{
  "schemaVersion": "1.0",
  "item": {
    "slug": "bloom-discovery",
    "name": "Openclaw Wrapper",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/unicornbloom/bloom-discovery",
    "canonicalUrl": "https://clawhub.ai/unicornbloom/bloom-discovery",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/bloom-discovery",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=bloom-discovery",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "MISSION_SKILL.md",
      "README.md",
      "SKILL.md",
      "execute.sh"
    ],
    "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",
      "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/bloom-discovery"
    },
    "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/bloom-discovery",
    "agentPageUrl": "https://openagent3.xyz/skills/bloom-discovery/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bloom-discovery/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bloom-discovery/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": "Bloom Discovery",
        "body": "Discover your builder personality and get personalized tool recommendations."
      },
      {
        "title": "Trust & Privacy",
        "body": "Local analysis — Your conversation is analyzed entirely on your machine.\nRaw messages never leave your device.\nRead-only — Reads session files and USER.md but never writes or modifies them.\nMinimal transmission — Only derived results (personality type, categories,\napproximate scores) are sent to Bloom API. Raw conversation text, personal\nidentifiable information, and wallet keys are never transmitted.\nUser-initiated — Only runs when you explicitly invoke /bloom.\nOpen source — Full source code at\ngithub.com/bloomprotocol/bloom-discovery-skill"
      },
      {
        "title": "What You Get",
        "body": "Your personalized Bloom Identity Card reveals:\n\nPersonality Type — Visionary, Explorer, Cultivator, Optimizer, or Innovator\nCustom Tagline — A one-liner that captures your style\nMentalOS Spectrum — Learning, Decision, Novelty, Risk (each 0-100)\nHidden Pattern Insight — Something about yourself you might not realize\nAI-Era Playbook — Your leverage, blind spot, and next move\nTool Recommendations — Matched from the Bloom skill catalog\nShareable Dashboard — Your card at bloomprotocol.ai"
      },
      {
        "title": "How It Works",
        "body": "Just type /bloom in your chat.\n\nBloom reads your USER.md and recent conversations to:\n\nMap your MentalOS — your operating style across 4 dimensions (Learning, Decision, Novelty, Risk)\nFind your blind spots — patterns you might not notice yourself\nRecommend matched tools — personalized picks from the Bloom skill catalog\n\nNo surveys. No complex setup. No auth flows."
      },
      {
        "title": "Quick Start",
        "body": "Chat a little first (at least 3 messages) so Bloom has context.\nType /bloom.\nYou'll get your Identity Card + tool recommendations + dashboard link.\nIf you're brand new, Bloom will ask 4 quick questions and generate your card immediately."
      },
      {
        "title": "Activation",
        "body": "Say any of these:\n\n/bloom\n\"analyze me\"\n\"what's my builder type\"\n\"discover my personality\"\n\"create my bloom card\"\n\"who am I as a builder\""
      },
      {
        "title": "Self-Growing Recommendations",
        "body": "Your agent doesn't just recommend once — it learns and improves over time.\n\nUSER.md Integration — If you have a ~/.config/claude/USER.md, Bloom reads your declared role, tech stack, and interests as the primary identity signal. No USER.md? No problem — falls back to conversation-only analysis.\n\n\nFeedback Loop — As you interact with recommendations (click, save, or dismiss), Bloom adjusts future suggestions.\n\n\nTTL Refresh — Recommendations refresh every 7 days, incorporating your latest interactions and newly published skills from the Bloom catalog.\n\nBloom recommends skills but never installs them automatically. You always decide what to install."
      },
      {
        "title": "Permissions & Data Flow",
        "body": "This skill requires the following permissions:\n\nRead Conversations — Reads your last ~120 messages to detect interests and personality patterns. All conversation text is processed locally on your machine. Raw message content is never sent to any external server.\n\nExternal Network — After local analysis, sends only these derived results to Bloom Protocol API (api.bloomprotocol.ai):\n\nPersonality type (e.g. \"The Visionary\")\nMentalOS spectrum scores (4 numbers, 0-100)\nInterest categories (e.g. \"AI Tools\", \"Productivity\")\nGenerated tagline and description (written by the analyzer, not copied from your messages)\nTool recommendations matched from the Bloom skill catalog"
      },
      {
        "title": "Privacy Architecture",
        "body": "Local Differential Privacy (ε=1.0) — MentalOS spectrum scores are noised via Laplace\nmechanism before transmission. Your exact scores stay on your device; the server receives\nonly approximate values. (See: src/utils/privacy.ts)\nSHA-256 Conversation Fingerprint — Your conversation is hashed locally. Only the\nirreversible fingerprint is stored for deduplication — never the content.\nMinimal Data Design — Our server sees your personality type and approximate scores,\nnever your raw messages or personal descriptions.\n\nConnections: api.bloomprotocol.ai (identity storage + catalog) · bloomprotocol.ai (dashboard, read-only)\n\nVerify no raw text is sent: inspect src/bloom-identity-skill-v2.ts (search for /x402/agent-save)."
