Skip to content
Agentmart
Submit a tool

conversion-audit

Audit funnel friction — CTA clarity, trust, drop-off hypotheses — and produce smallest-change recommendations.

Skill by Alfred-Lau

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/alfred-lau-conversion-audit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Audit funnel friction — CTA clarity, trust, drop-off hypotheses — and produce smallest-change recommendations.

Use cases: security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/conversion-audit

What's inside

Skill name
conversion-audit
Description
Audit funnel friction — CTA clarity, trust, drop-off hypotheses — and produce smallest-change recommendations.
License
MIT
Instructions
34 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • checklist.md

SKILL.md (first lines)

# Conversion Audit

Find **why the primary success action isn't happening**. Output is a short audit + ordered bets — not a redesign.

## Process

### 1. Load

`BRIEF.md` (success action + metrics), `IA.md`, page-spec for the landing, `BRAND.md`, `TRACKING.md` / analytics notes, any `GROWTH.md` history. If success action is undefined, stop and run `/brief-site` first.

### 2. Walk the funnel

From land → understand → trust → act. Use [checklist.md](./checklist.md). Prefer evidence: screenshots, live click-through, analytics if available. Mark unknowns explicitly.

### 3. Hypotheses

Write 3–7 friction findings. Each:

| Field | |
| --- | --- |
| Friction | what's hard/confusing |
| Evidence | seen / measured / assumed |
| Bet | smallest change |
| Metric | how we'd know |

Sort by leverage × ease. Reject big-bang redesigns — those go to `/site-wayfinder` or `/visual-direction`, not this audit.

### 4. Write

Save `docs/site/audits/conversion-<date-or-slug>.md` (create `audits/`). Point the top bet at `/grow-loop` (or `/page-spec` → `/implement-ui` if the change is already crisp).

**Completion criterion:** success action restated; findings table complete; top bet is one change, not a bundle.

From Alfred-Lau/skills, MIT.

More from Alfred-Lau/skills

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 29, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Alfred-Lau/skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Alfred-Lau

Cite this page

conversion-audit skill. Agent Mart. https://agentmart.dev/skills/alfred-lau-conversion-audit (last updated 2026-10-24)