Skip to content
SkillModel-led171 tokens in use

Ad Creative Audit

Audits paid ad copy, images and video for concept diversity, format fit, fatigue, accessibility and policy, and returns refresh briefs to test.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-creative
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Ad Creative Audit costs

66tokens idle
171tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure11/25
  • Examples0/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

The creative audit skill inventories ad assets by concept, hook, offer, format, placement, audience, date and performance window, then evaluates attention, clarity, offer evidence, platform-native execution, accessibility, destination match, safe zones and disclosure.

Fatigue is diagnosed only from time-series delivery and response evidence, never from age alone. Creative quality, format compliance and measured performance are reported separately.

What You Get

  • An asset inventory by concept, hook, offer, format and placement
  • Findings on clarity, accessibility, safe zones, destination match and disclosure
  • A fatigue diagnosis based on time-series data
  • Refresh or experiment briefs with hypothesis and success measure

Common Use Cases

  • Checking whether a set of ads is really diverse or only resized copies
  • Diagnosing creative fatigue on a Meta or TikTok account
  • Reviewing video and image ads for platform-native fit
  • Planning the next round of creative tests

What Makes It Unique

It treats cosmetic resizes as one concept and refuses universal rules for refresh cadence, creative count, sound behavior or performance thresholds. Emotional and cultural judgment stays with a human reviewer.

Under The Hood

This is a prompt-only skill with no scripts. The agent reads the creative and policy references for the active platforms and works from the assets, exports and screenshots you supply. It runs no commands, makes no account changes and writes its output through the common Claude Ads contracts.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers