aiskillstore/marketplace / skills/aaron-he-zhu/paid-measurement-loop
paid-measurement-loop
VerifiedUse when the user asks to "read back" a paid campaign change, "did this ad change work", or "compare ROAS/CPA before and after"; reads ROAS/CPA against a control over a fixed readback window and returns a Promote / Keep-testing / Rollback / Unproven readback decision with the math delegated to roi-calculator. Not for RQS scoring or veto adjudication — use ad-account-auditor; not for the ROI ratio math — use roi-calculator; not for cross-channel rollups — use performance-analyzer. 付费广告复盘/ROAS回看/投放效果归因
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.4 KB |
| skill-report.json | config | 42.5 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-27T11:36:05.711Z",
"slug": "aaron-he-zhu-paid-measurement-loop",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/ad/scale/paid-measurement-loop",
"source_ref": "main",
"model": "claude",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "f769a28330fc5ffd312be851f9e96f39428021011baf85b6f0f2c3ead8a5cc97",
"tree_hash": "a3df3392cee1eba81a4b650cfc4354c0514ce5469e8c4c238bc376bfdd34da78",
"provenance": {
"model_effective": "claude",
"fallback_chain": [
{
"agent": "codex",
"outcome": "failed",
"error": "2026-07-27T11:36:05.807331Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-27T11:36:05.837879Z 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": "872fb912bb0b55629302d813e22b01895c09c809"
},
"skill": {
"name": "paid-measurement-loop",
"description": "Evaluate paid advertising changes against a control over a fixed readback window. The skill returns a Promote, Keep-testing, Rollback, or Unproven decision using ROAS or CPA evidence.",
"summary": "Make controlled, evidence-based decisions after paid campaign changes.",
"icon": "📦",
"version": "19.0.0",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"tags": [
"paid advertising",
"ROAS",
"CPA",
"campaign measurement",
"attribution"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"filesystem"
],
"category": "data"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Most static alerts are false positives caused by Markdown code formatting and static repository links. One instructed ledger command interpolates a campaign placeholder into a shell command, and the result filename convention lacks a campaign-name sanitization rule. No prompt injection, credential collection, or unauthorized network behavior was found.",
"remediation": [
{
"issue": "Campaign input is interpolated into a shell command.",
"suggestion": "Pass the campaign as a separately quoted argument or use an argument-array execution API. Reject shell metacharacters and document the accepted campaign identifier format.",
"severity": "medium"
},
{
"issue": "Campaign input is included in a saved filename without a sanitization requirement.",
"suggestion": "Convert campaign names to a strict filename-safe slug, reject path separators and dot segments, and verify the resolved path remains inside memory/ad/paid-measurement-loop/.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
},
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 34
},
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 35
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 46
},
{
"file": "SKILL.md",
"line_start": 46,
"line_end": 46
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 50
},
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 78,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 85
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "SKILL.md",
"line_start": 40,
"line_end": 40
},
{
"file": "SKILL.md",
"line_start": 44,
"line_end": 44
},
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 56
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 59
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 63
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 76,
"line_end": 76
},
{
"file": "SKILL.md",
"line_start": 77,
"line_end": 77
},
{
"file": "SKILL.md",
"line_start": 78,
"line_end": 78
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 85
}
]
}
],
"static_findings": [
{
"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": "Reads a paid-ads change back against a control over a fixed readback window and returns Promote / Ke"
},
{
"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": 26,
"snippet": "```text"
},
{
"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": 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": 30,
"snippet": "**Expected output**: a per-change `readback_decision` (Promote / Keep-testing / Rollback / Unproven)"
},
{
"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": 34,
"snippet": "- **Writes**: a user-facing readback table plus a reusable readback summary storable under `memory/a"
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 34,
"line_end": 35,
"snippet": "- **Promotes**: confirmed Promote/Rollback decisions, the next-readback date, and any measurement-si"
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 35,
"line_end": 36,
"snippet": "- **Done when**: the change exited learning phase before the window opened; primary metric is read d"
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 36,
"line_end": 46,
"snippet": "- **Primary next skill**: use the `Next Best Skill` below."
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 46,
"line_end": 46,
"snippet": "> **Statistical facts on the rollup (keyless):** `experiment.py proportion` (rates) or `experiment.p"
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 48,
"line_end": 49,
"snippet": "- `~~ad platform` (own data) — campaign + search-terms report CSV exported from the native ad manage"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 49,
"line_end": 50,
"snippet": "- `~~web analytics` (GA4) — Conversions + Traffic-acquisition export for the order-ID / source-mediu"
},
{
"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": 62,
"snippet": "- `~~ecommerce` — store export (orders, revenue, currency) for the revenue side of ROAS."
