{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vibe-check",
    "name": "vibe-check",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/tkuehnl/vibe-check",
    "canonicalUrl": "https://clawhub.ai/tkuehnl/vibe-check",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/vibe-check",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vibe-check",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "README.md",
      "SECURITY.md",
      "SKILL.md",
      "TESTING.md",
      "scripts/analyze.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/vibe-check"
    },
    "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/vibe-check",
    "agentPageUrl": "https://openagent3.xyz/skills/vibe-check/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vibe-check/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vibe-check/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": "🎭 Vibe Check",
        "body": "Audit code for \"vibe coding\" — AI-generated code accepted without proper human review. Get a scored report card with specific findings and fix suggestions."
      },
      {
        "title": "Trigger",
        "body": "Activate when the user mentions any of:\n\n\"vibe check\"\n\"vibe-check\"\n\"audit code\"\n\"code quality\"\n\"vibe score\"\n\"check my code\"\n\"review this code for vibe coding\"\n\"code review\"\n\"vibe audit\""
      },
      {
        "title": "1. Determine the Target",
        "body": "Ask the user what code to analyze. Accepted inputs:\n\nSingle file: app.py, src/utils.ts\nDirectory: src/, ., my-project/\nGit diff: last N commits, staged changes, or branch comparison"
      },
      {
        "title": "2. Run the Analysis",
        "body": "# Single file or directory\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" TARGET\n\n# With fix suggestions\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix TARGET\n\n# Git diff (last 3 commits)\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --diff HEAD~3\n\n# Staged changes with fixes\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --staged --fix\n\n# Save to file\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix --output report.md TARGET"
      },
      {
        "title": "3. Present the Report",
        "body": "The output is a Markdown report. Present it directly — it's designed to be screenshot-worthy."
      },
      {
        "title": "Discord v2 Delivery Mode (OpenClaw v2026.2.14+)",
        "body": "When the conversation is happening in a Discord channel:\n\nSend a compact summary first (grade, score, file count, top 3 findings), then ask if the user wants the full report.\nKeep the first message under ~1200 characters and avoid wide Markdown tables in the first response.\nIf Discord components are available, include quick actions:\n\nShow Top Findings\nShow Fix Suggestions\nRun Diff Mode\n\n\nIf components are not available, provide the same follow-ups as a numbered list.\nPrefer short follow-up chunks (<=15 lines per message) when sending the full report."
      },
      {
        "title": "Quick Reference",
        "body": "CommandDescriptionvibe-check FILEAnalyze a single filevibe-check DIRScan directory recursivelyvibe-check --diffCheck last commit's changesvibe-check --diff HEAD~5Check last 5 commitsvibe-check --stagedCheck staged changesvibe-check --fix DIRInclude fix suggestionsvibe-check --output report.md DIRSave report to file"
      },
      {
        "title": "Sin Categories (what it checks)",
        "body": "CategoryWeightWhat It CatchesError Handling20%Missing try/catch, bare exceptions, no edge casesInput Validation15%No type checks, no bounds checks, trusting all inputDuplication15%Copy-pasted logic, DRY violationsDead Code10%Unused imports, commented-out blocks, unreachable codeMagic Values10%Hardcoded strings/numbers/URLs without constantsTest Coverage10%No test files, no test patterns, no assertionsNaming Quality10%Vague names (data, result, temp, x), misleading namesSecurity10%eval(), exec(), hardcoded secrets, SQL injection"
      },
      {
        "title": "Scoring",
        "body": "A (90-100): Pristine code, minimal issues\nB (80-89): Clean code with minor issues\nC (70-79): Decent but lazy patterns crept in\nD (60-69): Needs human attention\nF (<60): Heavy vibe coding detected"
      },
      {
        "title": "Notes for the Agent",
        "body": "The report is the star. Present it in full — it's designed to look great.\nAfter presenting, offer to run --fix mode if they didn't already.\nSuggest the README badge: ![Vibe Score](https://img.shields.io/badge/vibe--score-XX%2F100-COLOR)\nFor large codebases, suggest focusing on specific directories or using --diff mode.\nIf no LLM API key is set, the tool falls back to heuristic analysis (less accurate but still useful).\nSupported languages (v1): Python, TypeScript, JavaScript only."
      },
      {
        "title": "References",
        "body": "scripts/vibe-check.sh — Main entry point\nscripts/analyze.sh — LLM code analysis engine (with heuristic fallback)\nscripts/git-diff.sh — Git diff file extractor\nscripts/report.sh — Markdown report generator\nscripts/common.sh — Shared utilities and constants"
      },
      {
        "title": "Example 1: Audit a Directory",
        "body": "User: \"Vibe check my src directory\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" src/\n\nOutput: Full scorecard with per-file breakdown, category scores, and top findings."
      },
      {
        "title": "Example 2: Check with Fixes",
        "body": "User: \"Review this code for vibe coding and suggest fixes\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix src/\n\nOutput: Scorecard + unified diff patches for each finding."
      },
      {
        "title": "Example 3: Git Diff Mode",
        "body": "User: \"Check the code quality of my last 3 commits\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --diff HEAD~3\n\nOutput: Scorecard focused only on recently changed files."
