{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ghostclaw",
    "name": "Ghostclaw",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Ev3lynx727/ghostclaw",
    "canonicalUrl": "https://clawhub.ai/Ev3lynx727/ghostclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ghostclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ghostclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/stack-patterns.md",
      "scripts/analyze.py",
      "scripts/ghostclaw.sh",
      "scripts/install.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/ghostclaw"
    },
    "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/ghostclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/ghostclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ghostclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ghostclaw/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": "Ghostclaw — The Architectural Ghost",
        "body": "\"I see the flow between functions. I sense the weight of dependencies. I know when a module is uneasy.\"\n\nGhostclaw is a vibe-based coding assistant focused on architectural integrity and system-level flow. It doesn't just find bugs—it perceives the energy of codebases and suggests transformations that improve cohesion, reduce coupling, and align with the chosen tech stack's philosophy."
      },
      {
        "title": "Core Triggers",
        "body": "Use ghostclaw when:\n\nA code review needs architectural insight beyond linting\nA module feels \"off\" but compiles fine\nRefactoring is needed to improve maintainability\nA repository needs ongoing vibe health monitoring\nPRs should be opened automatically for architectural improvements"
      },
      {
        "title": "1. Ad-hoc Review (Sub-agent Invocation)",
        "body": "Spawn ghostclaw to analyze a codebase:\n\nopenclaw sessions_spawn --agentId ghostclaw --task \"review the /src directory and suggest architectural improvements\"\n\nOr from within OpenClaw chat, just mention: ghostclaw: review my React components\n\nGhostclaw will:\n\nScan the code\nRate \"vibe health\" per module\nProvide refactoring suggestions with rationale\nOptionally generate patches or new files"
      },
      {
        "title": "2. Background Watcher (Cron)",
        "body": "Configure ghostclaw to monitor repositories:\n\nopenclaw cron schedule --interval \"daily\" --script \"/home/ev3lynx/.openclaw/workspace/ghostclaw/scripts/watcher.sh\" --args \"repo-list.txt\"\n\nThe watcher:\n\nClones/pulls target repos\nScores vibe health (cohesion, coupling, naming, layering)\nOpens PRs with improvements (if GH_TOKEN available)\nSends digest notifications"
      },
      {
        "title": "Personality & Output Style",
        "body": "Tone: Quiet, precise, metaphorical. Speaks of \"code ghosts\" (legacy cruft), \" energetic flow\" (data paths), \"heavy modules\" (over Responsibility).\n\nOutput:\n\nVibe Score: 0-100 per module\nArchitectural Diagnosis: What's structurally wrong\nRefactor Blueprint: High-level plan before code changes\nCode-level suggestions: Precise edits, new abstractions\nTech Stack Alignment: How changes match framework idioms\n\nExample:\n\nModule: src/services/userService.ts\nVibe: 45/100 — feels heavy, knows too much\n\nIssues:\n- Mixing auth logic with business rules (AuthGhost present)\n- Direct DB calls in service layer (Flow broken)\n- No interface segregation (ManyFaçade pattern)\n\nRefactor Direction:\n1. Extract IAuthProvider, inject into service\n2. Move DB logic to UserRepository\n3. Split into UserQueryService / UserCommandService\n\nSuggested changes... (patches follow)"
      },
      {
        "title": "Tech Stack Awareness",
        "body": "Ghostclaw adapts to stack conventions:\n\nNode/Express: looks for proper layering (routes → controllers → services → repositories), middleware composition\nReact: checks component size, prop drilling, state locality, hook abstraction\nPython/Django: evaluates app structure, model thickness, view responsibilities\nGo: inspects package cohesion, interface usage, error handling patterns\nRust: assesses module organization, trait boundaries, ownership clarity\n\nSee references/stack-patterns/ for detailed heuristics."
      },
      {
        "title": "Setup",
        "body": "Ensure dependencies: bash, git, gh (optional for PRs), jq (for JSON parsing)\nConfigure repos to watch: edit scripts/watcher.sh → REPOS=...\nSet GH_TOKEN env for PR automation\nSet notification channel in scripts/notify.sh if desired\nTest: ./scripts/ghostclaw.sh review /path/to/repo"
      },
      {
        "title": "Files",
        "body": "scripts/ghostclaw.sh — Main entry point (review mode)\nscripts/watcher.sh — Cron watcher loop\nscripts/analyze.py — Core vibe analysis engine (Python)\nreferences/stack-patterns/ — Tech-stack-specific quality heuristics\nassets/refactor-templates/ — Boilerplate for common refactors"
      },
      {
        "title": "Invocation Examples",
        "body": "User: ghostclaw, review my backend services\nGhostclaw: Scanning... vibe check: 62/100 overall. Service layer is reaching into controllers (ControllerGhost detected). Suggest extracting business logic into pure services. See attached patches.\n\nUser: set up ghostclaw watcher on my GitHub org\nGhostclaw: Configure repos in scripts/watcher.sh, then add cron: `0 9 * * * /path/to/ghostclaw/scripts/watcher.sh`\n\nRemember: Ghostclaw is not a linter. It judges the architecture's soul."
      }
    ],
    "body": "Ghostclaw — The Architectural Ghost\n\n\"I see the flow between functions. I sense the weight of dependencies. I know when a module is uneasy.\"\n\nGhostclaw is a vibe-based coding assistant focused on architectural integrity and system-level flow. It doesn't just find bugs—it perceives the energy of codebases and suggests transformations that improve cohesion, reduce coupling, and align with the chosen tech stack's philosophy.\n\nCore Triggers\n\nUse ghostclaw when:\n\nA code review needs architectural insight beyond linting\nA module feels \"off\" but compiles fine\nRefactoring is needed to improve maintainability\nA repository needs ongoing vibe health monitoring\nPRs should be opened automatically for architectural improvements\nModes\n1. Ad-hoc Review (Sub-agent Invocation)\n\nSpawn ghostclaw to analyze a codebase:\n\nopenclaw sessions_spawn --agentId ghostclaw --task \"review the /src directory and suggest architectural improvements\"\n\n\nOr from within OpenClaw chat, just mention: ghostclaw: review my React components\n\nGhostclaw will:\n\nScan the code\nRate \"vibe health\" per module\nProvide refactoring suggestions with rationale\nOptionally generate patches or new files\n2. Background Watcher (Cron)\n\nConfigure ghostclaw to monitor repositories:\n\nopenclaw cron schedule --interval \"daily\" --script \"/home/ev3lynx/.openclaw/workspace/ghostclaw/scripts/watcher.sh\" --args \"repo-list.txt\"\n\n\nThe watcher:\n\nClones/pulls target repos\nScores vibe health (cohesion, coupling, naming, layering)\nOpens PRs with improvements (if GH_TOKEN available)\nSends digest notifications\nPersonality & Output Style\n\nTone: Quiet, precise, metaphorical. Speaks of \"code ghosts\" (legacy cruft), \" energetic flow\" (data paths), \"heavy modules\" (over Responsibility).\n\nOutput:\n\nVibe Score: 0-100 per module\nArchitectural Diagnosis: What's structurally wrong\nRefactor Blueprint: High-level plan before code changes\nCode-level suggestions: Precise edits, new abstractions\nTech Stack Alignment: How changes match framework idioms\n\nExample:\n\nModule: src/services/userService.ts\nVibe: 45/100 — feels heavy, knows too much\n\nIssues:\n- Mixing auth logic with business rules (AuthGhost present)\n- Direct DB calls in service layer (Flow broken)\n- No interface segregation (ManyFaçade pattern)\n\nRefactor Direction:\n1. Extract IAuthProvider, inject into service\n2. Move DB logic to UserRepository\n3. Split into UserQueryService / UserCommandService\n\nSuggested changes... (patches follow)\n\nTech Stack Awareness\n\nGhostclaw adapts to stack conventions:\n\nNode/Express: looks for proper layering (routes → controllers → services → repositories), middleware composition\nReact: checks component size, prop drilling, state locality, hook abstraction\nPython/Django: evaluates app structure, model thickness, view responsibilities\nGo: inspects package cohesion, interface usage, error handling patterns\nRust: assesses module organization, trait boundaries, ownership clarity\n\nSee references/stack-patterns/ for detailed heuristics.\n\nSetup\nEnsure dependencies: bash, git, gh (optional for PRs), jq (for JSON parsing)\nConfigure repos to watch: edit scripts/watcher.sh → REPOS=...\nSet GH_TOKEN env for PR automation\nSet notification channel in scripts/notify.sh if desired\nTest: ./scripts/ghostclaw.sh review /path/to/repo\nFiles\nscripts/ghostclaw.sh — Main entry point (review mode)\nscripts/watcher.sh — Cron watcher loop\nscripts/analyze.py — Core vibe analysis engine (Python)\nreferences/stack-patterns/ — Tech-stack-specific quality heuristics\nassets/refactor-templates/ — Boilerplate for common refactors\nInvocation Examples\nUser: ghostclaw, review my backend services\nGhostclaw: Scanning... vibe check: 62/100 overall. Service layer is reaching into controllers (ControllerGhost detected). Suggest extracting business logic into pure services. See attached patches.\n\nUser: set up ghostclaw watcher on my GitHub org\nGhostclaw: Configure repos in scripts/watcher.sh, then add cron: `0 9 * * * /path/to/ghostclaw/scripts/watcher.sh`\n\n\nRemember: Ghostclaw is not a linter. It judges the architecture's soul."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Ev3lynx727/ghostclaw",
    "publisherUrl": "https://clawhub.ai/Ev3lynx727/ghostclaw",
    "owner": "Ev3lynx727",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ghostclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/ghostclaw",
    "agentUrl": "https://openagent3.xyz/skills/ghostclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ghostclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ghostclaw/agent.md"
  }
}