{
  "schemaVersion": "1.0",
  "item": {
    "slug": "flowclaw",
    "name": "FlowClaw",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/windseeker1111/flowclaw",
    "canonicalUrl": "https://clawhub.ai/windseeker1111/flowclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "manual_only",
    "downloadUrl": "/downloads/flowclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=flowclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "config/flowclaw-state.json",
      "scripts/flowclaw.sh",
      "scripts/provider-usage.sh",
      "scripts/save-account.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Open the source page and confirm the package flow manually.",
      "Review SKILL.md if you can obtain the files.",
      "Treat this source as manual setup until the download is verified."
    ],
    "agentAssist": {
      "summary": "Use the source page and any available docs to guide the install because the item currently does not return a direct package file.",
      "steps": [
        "Open the source page via Open source listing.",
        "If you can obtain the package, extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the source page and extracted files."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks."
        },
        {
          "label": "Upgrade existing",
          "body": "I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "flowclaw",
      "status": "source_issue",
      "reason": "not_found",
      "recommendedAction": "review_source",
      "checkedAt": "2026-05-01T13:36:29.718Z",
      "expiresAt": "2026-05-02T13:36:29.718Z",
      "httpStatus": 404,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=flowclaw",
      "contentType": "text/plain",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=flowclaw",
        "contentDisposition": null,
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "flowclaw"
      },
      "scope": "item",
      "summary": "Known item issue.",
      "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.",
      "primaryActionLabel": "Open source listing",
      "primaryActionHref": "https://clawhub.ai/windseeker1111/flowclaw"
    },
    "validation": {
      "installChecklist": [
        "Open the source listing and confirm there is a real package or setup artifact available.",
        "Review SKILL.md before asking your agent to continue.",
        "Treat this source as manual setup until the upstream download flow is fixed."
      ],
      "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/flowclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/flowclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/flowclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/flowclaw/agent.md"
  },
  "agentAssist": {
    "summary": "Use the source page and any available docs to guide the install because the item currently does not return a direct package file.",
    "steps": [
      "Open the source page via Open source listing.",
      "If you can obtain the package, extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the source page and extracted files."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks."
      },
      {
        "label": "Upgrade existing",
        "body": "I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "FlowClaw — LLM Usage Monitor & Load Balancer",
        "body": "Track usage. Balance routing. Never waste a credit.\n\nUnified dashboard + auto-routing for all your LLM subscriptions. Uses Earliest Deadline First scheduling — accounts resetting soonest are prioritized so unused credits aren't wasted."
      },
      {
        "title": "Supported Providers",
        "body": "ProviderAuthData SourceAnthropic Claude MaxOAuth (unlimited accounts)api.anthropic.com/api/oauth/usageGoogle Gemini CLIOAuth via OpenClawcloudcode-pa.googleapis.comGoogle Antigravitycodexbarcodexbar usage APIOpenAI CodexOAuth via OpenClawchatgpt.com/backend-api/wham/usageGitHub CopilotOAuth via OpenClawapi.github.com/copilot_internal/userOllamaLocal (auto-detected)localhost:11434/api/tags"
      },
      {
        "title": "Commands",
        "body": "# 📊 Usage Monitoring\nflowclaw status [--fresh] [--json]     # Full provider dashboard\nflowclaw monitor [--json] [--cached]   # Clean usage report (no scoring)\n\n# 🧠 Load Balancing\nflowclaw score [--json]                # Scored ranking of all accounts\nflowclaw optimize [--dry-run]          # Reorder OpenClaw model priority\nflowclaw auto                          # Optimize silently (for cron jobs)\n\n# 🛠 Utilities\nflowclaw test                          # Run scoring engine unit tests\nflowclaw history [N]                   # Routing decision history"
      },
      {
        "title": "Anthropic (Claude Max) — unlimited accounts",
        "body": "claude login\nbash {baseDir}/scripts/save-account.sh\n# Repeat for each account"
      },
      {
        "title": "Google Gemini CLI",
        "body": "openclaw models auth login --provider google-gemini-cli"
      },
      {
        "title": "Google Antigravity",
        "body": "openclaw models auth login --provider google-antigravity\nbrew install --cask steipete/tap/codexbar   # Required for usage metrics"
      },
      {
        "title": "OpenAI Codex",
        "body": "openclaw models auth login --provider openai-codex"
      },
      {
        "title": "GitHub Copilot",
        "body": "openclaw models auth login-github-copilot"
      },
      {
        "title": "Ollama",
        "body": "brew install ollama && ollama pull qwen3:235b\n# Auto-detected — no config needed"
      },
      {
        "title": "Cron Automation",
        "body": "# Optimize routing every 30 minutes\n*/30 * * * * bash ~/clawd/skills/flowclaw/scripts/flowclaw.sh auto"
      },
      {
        "title": "Scoring Algorithm",
        "body": "score = urgency(0.30) + availability(0.25) + proximity(0.15) + weekly_headroom(0.20) + tier(0.10)\n\nFactorFormulaMeasuresUrgencyremaining / hours_to_resetCredits wasting per hourAvailability√(remaining)Dampened capacityProximity1 - (hours / window)Deadline pressureWeekly headroom(100 - weekly%) / 1007-day capacity reserveTier bonusFree=+0.8, Sub=0, Local=-0.3Cost preference\n\nPerishable inventory: Both 5h session and 7d weekly windows expire. When ≤6h to weekly reset, penalty is removed — burn remaining credits. Family-aware: Only swaps within same capability class (Opus↔Opus, not Opus↔Gemini)."
