Hainrixz/claude-ads / ads
ads
UnverifiedFree-first paid advertising audit and optimization skill, focused on the 3 platforms where 95% of advertiser spend lives: Meta, Google, TikTok. Guided onboarding (/ads start) saves context once and step-by-step OAuth walkthroughs; continuous coach (/ads next) ranks Quick Wins after each audit. ~158 weighted checks with scoring, parallel agents, industry templates, and AI creative generation.
references/audit-output-schema.json
View on GitHub{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://github.com/Hainrixz/claude-ads/ads/references/audit-output-schema.json",
"title": "Claude Ads — Audit Agent Output",
"description": "Canonical output schema every audit-* agent must emit alongside its human-readable markdown. The orchestrator (`ads/SKILL.md`) parses these JSON files to aggregate the cross-platform Ads Health Score. Adding a new audit platform = produce JSON that validates against this schema.",
"type": "object",
"required": ["platform", "version", "health_score", "grade", "category_scores", "checks"],
"additionalProperties": false,
"properties": {
"platform": {
"type": "string",
"enum": ["google", "meta", "tiktok"],
"description": "Which audit produced this result. Must match the agent's `name` minus the `audit-` prefix."
},
"version": {
"type": "string",
"pattern": "^[0-9]+\\.[0-9]+$",
"description": "Schema version this document conforms to (e.g. \"1.0\"). Bump on breaking schema changes."
},
"generated_at": {
"type": "string",
"format": "date-time",
"description": "ISO-8601 timestamp when the audit completed."
},
"account_id": {
"type": ["string", "null"],
"description": "Optional platform-native account identifier (e.g. Meta ad_account_id, Google CID). Null if audit ran on manual exports."
},
"data_source": {
"type": "string",
"enum": ["mcp", "export", "screenshot", "manual", "mixed"],
"description": "How the audit obtained its source data. \"mcp\" means live platform API via MCP server."
},
"health_score": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Weighted aggregate score for this platform/dimension. See `scoring-system.md`."
},
"grade": {
"type": "string",
"enum": ["A", "B", "C", "D", "F"],
"description": "Letter grade derived from health_score (A:90-100, B:75-89, C:60-74, D:40-59, F:<40)."
},
"category_scores": {
"type": "object",
"description": "Per-category breakdown summing (weighted) to health_score.",
"additionalProperties": {
"type": "object",
"required": ["score", "weight"],
"additionalProperties": false,
"properties": {
"score": { "type": "number", "minimum": 0, "maximum": 100 },
"weight": { "type": "number", "minimum": 0, "maximum": 1 }
}
}
},
"checks": {
"type": "array",
"description": "All checks evaluated, in order. Skipped checks should be included with result \"N/A\".",
"items": {
"type": "object",
"required": ["id", "severity", "result"],
"additionalProperties": false,
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Z]+(-[A-Z]+)?-?[A-Z0-9]+$",
"description": "Stable check identifier (e.g. G01, M-AT1, T-PI2, X-PI1). Letters identify platform/family."
},
"category": { "type": "string" },
"name": { "type": "string", "description": "Short check title." },
"severity": { "type": "string", "enum": ["critical", "high", "medium", "low"] },
"result": { "type": "string", "enum": ["PASS", "WARNING", "FAIL", "N/A"] },
"finding": { "type": "string", "description": "What was observed in the data." },
"recommendation": { "type": "string", "description": "What to do about it." },
"fix_time_minutes": { "type": ["number", "null"], "minimum": 0 },
"evidence": {
"type": ["object", "null"],
"description": "Optional structured evidence (metric values, screenshots paths, MCP tool responses).",
"additionalProperties": true
}
}
}
},
"quick_wins": {
"type": "array",
"description": "Subset of checks with severity in {critical, high} AND fix_time_minutes <= 15. Sorted by impact.",
"items": {
"type": "object",
"required": ["check_id", "action"],
"additionalProperties": false,
"properties": {
"check_id": { "type": "string" },
"action": { "type": "string" },
"impact_estimate": { "type": "string" },
"effort_minutes": { "type": "number", "minimum": 0 }
}
}
},
"critical_issues": {
"type": "array",
"description": "Checks that failed at severity \"critical\". These block the platform from scoring above C until fixed.",
"items": {
"type": "object",
"required": ["check_id", "blocker_reason"],
"additionalProperties": false,
"properties": {
"check_id": { "type": "string" },
"blocker_reason": { "type": "string" },
"estimated_revenue_at_risk": { "type": ["string", "null"] }
}
}
},
"notes": {
"type": "string",
"description": "Free-form notes for the orchestrator or human reviewer."
}
}
}
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 |