improve-website
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging, high-perf-browser, made-to-stick, design-everyday-things - asking the user questions at every decision point and recording results in the project docs/ folder (WEBSITE.md, DESIGN.md, EXPERIMENTS.md, IMPROVE-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user w
npx skills add wondelai/skills --skill improve-website --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides a user through an eight-phase, interactive journey to transform a underperforming live website into a ranked backlog of defensible fixes. It orchestrates eight skills phase by phase: cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging, high-perf-browser, made-to-stick, design-everyday-things, and records decisions and results in project docs (WEBSITE.md, DESIGN.md, EXPERIMENTS.md, IMPROVE-WEBSITE-PLAN.md). It asks questions at decision points and resumes across sessions by storing state in docs.
How it works
- Phase sequence and orchestration: It sequences Phases 1 through 8, each with a defined purpose, brief, required Invoke command, and decision points.
- Invocations: Each phase uses a specific slug (e.g., cro-methodology, ux-heuristics, refactoring-ui, etc.) to run the corresponding skill. If a phase’s skill is not available, it can fall back to a minimal viable method or instruct the user to install via a command like
npx skills add wondelai/skills/<slug> --global. - Decision points: At each phase, it asks concrete decisions (which issues to fix now, whether to proceed, skip, or defer) and records them in the tracker under Key Decisions.
- Artifacts and documentation: Phases extend or create docs/ files (WEBSITE.md, DESIGN.md, METRICS.md, EXPERIMENTS.md, POSITIONING.md) by adding sections or fixes as per artifact templates; every recommendation lands as a checkbox or table row with owner and priority.
- Intake and plan: On first run, it performs Intake, creates docs/IMPROVE-WEBSITE-PLAN.md with phase statuses, and requires user confirmation to proceed.
- Output: Each phase concludes by drafting artifact content for sign-off, then updating the tracker and docs when approved.
When to use it
Use when you want to fix a landing page that isn’t converting, diagnose why visitors leave, audit for clarity and usability, or address a homepage that feels off after a redesign.
What it can touch
- Invoked phases via their slug (e.g., cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging, high-perf-browser, made-to-stick, design-everyday-things).
- Outputs are written to docs/ with uppercase section files (WEBSITE.md, DESIGN.md, EXPERIMENTS.md, IMPROVE-WEBSITE-PLAN.md).
Caveats
- Requires real site context and evidence to feed diagnoses (Phase 1 findings). It does not ship changes without Phase 1 evidence.
- Phases may be deferred or skipped based on gates or plan; Phase 1 cannot be skipped.
- It relies on the CLAUDE-CODE tool for phase execution; availability may affect execution mode.
# Improve a Website An interactive, resumable journey that turns a live-but-underperforming website into a ranked backlog of defensible fixes. Across eight phases it diagnoses why visitors don't convert, then fixes usability, hierarchy, typography, message, speed, memory, and errors — asking you at each decision point and recording results in `docs/`. Each change is tied to a reason; the big ones ship as tests. ## Core Principle **Diagnose, fix, prove: evidence from real visitors decides what changes, and every fix ships as a testable hypothesis.** Order is deliberate — research first, then usability, look, message, speed, memory, and error-tolerance, because each phase's output feeds the next. This skill sequences the phases, asks the decision questions, and records what you decide. The constituent skills carry the method — invoke them rather than improvising their frameworks. ## Journey Map | Phase | Skill | Question it answers | Artifact | |---|---|---|---| | 1 | cro-methodology | Why don't visitors convert, and which fix moves the most money? | Extends docs/METRICS.md, docs/WEBSITE.md, docs/EXPERIMENTS.md — GATE | | 2 | ux-heuristics | Where do visitors stumble before they weig
- Core Principle
- Journey Map
- Operating Rules
- Intake
- Phases
- Phase 1 — Diagnose why visitors don't convert (cro-methodology) — GATE
- Phase 2 — Remove the usability friction (ux-heuristics)
- Phase 3 — Fix the visual hierarchy (refactoring-ui)
- Phase 4 — Make the words readable (web-typography)
- Phase 5 — Sharpen the message (storybrand-messaging)
- Phase 6 — Make the page fast (high-perf-browser)
- Phase 7 — Make the core idea stick (made-to-stick)
- Phase 8 — Design out the errors (design-everyday-things)
- Optional Phases
What does the improve-website skill do?
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging, high-perf-browser, made-to-stick, design-everyday-things - asking the user questions at every decision point and recording results in the project docs/ folder (WEBSITE.md, DESIGN.md, EXPERIMENTS.md, IMPROVE-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user w
How do I install it?
Run `npx skills add wondelai/skills --skill improve-website --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wondelai/skills, a repository with 1,835 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.