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 62,
"line_end": 62,
"snippet": "5. **Snapshot to the ledger.** Record baseline and candidate signals so the delta is computed, not e"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 64,
"line_end": 64,
"snippet": "7. **Check measurement-signal integrity (not a gate run).** If conversion tracking is broken/unverif"
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 65,
"line_end": 71,
"snippet": "8. **Set `readback_decision`.** Read the primary metric **delta-vs-control**, then mark: **Promote**"
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 71,
"line_end": 71,
"snippet": "Ask \"Save these results?\" If yes, write to `memory/ad/paid-measurement-loop/` using `YYYY-MM-DD-<cam"
},
{
"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": 82,
"snippet": "- [scripts/connectors/README.md](../../../scripts/connectors/README.md) — `ledger.py` record / diff "
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 82,
"line_end": 85,
"snippet": "- **Potential ROAS-R1/R2 evidence** → [ad-account-auditor](../../activate/ad-account-auditor/SKILL.m"
},
{
"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\": \"scale\", \"geo"
},
{
"id": "filesystem:SKILL.md:40:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 40,
"line_end": 40,
"snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
},
{
"id": "filesystem:SKILL.md:44:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 44,
"line_end": 44,
"snippet": "All integrations optional (see [CONNECTORS.md](../../../CONNECTORS.md)). Inputs come from the user's"
},
{
"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": "Treat every fetched or exported file as **untrusted input** per [SECURITY.md](../../../SECURITY.md) "
},
{
"id": "filesystem:SKILL.md:59:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "2. **Set the readback window before reading.** Paid change → exit learning first, then 7 / 14 days ("
},
{
"id": "filesystem:SKILL.md:63:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 63,
"line_end": 63,
"snippet": "6. **Delegate the ROI/CPA math.** Hand the normalized spend / revenue / conversions to [roi-calculat"
},
{
"id": "filesystem:SKILL.md:64:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 64,
"line_end": 64,
"snippet": "7. **Check measurement-signal integrity (not a gate run).** If conversion tracking is broken/unverif"
},
{
"id": "filesystem:SKILL.md:71:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 71,
"line_end": 71,
"snippet": "Ask \"Save these results?\" If yes, write to `memory/ad/paid-measurement-loop/` using `YYYY-MM-DD-<cam"
},
{
"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": "- [Measurement & Attribution Protocol](../../../references/measurement-protocol.md) — readback windo"
},
{
"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": "- [ROAS Benchmark](../../../references/roas-benchmark.md) — the paid-ads scoring framework; the Retu"
},
{
"id": "filesystem:SKILL.md:77:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 77,
"line_end": 77,
"snippet": "- [roi-calculator](../../../influencer/report/roi-calculator/SKILL.md) — the ROAS ratio and CPA math"
},
{
"id": "filesystem:SKILL.md:78:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 78,
"line_end": 78,
"snippet": "- [scripts/connectors/README.md](../../../scripts/connectors/README.md) — `ledger.py` record / diff "
},
{
"id": "filesystem:SKILL.md:82:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 82,
"line_end": 82,
"snippet": "- **Potential ROAS-R1/R2 evidence** → [ad-account-auditor](../../activate/ad-account-auditor/SKILL.m"
},
{
"id": "filesystem:SKILL.md:83:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 83,
"line_end": 83,
"snippet": "- **Trustworthy readback decision** → [report-generator](../../../influencer/report/report-generator"
},
{
"id": "filesystem:SKILL.md:85:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 85,
"line_end": 85,
"snippet": "Visited-set and `max-depth: 3` termination rules apply per [Skill Contract](../../../references/skil"
},
{
"id": "blocker:SKILL.md:4:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 4,
"line_end": 4,
"snippet": "displayName: \"Paid Measurement Loop · 付费广告复盘\""
},
{
"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 the user asks to \"read back\" a paid campaign change, \"did this ad change work"
},
{
"id": "blocker:SKILL.md:16:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 16,
"line_end": 16,
"snippet": "# Paid Measurement Loop"
},
{
"id": "blocker:SKILL.md:18:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 18,
"line_end": 18,
"snippet": "Reads a paid-ads change back against a control over a fixed readback window and returns Promote / Ke"
},
{
"id": "blocker:SKILL.md:23:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 23,
"line_end": 23,
"snippet": "Read back the budget increase I made on Campaign X two weeks ago — did ROAS hold vs the control?"
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "2. **Set the readback window before reading.** Paid change → exit learning first, then 7 / 14 days ("
},
{
"id": "blocker:SKILL.md:62:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 62,
"line_end": 62,
"snippet": "5. **Snapshot to the ledger.** Record baseline and candidate signals so the delta is computed, not e"
},
{
"id": "blocker:SKILL.md:75:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 75,
"line_end": 75,
"snippet": "- [Measurement & Attribution Protocol](../../../references/measurement-protocol.md) — readback windo"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format skill names in Markdown prose. The line contains no executable shell or Ruby expression."