      }
    ],
    "body": "🎭 Vibe Check\n\nAudit code for \"vibe coding\" — AI-generated code accepted without proper human review. Get a scored report card with specific findings and fix suggestions.\n\nTrigger\n\nActivate when the user mentions any of:\n\n\"vibe check\"\n\"vibe-check\"\n\"audit code\"\n\"code quality\"\n\"vibe score\"\n\"check my code\"\n\"review this code for vibe coding\"\n\"code review\"\n\"vibe audit\"\nInstructions\n1. Determine the Target\n\nAsk the user what code to analyze. Accepted inputs:\n\nSingle file: app.py, src/utils.ts\nDirectory: src/, ., my-project/\nGit diff: last N commits, staged changes, or branch comparison\n2. Run the Analysis\n# Single file or directory\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" TARGET\n\n# With fix suggestions\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix TARGET\n\n# Git diff (last 3 commits)\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --diff HEAD~3\n\n# Staged changes with fixes\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --staged --fix\n\n# Save to file\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix --output report.md TARGET\n\n3. Present the Report\n\nThe output is a Markdown report. Present it directly — it's designed to be screenshot-worthy.\n\nDiscord v2 Delivery Mode (OpenClaw v2026.2.14+)\n\nWhen the conversation is happening in a Discord channel:\n\nSend a compact summary first (grade, score, file count, top 3 findings), then ask if the user wants the full report.\nKeep the first message under ~1200 characters and avoid wide Markdown tables in the first response.\nIf Discord components are available, include quick actions:\nShow Top Findings\nShow Fix Suggestions\nRun Diff Mode\nIf components are not available, provide the same follow-ups as a numbered list.\nPrefer short follow-up chunks (<=15 lines per message) when sending the full report.\nQuick Reference\nCommand\tDescription\nvibe-check FILE\tAnalyze a single file\nvibe-check DIR\tScan directory recursively\nvibe-check --diff\tCheck last commit's changes\nvibe-check --diff HEAD~5\tCheck last 5 commits\nvibe-check --staged\tCheck staged changes\nvibe-check --fix DIR\tInclude fix suggestions\nvibe-check --output report.md DIR\tSave report to file\nSin Categories (what it checks)\nCategory\tWeight\tWhat It Catches\nError Handling\t20%\tMissing try/catch, bare exceptions, no edge cases\nInput Validation\t15%\tNo type checks, no bounds checks, trusting all input\nDuplication\t15%\tCopy-pasted logic, DRY violations\nDead Code\t10%\tUnused imports, commented-out blocks, unreachable code\nMagic Values\t10%\tHardcoded strings/numbers/URLs without constants\nTest Coverage\t10%\tNo test files, no test patterns, no assertions\nNaming Quality\t10%\tVague names (data, result, temp, x), misleading names\nSecurity\t10%\teval(), exec(), hardcoded secrets, SQL injection\nScoring\nA (90-100): Pristine code, minimal issues\nB (80-89): Clean code with minor issues\nC (70-79): Decent but lazy patterns crept in\nD (60-69): Needs human attention\nF (<60): Heavy vibe coding detected\nNotes for the Agent\nThe report is the star. Present it in full — it's designed to look great.\nAfter presenting, offer to run --fix mode if they didn't already.\nSuggest the README badge: ![Vibe Score](https://img.shields.io/badge/vibe--score-XX%2F100-COLOR)\nFor large codebases, suggest focusing on specific directories or using --diff mode.\nIf no LLM API key is set, the tool falls back to heuristic analysis (less accurate but still useful).\nSupported languages (v1): Python, TypeScript, JavaScript only.\nReferences\nscripts/vibe-check.sh — Main entry point\nscripts/analyze.sh — LLM code analysis engine (with heuristic fallback)\nscripts/git-diff.sh — Git diff file extractor\nscripts/report.sh — Markdown report generator\nscripts/common.sh — Shared utilities and constants\nExamples\nExample 1: Audit a Directory\n\nUser: \"Vibe check my src directory\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" src/\n\n\nOutput: Full scorecard with per-file breakdown, category scores, and top findings.\n\nExample 2: Check with Fixes\n\nUser: \"Review this code for vibe coding and suggest fixes\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --fix src/\n\n\nOutput: Scorecard + unified diff patches for each finding.\n\nExample 3: Git Diff Mode\n\nUser: \"Check the code quality of my last 3 commits\"\n\nAgent runs:\n\nbash \"$SKILL_DIR/scripts/vibe-check.sh\" --diff HEAD~3\n\n\nOutput: Scorecard focused only on recently changed files."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/tkuehnl/vibe-check",
    "publisherUrl": "https://clawhub.ai/tkuehnl/vibe-check",
    "owner": "tkuehnl",
    "version": "0.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vibe-check",
    "downloadUrl": "https://openagent3.xyz/downloads/vibe-check",
    "agentUrl": "https://openagent3.xyz/skills/vibe-check/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vibe-check/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vibe-check/agent.md"
  }
}