biznomad/agent-skills/ads-compliance-check

Claude Code and agent skill by biznomad/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Pre-flight gate that blocks ad publish until brand-compliance, Meta 72-hour blackout, and platform policy red-flag checks pass. Triggers on "compliance check", "ads compliance", "compliance gate", "blackout check", "creative QA", "pre-flight ad check", "can I push this ad", "is it safe to launch", "check ad before publish", "verify ad creative", "ad QA gate".

Install

npx vskill@latest install biznomad/agent-skills/ads-compliance-check

SKILL.md

The same SKILL.md was published earlier as biznomad/agent-skills/ads-compliance-check.

/ads-compliance-check

A pre-flight gate that blocks ad publishing until three categories of checks pass:

(A) Brand-Compliance

Per memory feedback files:

  • feedback_hv_brand_compliance.md — Mason jar specs, gel colors, banned medical language, 36-grid naming
  • feedback_ad_creative_rules.md — logo must be real composite, no AI-generated brand text in video
  • feedback_image_quality.md — no generic Canva-level images, one-at-a-time approval gate
  • feedback_hv_copy_minerals.md — "90+ minerals" not "92 of 102"
  • feedback_product_reference_images.md — real product photos as ingredients, no sample jars, blur competitor logos

(B) Meta 72-Hour Blackout

Per feedback_meta_ads_72h_blackout.md:

  • Zero edits within 72h of any prior change
  • Max 20% single budget adjustment
  • New campaigns frozen 3 full days post-launch
  • Exception: ROAS < 0.5x AND spend > 2x daily target → emergency pause only

(C) Per-Platform Policy Red-Flags

  • Meta: health claims, before/after, "cure/treat/prevent/diagnose"
  • Google: YMYL (Your-Money-Your-Life) restrictions, financial-product guarantees
  • TikTok: medical/health claim restrictions, weight loss language

How to invoke

bash
python ~/.Codex/skills/ads-compliance-check/compliance-check.py [path/to/ads-manifest.json]

Default manifest path: ./ads-manifest.json

Exit codes

  • 0 — All checks PASS, safe to publish
  • 1 — One or more FAIL, do NOT publish; see fix list
  • 2 — Manifest invalid / missing

State file

Tracks last-change timestamps per {platform}:{account_id}:{campaign_id} at: ~/.Codex/skills/ads-compliance-check/.state/last-changes.json

After a successful publish, callers should update this file (or pass --record flag) so the next 72h blackout check works.

Reading order for the agent

  1. Read manifest file (path from $1 or default).
  2. Run compliance-check.py end-to-end; do not skip any check.
  3. Print structured report; DO NOT auto-fix unless explicitly asked.
  4. If FAIL, surface the fix list verbatim to the user before any publish attempt.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/biznomad/agent-skills/ads-compliance-check/badge)](https://verified-skill.com/skills/biznomad/agent-skills/ads-compliance-check)

Something wrong with this skill or its page? Tell us.