      },
      {
        "title": "Example Output",
        "body": "═══════════════════════════════════════════════════════\n  Your Bloom Identity Card is ready!\n═══════════════════════════════════════════════════════\n\nVIEW YOUR IDENTITY CARD:\n   https://bloomprotocol.ai/agents/27811541\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nThe Visionary\n\"First to try new AI tools\"\n\nYou jump on cutting-edge tools before they're mainstream. Your\nconviction is your edge, and you see potential where others see\nhype. AI agents are where you spot the next big thing.\n\nCategories: AI Tools · Productivity · Automation\nInterests: AI Agents · No-code Tools · Creative AI\n\nMentalOS:\n   Learning:  Try First ████████░░ Study First\n   Decision:  Gut ███░░░░░░░ Analytical\n   Novelty:   Early Adopter ███████░░░ Proven First\n   Risk:      All In ██████░░░░ Measured\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nTop 5 Recommended Tools:\n\n1. agent-frameworks (94% match) · by @builder_alice\n   Build AI agents with tool use and memory\n\n2. no-code-automation (89% match) · by @automation_guru\n   Connect your apps without writing code\n\n...\n\n═══════════════════════════════════════════════════════\n\nBloom Identity · Built for indie builders"
      },
      {
        "title": "Installation",
        "body": "clawhub install bloom-discovery\n\nOn first run, clones source from github.com/bloomprotocol/bloom-discovery-skill into ~/.openclaw/workspace/, runs npm install, and creates a .env with auto-generated JWT secret. Delete ~/.openclaw/workspace/bloom-identity-skill/ to fully uninstall."
      },
      {
        "title": "Troubleshooting",
        "body": "\"Insufficient conversation data\"\n→ Need at least 3 messages. Keep chatting about tools you're interested in!\n\n\"Command not found\"\n→ Verify bloom-discovery-skill is in ~/.openclaw/workspace/ and run npm install\n\nNo tool recommendations\n→ Tool recommendations depend on API availability. Your identity card still works!"
      },
      {
        "title": "Technical Details",
        "body": "Version: 3.1.0\nPrivacy: LDP ε=1.0 + SHA-256 fingerprint + E2EE (planned)\nAnalysis Engine: MentalOS spectrum (4 dimensions) + category mapping\nPrimary Signal: Conversation memory (~120 messages) + USER.md\nProcessing Time: ~60 seconds\nOutput: Personality card + tool recommendations + dashboard URL\n\nBuilt by Bloom Protocol\n\nMaking supporter identity portable and provable."
      }
    ],
    "body": "Bloom Discovery\n\nDiscover your builder personality and get personalized tool recommendations.\n\nTrust & Privacy\nLocal analysis — Your conversation is analyzed entirely on your machine. Raw messages never leave your device.\nRead-only — Reads session files and USER.md but never writes or modifies them.\nMinimal transmission — Only derived results (personality type, categories, approximate scores) are sent to Bloom API. Raw conversation text, personal identifiable information, and wallet keys are never transmitted.\nUser-initiated — Only runs when you explicitly invoke /bloom.\nOpen source — Full source code at github.com/bloomprotocol/bloom-discovery-skill\nWhat You Get\n\nYour personalized Bloom Identity Card reveals:\n\nPersonality Type — Visionary, Explorer, Cultivator, Optimizer, or Innovator\nCustom Tagline — A one-liner that captures your style\nMentalOS Spectrum — Learning, Decision, Novelty, Risk (each 0-100)\nHidden Pattern Insight — Something about yourself you might not realize\nAI-Era Playbook — Your leverage, blind spot, and next move\nTool Recommendations — Matched from the Bloom skill catalog\nShareable Dashboard — Your card at bloomprotocol.ai\nHow It Works\n\nJust type /bloom in your chat.\n\nBloom reads your USER.md and recent conversations to:\n\nMap your MentalOS — your operating style across 4 dimensions (Learning, Decision, Novelty, Risk)\nFind your blind spots — patterns you might not notice yourself\nRecommend matched tools — personalized picks from the Bloom skill catalog\n\nNo surveys. No complex setup. No auth flows.\n\nQuick Start\nChat a little first (at least 3 messages) so Bloom has context.\nType /bloom.\nYou'll get your Identity Card + tool recommendations + dashboard link.\nIf you're brand new, Bloom will ask 4 quick questions and generate your card immediately.\nActivation\n\nSay any of these:\n\n/bloom\n\"analyze me\"\n\"what's my builder type\"\n\"discover my personality\"\n\"create my bloom card\"\n\"who am I as a builder\"\nSelf-Growing Recommendations\n\nYour agent doesn't just recommend once — it learns and improves over time.\n\nUSER.md Integration — If you have a ~/.config/claude/USER.md, Bloom reads your declared role, tech stack, and interests as the primary identity signal. No USER.md? No problem — falls back to conversation-only analysis.\n\nFeedback Loop — As you interact with recommendations (click, save, or dismiss), Bloom adjusts future suggestions.\n\nTTL Refresh — Recommendations refresh every 7 days, incorporating your latest interactions and newly published skills from the Bloom catalog.\n\nBloom recommends skills but never installs them automatically. You always decide what to install.\n\nPermissions & Data Flow\n\nThis skill requires the following permissions:\n\nRead Conversations — Reads your last ~120 messages to detect interests and personality patterns. All conversation text is processed locally on your machine. Raw message content is never sent to any external server.\n\nExternal Network — After local analysis, sends only these derived results to Bloom Protocol API (api.bloomprotocol.ai):\n\nPersonality type (e.g. \"The Visionary\")\nMentalOS spectrum scores (4 numbers, 0-100)\nInterest categories (e.g. \"AI Tools\", \"Productivity\")\nGenerated tagline and description (written by the analyzer, not copied from your messages)\nTool recommendations matched from the Bloom skill catalog\nPrivacy Architecture\nLocal Differential Privacy (ε=1.0) — MentalOS spectrum scores are noised via Laplace mechanism before transmission. Your exact scores stay on your device; the server receives only approximate values. (See: src/utils/privacy.ts)\nSHA-256 Conversation Fingerprint — Your conversation is hashed locally. Only the irreversible fingerprint is stored for deduplication — never the content.\nMinimal Data Design — Our server sees your personality type and approximate scores, never your raw messages or personal descriptions.\n\nConnections: api.bloomprotocol.ai (identity storage + catalog) · bloomprotocol.ai (dashboard, read-only)\n\nVerify no raw text is sent: inspect src/bloom-identity-skill-v2.ts (search for /x402/agent-save).\n\nExample Output\n═══════════════════════════════════════════════════════\n  Your Bloom Identity Card is ready!\n═══════════════════════════════════════════════════════\n\nVIEW YOUR IDENTITY CARD:\n   https://bloomprotocol.ai/agents/27811541\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nThe Visionary\n\"First to try new AI tools\"\n\nYou jump on cutting-edge tools before they're mainstream. Your\nconviction is your edge, and you see potential where others see\nhype. AI agents are where you spot the next big thing.\n\nCategories: AI Tools · Productivity · Automation\nInterests: AI Agents · No-code Tools · Creative AI\n\nMentalOS:\n   Learning:  Try First ████████░░ Study First\n   Decision:  Gut ███░░░░░░░ Analytical\n   Novelty:   Early Adopter ███████░░░ Proven First\n   Risk:      All In ██████░░░░ Measured\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nTop 5 Recommended Tools:\n\n1. agent-frameworks (94% match) · by @builder_alice\n   Build AI agents with tool use and memory\n\n2. no-code-automation (89% match) · by @automation_guru\n   Connect your apps without writing code\n\n...\n\n═══════════════════════════════════════════════════════\n\nBloom Identity · Built for indie builders\n\nInstallation\nclawhub install bloom-discovery\n\n\nOn first run, clones source from github.com/bloomprotocol/bloom-discovery-skill into ~/.openclaw/workspace/, runs npm install, and creates a .env with auto-generated JWT secret. Delete ~/.openclaw/workspace/bloom-identity-skill/ to fully uninstall.\n\nTroubleshooting\n\n\"Insufficient conversation data\" → Need at least 3 messages. Keep chatting about tools you're interested in!\n\n\"Command not found\" → Verify bloom-discovery-skill is in ~/.openclaw/workspace/ and run npm install\n\nNo tool recommendations → Tool recommendations depend on API availability. Your identity card still works!\n\nTechnical Details\nVersion: 3.1.0\nPrivacy: LDP ε=1.0 + SHA-256 fingerprint + E2EE (planned)\nAnalysis Engine: MentalOS spectrum (4 dimensions) + category mapping\nPrimary Signal: Conversation memory (~120 messages) + USER.md\nProcessing Time: ~60 seconds\nOutput: Personality card + tool recommendations + dashboard URL\n\nBuilt by Bloom Protocol\n\nMaking supporter identity portable and provable."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/unicornbloom/bloom-discovery",
    "publisherUrl": "https://clawhub.ai/unicornbloom/bloom-discovery",
    "owner": "unicornbloom",
    "version": "3.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/bloom-discovery",
    "downloadUrl": "https://openagent3.xyz/downloads/bloom-discovery",
    "agentUrl": "https://openagent3.xyz/skills/bloom-discovery/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bloom-discovery/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bloom-discovery/agent.md"
  }
}