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-history-schema.json
View on GitHub{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://github.com/Hainrixz/claude-ads/blob/main/ads/references/audit-history-schema.json",
"title": "claude-ads audit history index",
"description": "Shape of ~/.claude-ads/history/index.json — a summary log of every audit ever run, in chronological order. Full per-audit JSON snapshots live alongside as ~/.claude-ads/history/<platform>-<YYYYMMDDhhmmss>.json (each conforms to ads/references/audit-output-schema.json). /ads next uses this index to detect regressions, surface trends, and rank Quick Wins by recency.",
"type": "object",
"additionalProperties": false,
"required": ["version", "audits"],
"properties": {
"version": {
"type": "string",
"const": "1.0"
},
"audits": {
"type": "array",
"description": "Chronologically ordered (oldest first). Append-only — /ads start reset clears the whole file.",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["platform", "timestamp", "file"],
"properties": {
"platform": {
"type": "string",
"enum": ["meta", "google", "tiktok"]
},
"timestamp": {
"type": "string",
"format": "date-time",
"description": "ISO-8601 UTC timestamp the audit completed."
},
"health_score": {
"type": ["number", "null"],
"minimum": 0,
"maximum": 100,
"description": "Overall health score reported by the audit-* agent."
},
"grade": {
"type": ["string", "null"],
"enum": [null, "A", "B", "C", "D", "F"]
},
"data_source": {
"type": ["string", "null"],
"enum": [null, "mcp", "direct_api", "export", "manual", "mixed"],
"description": "Which tier produced the data for this audit (matches audit-output-schema.json data_source field)."
},
"critical_count": {
"type": ["integer", "null"],
"minimum": 0
},
"quick_wins_count": {
"type": ["integer", "null"],
"minimum": 0
},
"file": {
"type": "string",
"pattern": "^(meta|google|tiktok)-[0-9]{14,20}\\.json$",
"description": "Relative filename of the full audit JSON snapshot inside ~/.claude-ads/history/. Format: <platform>-<YYYYMMDDhhmmss[ffffff]>.json (microseconds appended to disambiguate same-second saves)."
}
}
}
}
}
}
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 |