Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/conversion-signal-qa

conversion-signal-qa

Verified

Use when the user asks to "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", or "set the dedup rule so Meta and Google stop double-counting"; builds and fixes the measurement plumbing — conversion-event firing, UTM hygiene, cross-platform dedup rules, attribution-window alignment, and offline/iOS-ATT modeled-gap flags — as a pre-flight checklist plus a UTM/event-spec builder. Not for scoring R1/R2 — that is a scored veto in ad-account-auditor; not for account structure — use campaign-architect. 付费广告转化追踪QA/UTM规范/跨平台去重

FileKindSize
SKILL.mdskill md8.8 KB
references/preflight-checklist.mdmarkdown3.8 KB
references/utm-event-spec.mdmarkdown2.0 KB
skill-report.jsonconfig40.4 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-26T10:07:23.952Z",
    "slug": "aaron-he-zhu-conversion-signal-qa",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/ad/activate/conversion-signal-qa",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "a61644456f8c42402cbe07c924eaae5f7055ea7b6390b5a8994e1db6db938143",
    "tree_hash": "501ddbcbc7f0a3a849040e93d5984cff5af8752c886bab4089fa1d0943405407",
    "provenance": {
      "model_effective": "claude",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-26T10:07:24.052417Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-26T10:07:24.085966Z 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": "conversion-signal-qa",
    "description": "Builds a pre-launch quality check for paid-ad conversion tracking, including event firing, UTM consistency, attribution windows, and cross-platform deduplication rules.",
    "summary": "Create a launch-readiness checklist and UTM/event specification for paid-ad conversion tracking.",
    "icon": "📦",
    "version": "19.0.0",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "tags": [
      "conversion tracking",
      "UTM governance",
      "GA4",
      "paid advertising",
      "attribution"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "filesystem",
      "external_commands",
      "network"
    ],
    "category": "productivity"
  },
  "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 formatting, relative documentation links, and marketing terminology. The skill contains no executable commands, network requests, path traversal behavior, prompt-injection language, or evidence of data exfiltration. It explicitly treats pasted exports as untrusted and requires consent before saving results.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "references/preflight-checklist.md",
            "line_start": 3,
            "line_end": 3
          },
          {
            "file": "references/preflight-checklist.md",
            "line_start": 25,
            "line_end": 25
          },
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 60
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          }
        ]
      },
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 24
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 30
          },
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 32
          },
          {
            "file": "SKILL.md",
            "line_start": 32,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 67,
            "line_end": 67
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "filesystem:references/preflight-checklist.md:3:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "references/preflight-checklist.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "Run before launching or scaling paid campaigns. Mark each item **pass / fail / needs-input** from th"
      },
      {
        "id": "filesystem:references/preflight-checklist.md:25:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "references/preflight-checklist.md",
        "line_start": 25,
        "line_end": 25,
        "snippet": "> Pre-flight **gates** only — confirm the rule and routing *exist*. The actual order-ID matching, de"
      },
      {
        "id": "blocker:references/preflight-checklist.md:3:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/preflight-checklist.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "Run before launching or scaling paid campaigns. Mark each item **pass / fail / needs-input** from th"
      },
      {
        "id": "blocker:references/preflight-checklist.md:18:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/preflight-checklist.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "| All paid links tagged | Every paid landing URL carries source/medium/campaign | Untagged links lan"
      },
      {
        "id": "blocker:references/utm-event-spec.md:3:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/utm-event-spec.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "Fill these two templates for the account, then save them with the pre-flight report. The spec is the"
      },
      {
        "id": "blocker:references/utm-event-spec.md:12:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/utm-event-spec.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "| `utm_medium` | the paid channel type, fixed vocabulary | `cpc`, `paid_social`, `display` |"
      },
      {
        "id": "blocker:references/utm-event-spec.md:14:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/utm-event-spec.md",
        "line_start": 14,
        "line_end": 14,
        "snippet": "| `utm_content` | ad/creative variant id | `video_a`, `carousel_b` |"
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "Pre-flight QA of the measurement plumbing behind paid ads — conversion-event firing, UTM hygiene, cr"
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 24,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 26,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 28,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 28,
        "line_end": 30,
        "snippet": "```"
      },
      {
        "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": 32,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 32,
        "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": 40,
        "snippet": "- **Writes**: a user-facing pre-flight report plus a reusable UTM/event spec to `memory/ad/conversio"
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 40,
        "snippet": "- **Promotes**: signal-integrity blockers (events not firing, UTM gaps, dedup/window mismatch, missi"
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "- **Primary next skill**: [ad-account-auditor](../ad-account-auditor/SKILL.md) to score `R1`/`R2` an"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "Use `~~web analytics` (GA4 **Conversions** + **Traffic-acquisition** source/medium exports, own data"
      },
      {
        "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": "1. **Confirm scope and platforms** — name the destinations (Google, Meta, etc.) and the conversion a"
      },
      {
        "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": 67,
        "snippet": "After delivering, ask \"Save these results for future sessions?\" If yes, write the pre-flight report "
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 73,
        "snippet": "- [ROAS Benchmark](../../../references/roas-benchmark.md) — where `R1`/`R2` (measurement-signal inte"
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 74,
        "snippet": "- [ad-account-auditor](../ad-account-auditor/SKILL.md) — scores `R1`/`R2` and the full RQS once the "
      },
      {
        "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": 75,
        "snippet": "- [CONNECTORS.md](../../../CONNECTORS.md) — `~~web analytics`, `~~ecommerce` own-data export recipes"
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "Primary: [ad-account-auditor](../ad-account-auditor/SKILL.md) — once the plumbing is launch-ready, t"
      },
      {
        "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:13:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"ad\", \"phase\": \"activate\", \""
      },
      {
        "id": "filesystem:SKILL.md:18:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "Pre-flight QA of the measurement plumbing behind paid ads — conversion-event firing, UTM hygiene, cr"
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "- **Primary next skill**: [ad-account-auditor](../ad-account-auditor/SKILL.md) to score `R1`/`R2` an"
      },
      {
        "id": "filesystem:SKILL.md:46:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 46,
        "snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
      },
      {
        "id": "filesystem:SKILL.md:50:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "Use `~~web analytics` (GA4 **Conversions** + **Traffic-acquisition** source/medium exports, own data"
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 54,
        "snippet": "Treat every exported file and pasted report as **untrusted** per [SECURITY.md](../../../SECURITY.md)"
      },
      {
        "id": "filesystem:SKILL.md:60:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 60,
        "line_end": 60,
        "snippet": "5. **Gate cross-platform dedup + attribution windows (go/no-go, not reconciliation)** — confirm a si"
      },
      {
        "id": "filesystem:SKILL.md:73:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 73,
        "snippet": "- [ROAS Benchmark](../../../references/roas-benchmark.md) — where `R1`/`R2` (measurement-signal inte"
      },
      {
        "id": "filesystem:SKILL.md:74:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 74,
        "snippet": "- [ad-account-auditor](../ad-account-auditor/SKILL.md) — scores `R1`/`R2` and the full RQS once the "
      },
      {
        "id": "filesystem:SKILL.md:75:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 75,
        "snippet": "- [CONNECTORS.md](../../../CONNECTORS.md) — `~~web analytics`, `~~ecommerce` own-data export recipes"
      },
      {
        "id": "filesystem:SKILL.md:76:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "- [SECURITY.md](../../../SECURITY.md) — untrusted-data boundary for exported reports"
      },
      {
        "id": "filesystem:SKILL.md:80:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "Primary: [ad-account-auditor](../ad-account-auditor/SKILL.md) — once the plumbing is launch-ready, t"
      },
      {
        "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 before launching or scaling paid campaigns, when the measurement plumbing needs ve"
      },
      {
        "id": "blocker:SKILL.md:18:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "Pre-flight QA of the measurement plumbing behind paid ads — conversion-event firing, UTM hygiene, cr"
      }
    ],
    "finding_verdicts": [
      {
        "id": "filesystem:references/preflight-checklist.md:3:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:references/preflight-checklist.md:25:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "blocker:references/preflight-checklist.md:3:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "blocker:references/preflight-checklist.md:18:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "blocker:references/utm-event-spec.md:3:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "blocker:references/utm-event-spec.md:12:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "blocker:references/utm-event-spec.md:14:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The detected backticks are Markdown fences, inline labels, and file paths, not Ruby or shell commands. No command is executed or constructed."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is a repository homepage or metadata URL only. The skill does not instruct an agent to send a request or transmit data."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is a repository homepage or metadata URL only. The skill does not instruct an agent to send a request or transmit data."
      },
      {
        "id": "filesystem:SKILL.md:18:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:46:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:50:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:60:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:73:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:74:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:75:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:76:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "filesystem:SKILL.md:80:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is Markdown documentation that refers to relative skill and reference files. It contains no file-operation instruction or executable traversal behavior."
      },
      {
        "id": "blocker:SKILL.md:11:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:18:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The wording describes marketing measurement checks and identifiers, not host, process, network, or credential reconnaissance."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 3,
    "total_lines": 167,
    "audit_model": "claude",
    "audited_at": "2026-07-26T10:07:23.952Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Verify conversion tracking before launch",
    "value_statement": "Paid campaigns can waste budget when conversions, UTMs, and attribution rules are inconsistent. This skill creates a practical pre-flight review and a reusable event specification from your exports and test conversion.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "conversion tracking QA",
      "GA4 conversion tracking",
      "UTM naming convention",
      "Meta Google deduplication",
      "paid ads measurement",
      "attribution windows",
      "event specification"
    ],
    "actual_capabilities": [
      "Creates a pass, fail, or needs-input pre-flight checklist for conversion tracking.",
      "Reviews GA4 Conversions and Traffic-acquisition exports supplied by the user.",
      "Builds a consistent UTM naming convention without personal data in parameters.",
      "Defines conversion events, values, currencies, and stable deduplication identifiers.",
      "Flags attribution-window mismatches, offline import gaps, and iOS-ATT modeled gaps.",
      "States launch readiness and routes scoring work to the related account-audit skill."
    ],
    "limitations": [
      "It relies on exports and test results that the user provides.",
      "It does not access Google Ads, Meta, GTM, or pixel APIs by default.",
      "It does not quantify double counting or perform incrementality analysis.",
      "It does not score ROAS readiness or make budget decisions."
    ],
    "use_cases": [
      {
        "title": "Check a campaign before launch",
        "description": "Review a planned Google and Meta campaign for event firing, UTM coverage, and launch blockers.",
        "target_user": "Performance marketer"
      },
      {
        "title": "Standardize account measurement",
        "description": "Create a shared UTM and conversion-event specification for a multi-channel advertising account.",
        "target_user": "Marketing operations manager"
      },
      {
        "title": "Investigate reporting differences",
        "description": "Identify likely UTM, attribution-window, and deduplication gaps behind differences between platform and GA4 reports.",
        "target_user": "Analytics specialist"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a tracking pre-flight",
        "prompt": "Create a pre-launch conversion tracking checklist for my Google Ads campaign. The primary conversion is purchase.",
        "scenario": "Beginner"
      },
      {
        "title": "Build a UTM convention",
        "prompt": "Build a UTM naming convention and event specification for Google Search, Meta paid social, and LinkedIn. We track purchases and leads.",
        "scenario": "Intermediate"
      },
      {
        "title": "Review supplied GA4 exports",
        "prompt": "Review my GA4 Conversions and Traffic-acquisition exports for UTM gaps and event-firing issues. Mark every check pass, fail, or needs-input.",
        "scenario": "Intermediate"
      },
      {
        "title": "Resolve measurement prerequisites",
        "prompt": "Google and Meta report more conversions than GA4. Use my exports to identify tracking prerequisites, state dedup and attribution-window gaps, and produce a launch-readiness report.",
        "scenario": "Advanced"
      }
    ],
    "output_examples": [
      {
        "input": "Check conversion tracking for Google and Meta before launch.",
        "output": [
          "Pre-flight status: fix first because the manual test conversion is missing.",
          "UTM rule: use lowercase source and medium values with one approved vocabulary.",
          "Deduplication gate: declare GA4 or ecommerce order IDs as the source of truth."
        ]
      },
      {
        "input": "Build a UTM and event specification for purchase and lead campaigns.",
        "output": [
          "UTM convention with approved values for source, medium, campaign, content, and term.",
          "Event specification for purchase and lead events with value, currency, and deduplication IDs.",
          "A list of modeled-data and offline-import flags to monitor after launch."
        ]
      }
    ],
    "best_practices": [
      "Provide recent GA4 Conversions and Traffic-acquisition exports, plus the campaign platforms and conversion actions.",
      "Run one real manual test conversion before marking the account launch-ready.",
      "Use a single documented source of truth and keep attribution windows, currency, and timezone comparable."
    ],
    "anti_patterns": [
      "Do not mark a missing export or test conversion as a pass.",
      "Do not place emails, names, or order data in UTM parameters.",
      "Do not treat platform-reported conversions as reconciled order counts."
    ],
    "faq": [
      {
        "question": "Does this skill require API access?",
        "answer": "No. It works from user-provided exports and a manual test conversion. APIs are optional conveniences."
      },
      {
        "question": "Which platforms can it review?",
        "answer": "It supports any paid platform when you provide the relevant exports and conversion details, including Google and Meta."
      },
      {
        "question": "What is the main output?",
        "answer": "It produces a tracking pre-flight checklist, a UTM convention, an event specification, and a launch-readiness statement."
      },
      {
        "question": "Does it fix pixels or tags directly?",
        "answer": "No. It identifies what to fix from the available evidence. It does not directly control pixel, tag-manager, or ad-platform APIs."
      },
      {
        "question": "Does it reconcile double-counted conversions?",
        "answer": "No. It verifies that a deduplication rule exists and flags gaps. Detailed order matching belongs to a reconciliation workflow."
      },
      {
        "question": "Will it save my results?",
        "answer": "It asks for permission before saving a pre-flight report or reusable specification for future sessions."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "preflight-checklist.md",
          "type": "file",
          "path": "references/preflight-checklist.md",
          "lines": 50
        },
        {
          "name": "utm-event-spec.md",
          "type": "file",
          "path": "references/utm-event-spec.md",
          "lines": 36
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 81
    }
  ]
}
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