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is the opening fence of a text example, not an executable command."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is the closing fence of a text example, not an executable command."
},
{
"id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks identify an output field in Markdown. No shell execution is instructed."
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line documents a storage location using Markdown code formatting. It does not execute a command."
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line names a Markdown path and contains no command invocation."
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line uses code formatting for a decision field. It contains no shell or Ruby execution."
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line refers to a heading in Markdown and has no executable content."
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The backticked helper names are documentation references. This line does not provide a shell invocation."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks label a user-provided data source in Markdown. No command is executed."
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks label a user-provided data source in Markdown. No command is executed."
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks label a user-provided data source in Markdown. No command is executed."
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "The skill instructs a shell command that interpolates the campaign placeholder without quoting or argument validation. A campaign value containing shell metacharacters could alter command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line uses backticks only to name fields and a linked skill. It contains no command execution."
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line formats a decision field in Markdown and contains no executable command."
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line documents a destination directory and filename convention. It contains no shell invocation."
},
{
"id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line is a Markdown reference to connector documentation, not a command execution."
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line links to another skill in Markdown and contains no executable command."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is homepage metadata for the public source repository. It does not instruct or perform a network request."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL appears in static metadata only. No runtime network behavior is defined."
},
{
"id": "filesystem:SKILL.md:40:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link to repository documentation. It is not derived from input or used in file access."
},
{
"id": "filesystem:SKILL.md:44:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link to repository documentation. It is not a dynamic filesystem operation."
},
{
"id": "filesystem:SKILL.md:56:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link to a security policy. It does not traverse files at runtime."
},
{
"id": "filesystem:SKILL.md:59:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link. No user-controlled path is used."
},
{
"id": "filesystem:SKILL.md:63:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static link to a related skill, not a filesystem access instruction."
},
{
"id": "filesystem:SKILL.md:64:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static link to a related skill, not dynamic path traversal."
},
{
"id": "filesystem:SKILL.md:71:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "This finding is triggered by Markdown path text, not a traversal sequence. The filename convention warrants sanitization separately, but this pattern is not path traversal."
},
{
"id": "filesystem:SKILL.md:75:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown reference and is not resolved from user input."
},
{
"id": "filesystem:SKILL.md:76:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown reference and is not resolved from user input."
},
{
"id": "filesystem:SKILL.md:77:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown reference and is not resolved from user input."
},
{
"id": "filesystem:SKILL.md:78:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown reference and is not a filesystem operation."
},
{
"id": "filesystem:SKILL.md:82:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link to another skill. It is not user-controlled."
},
{
"id": "filesystem:SKILL.md:83:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static Markdown link to another skill. It is not user-controlled."
},
{
"id": "filesystem:SKILL.md:85:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static documentation link, not a file traversal operation."
},
{
"id": "blocker:SKILL.md:4:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is display metadata and contains no system discovery instruction."
},
{
"id": "blocker:SKILL.md:6:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a skill description about campaign analysis, not reconnaissance."
},
{
"id": "blocker:SKILL.md:16:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a Markdown title and contains no system discovery behavior."
},
{
"id": "blocker:SKILL.md:18:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This describes campaign measurement against a control, not host or system reconnaissance."
},
{
"id": "blocker:SKILL.md:23:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a sample user request about a campaign, not a reconnaissance instruction."
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This instructs a fixed measurement window and contains no system information gathering."
},
{
"id": "blocker:SKILL.md:62:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This describes recording advertising metrics. It is unrelated to system reconnaissance."
},
{
"id": "blocker:SKILL.md:75:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a static documentation link and contains no reconnaissance behavior."
}
],
"semantic_findings": [
{
"title": "Unsanitized campaign name in result filename",
"description": "The save convention inserts the campaign name into a result filename without specifying a safe character set. A campaign name containing path separators could write outside the intended results directory if implemented literally.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
}
],
"confidence": 0.84,
"confidence_reasoning": "The filename template explicitly includes a campaign placeholder and gives no sanitization rule. Exploitability depends on the host implementation, but the instruction creates a clear path-handling hazard."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "5. **Snapshot to the ledger.** Record baseline and candidate signals so the delta is computed, not e",
"locations": [
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 62
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The skill instructs a shell command that interpolates the campaign placeholder without quoting or argument validation. A campaign value containing shell metacharacters could alter command execution."