      }
    ],
    "body": "FlowClaw — LLM Usage Monitor & Load Balancer\n\nTrack usage. Balance routing. Never waste a credit.\n\nUnified dashboard + auto-routing for all your LLM subscriptions. Uses Earliest Deadline First scheduling — accounts resetting soonest are prioritized so unused credits aren't wasted.\n\nSupported Providers\nProvider\tAuth\tData Source\nAnthropic Claude Max\tOAuth (unlimited accounts)\tapi.anthropic.com/api/oauth/usage\nGoogle Gemini CLI\tOAuth via OpenClaw\tcloudcode-pa.googleapis.com\nGoogle Antigravity\tcodexbar\tcodexbar usage API\nOpenAI Codex\tOAuth via OpenClaw\tchatgpt.com/backend-api/wham/usage\nGitHub Copilot\tOAuth via OpenClaw\tapi.github.com/copilot_internal/user\nOllama\tLocal (auto-detected)\tlocalhost:11434/api/tags\nCommands\n# 📊 Usage Monitoring\nflowclaw status [--fresh] [--json]     # Full provider dashboard\nflowclaw monitor [--json] [--cached]   # Clean usage report (no scoring)\n\n# 🧠 Load Balancing\nflowclaw score [--json]                # Scored ranking of all accounts\nflowclaw optimize [--dry-run]          # Reorder OpenClaw model priority\nflowclaw auto                          # Optimize silently (for cron jobs)\n\n# 🛠 Utilities\nflowclaw test                          # Run scoring engine unit tests\nflowclaw history [N]                   # Routing decision history\n\nSetup\nAnthropic (Claude Max) — unlimited accounts\nclaude login\nbash {baseDir}/scripts/save-account.sh\n# Repeat for each account\n\nGoogle Gemini CLI\nopenclaw models auth login --provider google-gemini-cli\n\nGoogle Antigravity\nopenclaw models auth login --provider google-antigravity\nbrew install --cask steipete/tap/codexbar   # Required for usage metrics\n\nOpenAI Codex\nopenclaw models auth login --provider openai-codex\n\nGitHub Copilot\nopenclaw models auth login-github-copilot\n\nOllama\nbrew install ollama && ollama pull qwen3:235b\n# Auto-detected — no config needed\n\nCron Automation\n# Optimize routing every 30 minutes\n*/30 * * * * bash ~/clawd/skills/flowclaw/scripts/flowclaw.sh auto\n\nScoring Algorithm\nscore = urgency(0.30) + availability(0.25) + proximity(0.15) + weekly_headroom(0.20) + tier(0.10)\n\nFactor\tFormula\tMeasures\nUrgency\tremaining / hours_to_reset\tCredits wasting per hour\nAvailability\t√(remaining)\tDampened capacity\nProximity\t1 - (hours / window)\tDeadline pressure\nWeekly headroom\t(100 - weekly%) / 100\t7-day capacity reserve\nTier bonus\tFree=+0.8, Sub=0, Local=-0.3\tCost preference\n\nPerishable inventory: Both 5h session and 7d weekly windows expire. When ≤6h to weekly reset, penalty is removed — burn remaining credits. Family-aware: Only swaps within same capability class (Opus↔Opus, not Opus↔Gemini)."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/windseeker1111/flowclaw",
    "publisherUrl": "https://clawhub.ai/windseeker1111/flowclaw",
    "owner": "windseeker1111",
    "version": "1.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/flowclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/flowclaw",
    "agentUrl": "https://openagent3.xyz/skills/flowclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/flowclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/flowclaw/agent.md"
  }
}