loading
loading
Score a batch of ad variants on angle, clarity, proof, and risk — and suggest distinct next angles.
Stops a batch of ad variants from being ten takes on one weak angle — scores each on proof and risk, then pushes distinct next angles.
Listed for review
No verified public repo for this skill yet, so this page does not give you an install command. Skills with a verified source install in one command — or fully manual: copy the skill folder into .claude/skills/ and your agent picks it up.
Boostor Quality Score
84/100 · B
Ad Creative Variant Judge reviews a set of AI-generated ad variants against your offer, audience, and platform rules, then returns a scored review per variant: angle, audience fit, clarity, proof, and compliance risk, plus prompts for distinct next angles. It exists because variants are usually judged by taste alone and tend to repeat one weak angle — this flags claims that need substantiation and pushes toward genuinely different angle families.
Pull AI copy back to brand voice, flag banned phrases, and mark any claim that still needs proof.
Fixes voice without flattening you into generic SaaS copy — it preserves the specifics and flags the claims that still need proof.
Transparent + deterministic: every point above is computed from this skill's real fields plus a prompt-injection safety scan. No black box, no pay-to-rank.
Generate human-readable changelogs from git history and PR descriptions.
Turns git log into a changelog a human would actually read, grouped by feature, fix, and breaking change — the release chore most teams skip until launch day.
Rank decaying pages by stale claims, intent drift, and broken links — and say refresh vs rewrite vs delete.
Ranks decaying pages by real evidence and tells you refresh vs rewrite vs delete — not just bumping the date and calling it updated.