Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/ad-account-auditor

ad-account-auditor

Verified

Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分

FileKindSize
SKILL.mdskill md8.0 KB
references/auditor-runtime.mdmarkdown7.4 KB
skill-report.jsonconfig42.2 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-26T09:51:39.879Z",
    "slug": "aaron-he-zhu-ad-account-auditor",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/ad/activate/ad-account-auditor",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "cf9751434ea8fcd0b24d58a14c19ef4162cef2962b4e1ed846b0d86c0ec661b0",
    "tree_hash": "8710236724f0a73cb218ca972a3f62325af231dac88afc2a941a56e0667cd5c9",
    "provenance": {
      "model_effective": "claude",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-26T09:51:40.043212Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-26T09:51:40.073225Z ERROR codex_models_manage…"
        },
        {
          "agent": "claude",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    },
    "upstream_version_raw": "19.0.0",
    "upstream_version_normalized": "19.0.0",
    "upstream_version_source": "metadata.version",
    "upstream_version_status": "not_bumped",
    "upstream_commit_sha": "49c026d9d90630ed187fbce5c7f7f84ff4710d85"
  },
  "skill": {
    "name": "ad-account-auditor",
    "description": "Audit a paid advertising account with a 20-item ROAS framework before launch, budget growth, or major strategy changes.",
    "summary": "Evaluate measurement integrity, incrementality, safety, and operating quality using exported account data.",
    "icon": "📦",
    "version": "19.0.0",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "tags": [
      "paid advertising",
      "ROAS audit",
      "measurement integrity",
      "incrementality",
      "marketing compliance"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem"
    ],
    "category": "security"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All 39 static findings are false positives caused by Markdown code formatting, static documentation links, metadata URLs, and fixed reference paths. The reviewed instructions limit the skill to assessment, require explicit authorization before persistence, and prohibit ad-account mutations without separate approval. No prompt injection, credential collection, data exfiltration, or arbitrary command execution evidence was found.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 63,
            "line_end": 66
          },
          {
            "file": "SKILL.md",
            "line_start": 66,
            "line_end": 67
          },
          {
            "file": "SKILL.md",
            "line_start": 67,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 94
          },
          {
            "file": "SKILL.md",
            "line_start": 94,
            "line_end": 94
          },
          {
            "file": "SKILL.md",
            "line_start": 108,
            "line_end": 108
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 15,
            "line_end": 15
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 112
          },
          {
            "file": "SKILL.md",
            "line_start": 113,
            "line_end": 113
          },
          {
            "file": "SKILL.md",
            "line_start": 114,
            "line_end": 114
          },
          {
            "file": "SKILL.md",
            "line_start": 115,
            "line_end": 115
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 122,
            "line_end": 122
          },
          {
            "file": "SKILL.md",
            "line_start": 123,
            "line_end": 123
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "blocker:references/auditor-runtime.md:64:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/auditor-runtime.md",
        "line_start": 64,
        "line_end": 64,
        "snippet": "\"S2\": \"bid strategy and learning-state changes are governed\","
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 30,
        "line_end": 33,
        "snippet": "```text"
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 33,
        "line_end": 39,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 39,
        "snippet": "This skill judges. `conversion-signal-qa`, `attribution-reconciler`, `campaign-architect`, `ad-creat"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `roas-benchmark.md`, and the "
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 58,
        "snippet": "Declare profile (`direct-response|prospecting|incremental-profit`), target, currency, attribution wi"
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 63,
        "line_end": 66,
        "snippet": "2. Score all 20 `R1..S5` criteria from the benchmark with source/date/type/confidence."
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 66,
        "line_end": 67,
        "snippet": "- `ROAS-R1`: instrumentation demonstrably fails the named own-data truth set."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 67,
        "line_end": 68,
        "snippet": "- `ROAS-R2`: material double-counting/inflation is demonstrated."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "- `ROAS-O1`: material claim/disclosure failure against the `offer-claims-registry` approved state."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 70,
        "snippet": "- `ROAS-O2`: applicable platform/restricted-category violation."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 75,
        "snippet": "- `ROAS-A1`: placement evidence demonstrates a material safety breach."
