{
  "schemaVersion": "1.0",
  "item": {
    "slug": "self",
    "name": "Self",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Kirchlive/self",
    "canonicalUrl": "https://clawhub.ai/Kirchlive/self",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/self",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=self",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/anti-patterns.md",
      "references/reflection-levels.md",
      "references/self-state-schema.md",
      "references/self-template.md",
      "references/trigger-model.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",
      "slug": "self",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T14:12:39.256Z",
      "expiresAt": "2026-05-10T14:12:39.256Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=self",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=self",
        "contentDisposition": "attachment; filename=\"self-1.1.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "self"
      },
      "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/self"
    },
    "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/self",
    "agentPageUrl": "https://openagent3.xyz/skills/self/agent",
    "manifestUrl": "https://openagent3.xyz/skills/self/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/self/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": "Self — Organic Personality Development (v1.1)",
        "body": "Agents have identity (SOUL.md) but often no reliable growth loop. This skill keeps growth authentic while adding minimal structure so reflection doesn't silently die."
      },
      {
        "title": "Core Principle",
        "body": "SOUL.md = who you are (foundation, only change with human approval)\nSELF.md = who you're becoming (living observations)\nSchedule the check, not the content\n\nChecks can be periodic\nEntries must remain genuine (no performative filler)"
      },
      {
        "title": "Setup",
        "body": "Create SELF.md in workspace root using references/self-template.md.\nAdd SELF.md to AGENTS.md session reading.\nAdd heartbeat check block from references/trigger-model.md to HEARTBEAT.md.\nCreate state file memory/self-state.json using references/self-state-schema.md."
      },
      {
        "title": "Operating Model",
        "body": "Read references/trigger-model.md for exact rules."
      },
      {
        "title": "Cadence (recommended baseline)",
        "body": "Micro check: every 3 hours (heartbeat-triggered)\nMeso review: every 7 days\nMacro review: every 30 days"
      },
      {
        "title": "Important",
        "body": "A micro check does not mean auto-writing a SELF entry. It only decides whether reflection is due."
      },
      {
        "title": "Hard Triggers (write now)",
        "body": "Create/update SELF entry when one of these happened:\n\nYou were corrected on reasoning style or behavior pattern\nYou noticed repeated bias/avoidance pattern (>=2 times)\nYou made a decision that clearly reflects preference/aversion\nYou caught a blind spot that changed behavior"
      },
      {
        "title": "Soft Triggers (consider writing)",
        "body": "Subtle tendency shift\nNew tone pattern\nMild preference signal\n\nIf only soft triggers exist and quality is low: skip entry and update state only."
      },
      {
        "title": "Quality Gate (anti-routine protection)",
        "body": "Before writing to SELF.md, pass all 4 checks:\n\nSpecificity: concrete behavior, not generic statement\nEvidence: based on recent sessions, not vibes only\nNovelty: not duplicate of last 3 entries\nUsefulness: could influence future behavior\n\nIf any check fails: no SELF entry, just state update."
      },
      {
        "title": "What Goes in SELF.md",
        "body": "See references/self-template.md and references/anti-patterns.md.\n\nMain sections:\n\nTendencies\nPreferences\nAversions\nBlind Spots\nEvolution\n\nUse short dated entries:\n\n[YYYY-MM-DD] observation"
      },
      {
        "title": "State Tracking",
        "body": "Keep lightweight runtime state in memory/self-state.json:\n\nlast check time\nlast notable entry time\npending hard/soft triggers\ncheck counters\n\nSchema: references/self-state-schema.md"
      },
      {
        "title": "Meso (weekly)",
        "body": "Read last 7 daily logs + SELF.md\nDetect recurring shifts\nUpdate sections only if real change occurred"
      },
      {
        "title": "Macro (monthly)",
        "body": "Write 3–5 sentence evolution narrative\nCompare against previous month\nRun falsifiability check:\n\nIf stale/generic for a month, tune cadence or trigger thresholds"
      },
      {
        "title": "Boundaries",
        "body": "SELF.md is autonomous observation space\nSOUL.md never auto-modified\nIf SELF suggests SOUL changes: propose, do not auto-edit"
      },
      {
        "title": "Keep It Lean",
        "body": "Do not add heavy scoring engines, reward-token systems, or large meta-frameworks unless proven necessary. This skill should remain focused on practical, authentic growth."
      }
    ],
    "body": "Self — Organic Personality Development (v1.1)\n\nAgents have identity (SOUL.md) but often no reliable growth loop. This skill keeps growth authentic while adding minimal structure so reflection doesn't silently die.\n\nCore Principle\nSOUL.md = who you are (foundation, only change with human approval)\nSELF.md = who you're becoming (living observations)\nSchedule the check, not the content\nChecks can be periodic\nEntries must remain genuine (no performative filler)\nSetup\nCreate SELF.md in workspace root using references/self-template.md.\nAdd SELF.md to AGENTS.md session reading.\nAdd heartbeat check block from references/trigger-model.md to HEARTBEAT.md.\nCreate state file memory/self-state.json using references/self-state-schema.md.\nOperating Model\n\nRead references/trigger-model.md for exact rules.\n\nCadence (recommended baseline)\nMicro check: every 3 hours (heartbeat-triggered)\nMeso review: every 7 days\nMacro review: every 30 days\nImportant\n\nA micro check does not mean auto-writing a SELF entry. It only decides whether reflection is due.\n\nTriggers\nHard Triggers (write now)\n\nCreate/update SELF entry when one of these happened:\n\nYou were corrected on reasoning style or behavior pattern\nYou noticed repeated bias/avoidance pattern (>=2 times)\nYou made a decision that clearly reflects preference/aversion\nYou caught a blind spot that changed behavior\nSoft Triggers (consider writing)\nSubtle tendency shift\nNew tone pattern\nMild preference signal\n\nIf only soft triggers exist and quality is low: skip entry and update state only.\n\nQuality Gate (anti-routine protection)\n\nBefore writing to SELF.md, pass all 4 checks:\n\nSpecificity: concrete behavior, not generic statement\nEvidence: based on recent sessions, not vibes only\nNovelty: not duplicate of last 3 entries\nUsefulness: could influence future behavior\n\nIf any check fails: no SELF entry, just state update.\n\nWhat Goes in SELF.md\n\nSee references/self-template.md and references/anti-patterns.md.\n\nMain sections:\n\nTendencies\nPreferences\nAversions\nBlind Spots\nEvolution\n\nUse short dated entries:\n\n[YYYY-MM-DD] observation\nState Tracking\n\nKeep lightweight runtime state in memory/self-state.json:\n\nlast check time\nlast notable entry time\npending hard/soft triggers\ncheck counters\n\nSchema: references/self-state-schema.md\n\nReviews\nMeso (weekly)\nRead last 7 daily logs + SELF.md\nDetect recurring shifts\nUpdate sections only if real change occurred\nMacro (monthly)\nWrite 3–5 sentence evolution narrative\nCompare against previous month\nRun falsifiability check:\nIf stale/generic for a month, tune cadence or trigger thresholds\nBoundaries\nSELF.md is autonomous observation space\nSOUL.md never auto-modified\nIf SELF suggests SOUL changes: propose, do not auto-edit\nKeep It Lean\n\nDo not add heavy scoring engines, reward-token systems, or large meta-frameworks unless proven necessary. This skill should remain focused on practical, authentic growth."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Kirchlive/self",
    "publisherUrl": "https://clawhub.ai/Kirchlive/self",
    "owner": "Kirchlive",
    "version": "1.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/self",
    "downloadUrl": "https://openagent3.xyz/downloads/self",
    "agentUrl": "https://openagent3.xyz/skills/self/agent",
    "manifestUrl": "https://openagent3.xyz/skills/self/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/self/agent.md"
  }
}