critique
Grade a rendered ad's visual design against the rubric and fix what's weak
Install / Use
npx skills add steverzag/ad-creatorInstalls into whichever agent you are using.
Claude Commands
Claude Code slash commands
Quality Score
Category
MarketingSupported Platforms
Skill content
View source on GitHubdescription: Grade a rendered ad's visual design against the rubric and fix what's weak argument-hint: [ad slug, optionally "review only" to skip the fixes]
Run a design pass. Target: $ARGUMENTS — if empty, use the ad this
conversation has been working on, or the only folder in ads/.
Invoke the critique-ad skill and follow it. It owns the rubric, the
thumbnail test, and where each class of fix belongs; don't restate any of that
here.
Two things this command settles before the skill starts:
The input is pixels, never source. Render first, or grab frames for motion. If you haven't looked at the image, you haven't reviewed the ad.
Scope. This grades and fixes design — layout, hierarchy, type, colour, space, thumbnail legibility. It does not rewrite the offer, the angle, or the CTA target; flag those and let the user decide. Copy is fair game only where length is a layout problem, and cutting words always beats shrinking type.
If the argument says "review only", score and report without editing.
Distinct from /verify, which asks whether the ad rendered correctly. This one
asks whether it's any good. An ad can pass /verify completely and still fail
here at thumbnail size.
Related Skills
momen-cursurrules-prompt-file
40.6kCursor rules for building custom frontends with Momen.app as headless BaaS with GraphQL API, actionflows, AI agents, and Stripe integration.
pyspark-etl-best-practices-cursorrules-prompt-file
40.6kCursor rules for PySpark ETL development with code style, joins, window functions, map operations, and Iceberg patterns.
semiotic-react-dataviz-cursorrules-prompt-file
40.6kCursor rules for Semiotic data visualization library with 30+ chart types, MCP server, and AI-assisted chart generation.
claude-mem
90.9kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Security Score
Audited on Invalid Date