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 76,
        "snippet": "- Complete direct-response profile, raw 78, no veto/fail: `DONE/SHIP`, final 78."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 77,
        "snippet": "- Complete profile, raw 78, one verified R1 failure: `DONE_WITH_CONCERNS/FIX`, final 59."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 78,
        "snippet": "- Complete profile, verified R1 and R2 failures: `DONE/BLOCK`, raw retained, no final score."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 90,
        "snippet": "- Missing placement report: A1 Unknown, `NEEDS_INPUT/UNDECIDED`, no overall score."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 94,
        "snippet": "Lead with business impact and evidence. On trace request, qualify `ROAS-R1/R2/O1/O2/A1`; do not expo"
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 94,
        "line_end": 94,
        "snippet": "Begin with the auditor-runbook's exact typed conversation header. Never replace `status`, `verdict`,"
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 108,
        "line_end": 108,
        "snippet": "Persist only after explicit authorization to `memory/audits/ad/YYYY-MM-DD-<topic>.md`. Assemble and "
      },
      {
        "id": "external_commands:SKILL.md:56:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `roas-benchmark.md`, and the "
      },
      {
        "id": "external_commands:SKILL.md:56:template-literal-with-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Template literal with command substitution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `roas-benchmark.md`, and the "
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 10,
        "line_end": 10,
        "snippet": "homepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\""
      },
      {
        "id": "network:SKILL.md:15:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 15,
        "line_end": 15,
        "snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"ad\", \"phase\": \"activate\", \""
      },
      {
        "id": "filesystem:SKILL.md:49:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 49,
        "line_end": 49,
        "snippet": "| Safety/claims | Placement report, rendered ad/landing, approved claim/disclosure state from [offer"
      },
      {
        "id": "filesystem:SKILL.md:56:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `roas-benchmark.md`, and the "
      },
      {
        "id": "filesystem:SKILL.md:112:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 112,
        "line_end": 112,
        "snippet": "- [ROAS benchmark](../../../references/roas-benchmark.md)"
      },
      {
        "id": "filesystem:SKILL.md:113:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 113,
        "line_end": 113,
        "snippet": "- [Measurement protocol](../../../references/measurement-protocol.md)"
      },
      {
        "id": "filesystem:SKILL.md:114:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 114,
        "line_end": 114,
        "snippet": "- [Auditor runbook](../../../references/auditor-runbook.md)"
      },
      {
        "id": "filesystem:SKILL.md:115:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 115,
        "line_end": 115,
        "snippet": "- [Scoring semantics](../../../references/scoring-semantics.md)"
      },
      {
        "id": "filesystem:SKILL.md:119:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 119,
        "line_end": 119,
        "snippet": "- **Tracking:** [conversion-signal-qa](../conversion-signal-qa/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:120:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 120,
        "snippet": "- **Claims/disclosures:** [offer-claims-registry](../../../protocol/offer-claims-registry/SKILL.md) "
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 121,
        "snippet": "- **Attribution:** [attribution-reconciler](../../scale/attribution-reconciler/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:122:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 122,
        "line_end": 122,
        "snippet": "- **Structure/audience:** [campaign-architect](../../research/campaign-architect/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:123:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 123,
        "line_end": 123,
        "snippet": "- **Pacing:** [budget-pacing-monitor](../../scale/budget-pacing-monitor/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:56:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `roas-benchmark.md`, and the "
      },
      {
        "id": "blocker:SKILL.md:6:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 6,
        "line_end": 6,
        "snippet": "description: 'Use when auditing a paid ad account for incremental contribution, wasted spend, or mea"
      },
      {
        "id": "blocker:SKILL.md:11:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 11,
        "line_end": 11,
        "snippet": "when_to_use: \"Use when checking whether a paid account or portfolio is safe to launch or scale. Requ"
      },
      {
        "id": "blocker:SKILL.md:49:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 49,
        "line_end": 49,
        "snippet": "| Safety/claims | Placement report, rendered ad/landing, approved claim/disclosure state from [offer"
      },
      {
        "id": "blocker:SKILL.md:102:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 102,
        "line_end": 102,
        "snippet": "- All 20 items have valid states and provenance; Unknown is not renormalized."
      }
    ],
    "finding_verdicts": [
      {
        "id": "blocker:references/auditor-runtime.md:64:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text describes paid-ad audit criteria and evidence requirements. It performs no host, network, credential, or service reconnaissance."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line documents a fixed-argument git root lookup and reads fixed reference paths. It is not an arbitrary command execution mechanism; unavailable dependencies cause a fail-closed, not-scored result."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown inline or fenced-code formatting, not executable Ruby or shell. The referenced tokens name audit criteria, document paths, or an explicitly permissioned persistence workflow."
      },
      {
        "id": "external_commands:SKILL.md:56:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line documents a fixed-argument git root lookup and reads fixed reference paths. It is not an arbitrary command execution mechanism; unavailable dependencies cause a fail-closed, not-scored result."
      },
      {
        "id": "external_commands:SKILL.md:56:template-literal-with-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line documents a fixed-argument git root lookup and reads fixed reference paths. It is not an arbitrary command execution mechanism; unavailable dependencies cause a fail-closed, not-scored result."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is homepage metadata only. The skill declares no request to it and no other network operation."
      },
      {
        "id": "network:SKILL.md:15:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is homepage metadata only. The skill declares no request to it and no other network operation."
      },
      {
        "id": "filesystem:SKILL.md:49:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:56:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:112:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:113:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:114:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:115:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:119:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:120:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:122:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:123:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:56:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The relative paths are static documentation links or explicitly scoped reference reads, not user-controlled path construction. They do not provide an arbitrary file-read or traversal primitive."
      },
      {
        "id": "blocker:SKILL.md:6:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text describes paid-ad audit criteria and evidence requirements. It performs no host, network, credential, or service reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:11:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text describes paid-ad audit criteria and evidence requirements. It performs no host, network, credential, or service reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:49:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text describes paid-ad audit criteria and evidence requirements. It performs no host, network, credential, or service reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:102:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text describes paid-ad audit criteria and evidence requirements. It performs no host, network, credential, or service reconnaissance."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 2,
    "total_lines": 350,
    "audit_model": "claude",
    "audited_at": "2026-07-26T09:51:39.879Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Audit paid advertising accounts before scaling",
    "value_statement": "Paid advertising decisions can rely on inflated attribution, incomplete measurement, or unsafe placements. This skill reviews exported evidence against a structured ROAS framework and returns a clear gate decision.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "ad account audit",
      "ROAS audit",
      "paid media measurement",
      "incrementality analysis",
      "marketing compliance",
      "attribution reconciliation",
      "wasted ad spend"
    ],
    "actual_capabilities": [
      "Collects required account context, including currency, attribution window, conversion lag, and business constraints.",
      "Scores 20 ROAS criteria across audience, offer, return, and spend efficiency.",
      "Separates platform-reported results from normalized own-data outcome evidence.",
      "Flags verified measurement, attribution, claims, policy, and placement-safety vetoes.",
      "Returns SHIP, FIX, BLOCK, or UNDECIDED outcomes based on evidence coverage and scoring.",
      "Produces prioritized fixes with owners and rerun conditions without changing account settings."
    ],
    "limitations": [
      "It evaluates evidence supplied by the user and cannot independently verify missing exports or source systems.",
      "It does not enable campaigns, edit bids, upload audiences, or change advertising budgets.",
      "It does not replace legal, platform-policy, finance, or experimental-design review.",
      "Standalone installs may collect observations but cannot calculate a score or persist an audit artifact."