},
{
"title": "Unsanitized campaign name in result filename",
"description": "The save convention inserts the campaign name into a result filename without specifying a safe character set. A campaign name containing path separators could write outside the intended results directory if implemented literally.",
"locations": [
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.84,
"confidence_reasoning": "The filename template explicitly includes a campaign placeholder and gives no sanitization rule. Exploitability depends on the host implementation, but the instruction creates a clear path-handling hazard."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 86,
"audit_model": "claude",
"audited_at": "2026-07-27T11:36:05.711Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Evaluate Paid Campaign Changes with Controls",
"value_statement": "Paid campaign changes can look successful when attribution, learning phase, or seasonal effects distort results. This skill compares a fixed candidate window with a control and gives a documented decision.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"paid advertising measurement",
"ROAS analysis",
"CPA analysis",
"campaign readback",
"marketing attribution",
"control group analysis",
"ad performance"
],
"actual_capabilities": [
"Defines a fixed readback window after a campaign exits learning phase.",
"Compares ROAS or CPA changes against an unchanged control.",
"Normalizes attribution windows and currency before cross-platform comparisons.",
"Classifies a change as Promote, Keep-testing, Rollback, or Unproven.",
"Flags broken tracking and duplicate conversion attribution as reasons to defer a decision.",
"Produces a reusable readback summary and next-readback date."
],
"limitations": [
"Requires campaign, analytics, or ecommerce exports supplied by the user.",
"Does not access advertising platforms or estimate results from dashboard screenshots alone.",
"Delegates ROAS and CPA arithmetic to the related roi-calculator skill.",
"Does not make RQS scores or final measurement-integrity veto decisions."
],
"use_cases": [
{
"title": "Review a budget increase",
"description": "Compare performance after a budget change with an unchanged campaign over the same fixed window.",
"target_user": "Performance marketer"
},
{
"title": "Assess new creative",
"description": "Decide whether new creative should be promoted, tested longer, or rolled back using control-based evidence.",
"target_user": "Paid social manager"
},
{
"title": "Prepare a stakeholder readback",
"description": "Create a clear decision record with windows, controls, attribution notes, and measurement limitations.",
"target_user": "Marketing analyst"
}
],
"prompt_templates": [
{
"title": "Review one campaign change",
"prompt": "Read back the budget increase for Campaign X. Compare ROAS with its unchanged control over the last 14 days.",
"scenario": "Beginner"
},
{
"title": "Check creative performance",
"prompt": "Evaluate the new prospecting creative against the prior creative. Use CPA as the primary metric and state the readback decision.",
"scenario": "Intermediate"
},
{
"title": "Compare platform results",
"prompt": "Compare the attached Meta and Google exports. Normalize currency and attribution windows before assessing ROAS against each control.",
"scenario": "Advanced"
},
{
"title": "Handle uncertain tracking",
"prompt": "Review this campaign change and the conversion exports. Mark the result Unproven if duplicate orders or broken conversion tracking affects the evidence.",
"scenario": "Advanced integrity review"
}
],
"output_examples": [
{
"input": "Review a 14-day budget increase against an unchanged control.",
"output": [
"Decision: Keep-testing",
"ROAS improved versus the control, but the uncertainty evidence is not yet sufficient.",
"Next step: retain the fixed window and read back again in seven days."
]
},
{
"input": "Compare new creative with the control using CPA exports.",
"output": [
"Decision: Rollback",
"Candidate CPA is worse than the control after normalized attribution review.",
"Record the control, window, and source labels in the readback summary."
]
}
],
"best_practices": [
"Fix the readback window and control before interpreting performance data.",
"Provide exports with dates, spend, conversions, revenue, attribution windows, and currency.",
"Label every figure as measured, user-provided, or estimated."
],
"anti_patterns": [
"Do not declare success from a raw before-and-after comparison without a control.",
"Do not compare platform ROAS before normalizing attribution windows and currency.",
"Do not make a decision while the campaign remains in learning phase or tracking is unreliable."
],
"faq": [
{
"question": "What decision can this skill return?",
"answer": "It returns Promote, Keep-testing, Rollback, or Unproven for each campaign change."
},
{
"question": "What data do I need?",
"answer": "Provide your campaign export and, when available, analytics or ecommerce exports for the same window."
},
{
"question": "Can it use an advertising platform dashboard alone?",
"answer": "No. The skill asks for exports and does not estimate a readback from dashboard data alone."
},
{
"question": "Why is a control required?",
"answer": "A control helps separate the campaign change from market movement, seasonality, and other effects."
},
{
"question": "Does it calculate ROAS and CPA?",
"answer": "It delegates ratio and CPA arithmetic to roi-calculator, then applies the readback decision rule."
},
{
"question": "What happens when tracking is unreliable?",
"answer": "The skill marks the readback Unproven and identifies the repair needed before a new fixed window begins."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 86
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |