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/conciencia-schema.json
View on GitHub{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://github.com/Hainrixz/claude-ads/blob/main/ads/references/conciencia-schema.json",
"title": "claude-ads campaign awareness (conciencia de campaña)",
"description": "Shape of ~/.claude-ads/conciencia/<platform>-<campaign_id>.json — what Claude knows and does NOT know about the real business outcome of one campaign. Platform metrics come from audits / MCP / API / exports; business outcomes (conversations, qualified leads, closed deals, revenue, junk) come only from the user via dated check-ins. Unreported values stay null, never 0. Written by scripts/conciencia.py; read by /ads conciencia, /ads audit and /ads next.",
"type": "object",
"additionalProperties": false,
"required": ["version", "created_at", "updated_at", "campaign", "knowns", "unknowns", "checkins", "checkin_every_days", "next_checkin_at", "status"],
"properties": {
"version": { "type": "string", "const": "1.0" },
"created_at": { "type": "string", "format": "date-time" },
"updated_at": { "type": "string", "format": "date-time" },
"campaign": {
"type": "object",
"additionalProperties": false,
"required": ["platform", "campaign_id", "name", "objective", "conversion_channel", "tracking_mode"],
"properties": {
"platform": { "type": "string", "enum": ["meta", "google", "tiktok"] },
"campaign_id": { "type": "string", "pattern": "^[A-Za-z0-9_.-]+$", "description": "Platform-native campaign ID, or a slug if the user has none at hand." },
"name": { "type": "string" },
"objective": { "type": "string", "enum": ["leads", "messages", "calls", "forms", "sales"] },
"conversion_channel": { "type": "string", "enum": ["whatsapp", "messenger", "instagram_dm", "form", "call", "landing", "pixel_purchase"] },
"tracking_mode": { "type": "string", "enum": ["offline", "pixel"], "description": "offline = the close happens outside the platform and needs user check-ins. pixel = the platform sees the sale (e-commerce); awareness is optional." },
"ticket_value": { "type": ["number", "null"], "minimum": 0, "description": "Average value of one closed customer. Used for estimated real ROAS when revenue is not reported." },
"currency": { "type": ["string", "null"] },
"started_at": { "type": ["string", "null"], "format": "date" }
}
},
"knowns": {
"type": "array",
"description": "Facts Claude holds about this campaign, each with its source.",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["fact", "source", "date"],
"properties": {
"fact": { "type": "string" },
"source": { "type": "string", "enum": ["audit", "user", "api", "mcp", "export"] },
"date": { "type": "string", "format": "date-time" }
}
}
},
"unknowns": {
"type": "array",
"description": "Open questions Claude must not assume an answer to (e.g. 'tasa de cierre', 'calidad de leads').",
"items": { "type": "string" },
"uniqueItems": true
},
"checkins": {
"type": "array",
"description": "Dated reports, oldest first. Append-only.",
"items": { "$ref": "#/definitions/checkin" }
},
"checkin_every_days": { "type": "integer", "minimum": 1, "default": 7 },
"next_checkin_at": { "type": ["string", "null"], "format": "date-time" },
"status": { "type": "string", "enum": ["active", "paused", "closed"] }
},
"definitions": {
"checkin": {
"type": "object",
"additionalProperties": false,
"required": ["date", "platform_metrics", "user_reported"],
"properties": {
"date": { "type": "string", "format": "date-time" },
"period_from": { "type": ["string", "null"], "format": "date" },
"period_to": { "type": ["string", "null"], "format": "date" },
"source_of_platform_metrics": { "type": ["string", "null"], "enum": [null, "mcp", "api", "export", "audit", "user"] },
"platform_metrics": {
"type": "object",
"additionalProperties": false,
"properties": {
"spend": { "type": ["number", "null"], "minimum": 0 },
"clicks": { "type": ["integer", "null"], "minimum": 0 },
"messages": { "type": ["integer", "null"], "minimum": 0, "description": "Conversations started / leads as counted by the platform." },
"leads": { "type": ["integer", "null"], "minimum": 0 }
}
},
"user_reported": {
"type": "object",
"additionalProperties": false,
"properties": {
"conversations": { "type": ["integer", "null"], "minimum": 0, "description": "Real conversations / contacts the user actually received." },
"qualified": { "type": ["integer", "null"], "minimum": 0 },
"closed": { "type": ["integer", "null"], "minimum": 0 },
"revenue": { "type": ["number", "null"], "minimum": 0 },
"junk": { "type": ["integer", "null"], "minimum": 0, "description": "Contacts the user considers garbage (spam, wrong audience, no reply)." },
"notes": { "type": ["string", "null"] }
}
}
}
}
}
}
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 |