    ],
    "use_cases": [
      {
        "title": "Approve budget growth",
        "description": "Review measurement and incrementality evidence before increasing spend on a paid-media portfolio.",
        "target_user": "Performance marketing leader"
      },
      {
        "title": "Investigate weak ROAS",
        "description": "Identify likely attribution, duplication, placement, or economics issues in an underperforming account.",
        "target_user": "Paid media manager"
      },
      {
        "title": "Prepare an audit handoff",
        "description": "Create an evidence-based account review with gaps, priorities, owners, and rerun conditions.",
        "target_user": "Marketing operations analyst"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a basic audit",
        "scenario": "Beginner",
        "prompt": "Audit this paid advertising account for direct response. I will provide campaign exports, conversion data, currency, attribution window, conversion lag, and CAC limit."
      },
      {
        "title": "Check launch readiness",
        "scenario": "Intermediate",
        "prompt": "Review this account before launch. Use the direct-response profile and identify any missing evidence, verified vetoes, and the correct SHIP, FIX, BLOCK, or UNDECIDED outcome."
      },
      {
        "title": "Assess incrementality",
        "scenario": "Advanced",
        "prompt": "Audit this portfolio with the incremental-profit profile. Compare the holdout results and deduplicated order-ID exports against the stated margin, payback, attribution window, and conversion lag."
      },
      {
        "title": "Request an executive report",
        "scenario": "Expert",
        "prompt": "Run a complete ROAS audit using the supplied exports. Present business impact, evidence quality, 20-item scoring, verified controls, unknowns, prioritized owners, and a rerun condition. Do not change account settings."
      }
    ],
    "output_examples": [
      {
        "input": "A direct-response account has normalized order IDs and a 7-day click window, but no placement report.",
        "output": [
          "Outcome: UNDECIDED",
          "Reason: Placement safety evidence is missing, so A1 remains Unknown.",
          "Next step: Provide the placement report before a final gate decision."
        ]
      },
      {
        "input": "An account has a strong reported ROAS but verified duplicate conversion counting.",
        "output": [
          "Outcome: BLOCK",
          "Reason: A verified attribution inflation failure affects return measurement.",
          "Next step: Correct conversion deduplication and rerun the audit with normalized outcomes."
        ]
      },
      {
        "input": "An account has complete evidence, a raw score of 78, and no verified vetoes.",
        "output": [
          "Outcome: SHIP",
          "Result: The evidence supports the declared direct-response profile.",
          "Next step: Continue monitoring against the documented business constraint."
        ]
      }
    ],
    "best_practices": [
      "Provide normalized exports with dates, IDs, currency, attribution windows, and conversion lag.",
      "Use own-data outcomes and holdout evidence when available instead of relying only on platform reporting.",
      "Treat missing required evidence as Unknown and resolve it before making scaling decisions."
    ],
    "anti_patterns": [
      "Do not treat platform-reported ROAS as proof of incremental profit.",
      "Do not compare channels before normalizing currency, windows, lag, and outcome IDs.",
      "Do not change campaigns or budgets based on an audit without separate explicit approval."
    ],
    "faq": [
      {
        "question": "What data should I provide?",
        "answer": "Provide delivery, spend, conversion, economics, attribution, placement, and change-history exports when available."
      },
      {
        "question": "Can this skill change my advertising account?",
        "answer": "No. It is an assessment skill and does not enable campaigns, change bids, upload audiences, or scale budgets."
      },
      {
        "question": "What happens when evidence is missing?",
        "answer": "The skill marks the related item as Unknown and may return UNDECIDED instead of inferring a result."
      },
      {
        "question": "Does a high ROAS guarantee a SHIP result?",
        "answer": "No. The audit also checks measurement integrity, incrementality, safety, claims, policy, and operating quality."
      },
      {
        "question": "What does BLOCK mean?",
        "answer": "BLOCK means a required control has a verified failure, such as material attribution inflation or a safety breach."
      },
      {
        "question": "Can it assess incremental profit?",
        "answer": "Yes, when you provide a suitable holdout, geo split, or causal-test evidence and declared business constraints."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "auditor-runtime.md",
          "type": "file",
          "path": "references/auditor-runtime.md",
          "lines": 226
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 124
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall