Landing Page Copy Audit
Score landing page copy on clarity, CTA strength, and conversion fundamentals — deliver a prioritized rewrite plan in one pass.
🧠 Why it works
Landing page copy is governed by a small, knowable rubric. Once the criteria are pinned down — clarity, specificity, urgency, CTA strength, weasel-word density — an LLM with strict scoring instructions will outperform a casual human review because it is forced to commit to a number per criterion rather than hedge. The numeric scores turn the rewrite into a targeted patch, not a generic "punch this up" pass.
The audit is also reproducible: the same input produces the same scores, so you can iterate on a draft and see the score move.
⚙️ How it works
Prompt
``` You are a conversion copywriter. Audit the landing page copy below against this rubric. Score each criterion 1–5 with one reason. Then rewrite any line scoring below 4.
Rubric:
- Value-prop clarity — does the visitor understand what they get in 5 seconds?
- Audience specificity — is the target persona unambiguous?
- Urgency — is there a concrete reason to act now (not manufactured)?
- CTA verb strength — is the button verb specific and direct?
- Weasel density — count hedges ("maybe", "could", "helps you") per 100 words. Lower is better.
Output JSON: { "scores": {"clarity": n, "specificity": n, "urgency": n, "cta_verb": n, "weasel_density": n}, "rewrites": [{"original": "...", "rewrite": "..."}], "biggest_miss": "one sentence" }
Copy: <paste your hero, subhead, feature bullets, CTA> ```
Tips
- Run it three times with different model seeds if you can; average the scores.
- Do not ask the model to rewrite anything scoring 4+ — the marginal gain isn't worth introducing noise.
- Pair this with a second pass using Editorial Style Matcher once you have the rewrites, to keep voice consistent.
Description
Paste a landing page hero, subhead, feature bullets, and primary CTA. The skill scores each line on a five-criterion rubric (value-prop clarity, audience specificity, urgency, CTA action verb, weasel-word count) and returns a rewrite of anything below threshold.
Install this skill
A Claude skill is a skill.md file with YAML frontmatter and a markdown body.
Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.
mkdir -p ~/.claude/skills/landing-page-copy-audit \
&& curl -L https://aidiveforge.com/skill/landing-page-copy-audit.skill-md \
-o ~/.claude/skills/landing-page-copy-audit/skill.md
Save to ~/.claude/skills/landing-page-copy-audit/skill.md
Recommended Use
Sign in to suggestTools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.
Forge Auto-recommended matches
Tools
-
Beautiful.ai post 37%
Why: category partial · caps 0/0 · domain design · io-match
-
IvyCraft post 32%
Why: category partial · caps 0/0 · domain design
-
Presentforme.ai post 32%
Why: category partial · caps 0/0 · domain design
-
Quiver post 32%
Why: category partial · caps 0/0 · domain design
-
AIdea post 32%
Why: category partial · caps 0/0 · domain design
-
Framer post 32%
Why: category partial · caps 0/0 · domain design
-
Midjourney post 30%
Why: caps 0/0 · domain design · io-match
-
DALL-E 3 post 30%
Why: caps 0/0 · domain design · io-match
-
Stable Diffusion post 30%
Why: caps 0/0 · domain design · io-match
-
Leonardo AI post 30%
Why: caps 0/0 · domain design · io-match
-
Ideogram post 30%
Why: caps 0/0 · domain design · io-match
-
Flux post 30%
Why: caps 0/0 · domain design · io-match
Report compatibility
Tell the community which tool you used this skill with, and whether it worked.
Suggest a pairing
Recommend a tool or workflow pack that this skill works well with. Up to 5 recommendations per day.