Install
$ agentstack add skill-cbrock84-headcount-landing-page-cro-expert ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Landing page CRO
Diagnose before rewriting
A page converts when a visitor understands what this is, believes it will work for them, and has no unresolved objection at the moment they are asked to act. Failures are almost always one of those three, and the remedy differs entirely.
Read the page as a stranger who has five seconds. Then answer:
- What is this, in the reader's words? If the hero requires domain knowledge to parse, nothing
below it matters.
- Who is it for? A page for everyone converts nobody. Specificity is a conversion tactic, not a
marketing luxury.
- Why this instead of the alternative — including doing nothing, which is the real competitor.
- What is the single action? Multiple competing calls to action reliably reduce all of them.
The hero
Most of the outcome, decided in the space of a phone screen.
- Headline states the outcome, not the category and not a slogan. "Close your books in two days,
not two weeks" beats "Modern accounting infrastructure."
- Subhead handles the obvious next question — usually how, or for whom.
- One primary call to action, above the fold, with a label describing what happens next rather
than "Submit" or "Get started."
- Proof in the first screen. A logo row, a number, a named customer. Claims made with no
evidence in sight are discounted wholesale.
- Show the product. A screenshot of the real thing outperforms an abstract illustration for
almost every software product.
Down the page
Order by the reader's questions, not by your feature list: what it does → why it is better than what they do now → proof → objections → price → act.
Every claim needs evidence near it. Every section should be removable — if cutting it changes nothing, cut it. Long pages are fine; padded pages are not.
Repeat the call to action at each natural decision point, always the same action.
Objections
List the real reasons people do not buy — cost, switching effort, trust, whether it works for their case, who else uses it — and answer each on the page. Objections not handled on the page are handled by leaving.
The strongest objection handling is specific: a migration guide, a named customer like them, a concrete guarantee.
Prioritizing tests
Rank by traffic × expected effect × confidence, and test structural things before cosmetic ones. Headline, offer framing, page order, and form length move conversion. Button color does not, and testing it consumes the traffic a real test needed.
Most pages cannot support many adequately powered tests. Spend them on the hero and the offer.
Scoring a page
Where a score is useful, rate each of these one to five with the criteria stated: clarity of what it is, specificity of who it is for, strength of the primary action, proof present and near claims, objections handled, and visual hierarchy supporting the path.
Publish the criteria with the score. A page scored 6/10 with no rubric produces an argument; the same score with the rubric produces a work list.
Return contract
Findings ordered by expected impact, each with the evidence, the specific fix, and effort. The one change to make first. And what you would leave alone — a CRO audit that flags everything has prioritized nothing.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cbrock84
- Source: cbrock84/headcount
- License: MIT
- Homepage: https://cbrock84.github.io/headcount/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.