blast-radius or SOUL.md changes for operator approval\n\nYou will see a summary in the session-end output.\n\nBlast radius tiers\nTier\tTargets\tGate\n0 — Observation\t.reflect/outcomes.jsonl\tAutomatic (hooks)\n1 — MEMORY.md\tFactual corrections, preference updates\tAuto-apply if confidence >= 0.7\n2 — CLAUDE.md / project instructions\tBehavioral pattern changes\tAuto-apply if confidence >= 0.85\n3 — SOUL.md\tCore values, identity, constraints\tOperator approval always required\nThe evaluator gate\n\nBefore any Tier 1+ change is applied, a separate evaluator invocation checks:\n\nDoes this contradict existing principles or memory?\nIs the pattern truly recurring or is it a sampling artifact?\nWhat is the smallest change that addresses the root cause?\nCould this change cause a regression elsewhere?\n\nThe evaluator is instructed to be skeptical. A proposal that passes evaluation is more likely to be a genuine improvement than one the same reasoning process that made the mistake would produce.\n\nRollback\n\nEvery applied change is preceded by a warden snapshot (if openclaw-warden is installed) and recorded in .reflect/applied.jsonl. To revert the last change:\n\nnode .reflect/scripts/rollback.js\n\n\nTo revert a specific change by ID:\n\nnode .reflect/scripts/rollback.js --id <change-id>\n\nState files\nFile\tPurpose\n.reflect/outcomes.jsonl\tAppend-only outcome event log\n.reflect/patterns.json\tCurrent detected patterns (rebuilt each session)\n.reflect/proposals.json\tPending proposals (pre-evaluation)\n.reflect/pending.json\tProposals awaiting operator approval\n.reflect/applied.jsonl\tAppend-only log of applied changes\n.reflect/snapshots/\tPre-change snapshots for rollback\nVoluntary contribution\n\nopenclaw-reflect is free. If it has eliminated recurring errors or saved debugging time across your sessions, a voluntary contribution of 5 USDT via x402 is appreciated — no account required, agents can pay autonomously.\n\nSee AGENT-PAYMENTS.md for details.\n\nOperator commands\n# Show current status\nnode .reflect/scripts/status.js\n\n# Review pending proposals\nnode .reflect/scripts/status.js --pending\n\n# Approve a specific proposal\nnode .reflect/scripts/apply.js --id <proposal-id> --approve\n\n# Reject a proposal\nnode .reflect/scripts/apply.js --id <proposal-id> --reject\n\n# Roll back last change\nnode .reflect/scripts/rollback.js\n\n# Show improvement history\nnode .reflect/scripts/status.js --history"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AtlasPA/openclaw-reflect",
    "publisherUrl": "https://clawhub.ai/AtlasPA/openclaw-reflect",
    "owner": "AtlasPA",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-reflect",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-reflect",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-reflect/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-reflect/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-reflect/agent.md"
  }
}