UI improvement audit: evidence-backed design reviews
Audit a product surface against its own design system with a contract-runtime-correction proof gate and self-contained fix plans — read-only on your source
- What
- Audit a product surface against its own design system with a contract-runtime-correction proof gate and self-contained fix plans — read-only on your source
- Cost
- Free
- Needs
- a product codebase to audit; the skill is read-only — it never modifies product source, it only writes plans under design-plans/
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @ibelick's read-only UI improvement audit: select one coherent product surface, reconstruct the design system that actually governs it (tokens, primitives, documented decisions), then prove every finding through a contract-runtime-correction gate — a binding design decision, proof the implementation reaches the surface, and one deterministic correction — with falsification passes that delete anything unsupported; reports stop at three findings and only turn user-selected findings into self-contained implementation plans under design-plans/. By @ibelick, listed here with credit to its creator. Honest caveats: strictly read-only on product source (never modifies it), writes plans only; no finding preferred over an unsupported one; discards accessibility/ARIA findings unless explicitly requested; MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
UI improvement audit is a free listing for Ibelick's read-only UI improvement audit. It reviews one coherent product surface against the design system that governs it. Every finding must pass a contract-runtime-correction proof gate: a binding design decision, proof it reaches the surface, and one deterministic correction. Reports stop at three findings, and only user-selected findings become self-contained implementation plans.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 587ea30Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a product codebase to audit; the skill is read-only — it never modifies product source, it only writes plans under design-plans/ Install "UI improvement audit: evidence-backed design reviews" for me. It teaches the agent to audit one product surface against its own design system, prove findings through a contract-runtime-correction gate, and write self-contained implementation plans for user-selected fixes — strictly read-only on your source. Repository: https://raw.githubusercontent.com/ibelick/ui-skills/587ea305b948ad34f0c2d5c2ea4211d428f66ed8/skills/improve-ui/SKILL.md Pinned version: install the code at commit 587ea305b948ad34f0c2d5c2ea4211d428f66ed8 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "improve-ui". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing to configure — point it at a product surface when invoking it). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 587ea30 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.