match — Claude Code skill: interface comparison
The match Claude Code skill rebuilds a named interface part from its source and compares the result with the reference. It activates when a request points to an app, URL, screenshot, or design file.
MIT 175 installs ★ 69 updated 2026-11-14
npx skills add raphaelsalaja/skills --skill match -a claude-codeWhat match does
match inspects the actual screen or design file, reads its measured styles, and lists the states the reference supports. It then recreates only the requested part, such as a sidebar, and checks it against the reference at the same size and state. Branding stays out unless the request asks for it.
The skill copies compare.html into the ignored folder .match/<part>/, writes compare.js beside it, and places captures in img/. Each value is marked Match, Differs, or Not Verified; findings are reported with severity. Writing separate markup or styles for the comparison page breaks the skill's rule.
What it helps with
- recreate a named interface part from a screenshot or app
- read dimensions, spacing, and colours from a design
- list an element's states and transitions
- compare an implementation with its reference and record differences
Example prompts for the agent
- Recreate the sidebar from this screenshot and include its states.
- Compare this page with the open app at the same window size.
- Match this design exactly and list every difference from the source.
How to install match
1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill match -a claude-code2Manually: put the files in place
~/.claude/skills/match/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/match/
1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill match -a codex2Manually: put the files in place
.agents/skills/match/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill match -a cursor2Manually: put the files in place
.cursor/skills/match/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install raphaelsalaja/skills skills/match2Manually: put the files in place
.github/skills/match/SKILL.md1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill match -a gemini-cli2Platform CLI
gemini skills install https://github.com/raphaelsalaja/skills --path skills/matchManually: put the files in place
.devin/skills/match/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill match -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about match
How do I install match in Claude Code?
Run npx skills add raphaelsalaja/skills --skill match -a claude-code. The skill file is at ~/.claude/skills/match/SKILL.md.
What does match do?
It inspects a real interface and its measured values, rebuilds the requested part, then compares the result with the reference. Differences appear in a severity-based report.
How does match handle an exact-match request versus an inspiration request?
For an exact match, values come from the reference and guesses are flagged. For an inspiration request, the concept carries over while the project’s own tokens supply the styling.
Source text
SKILL.md · MIT
--- name: match description: Rebuilds a named reference from its real source and computed values, then compares the two side by side. --- # Match This skill rebuilds something the user pointed at in another app, site or design. It works from the real source and its measured values, not from memory of how it looks. ## One to one means exact values When the user says "one to one", "exact" or "like this", every value comes from the reference. A guessed value is a finding. When the user says "inspired by", carry the concept and use the project's own tokens. Use it whenever a message names an app, a URL, a screenshot, a design file or a design reference library. Building with the project's parts belongs to `reuse`. Checking the result runs in `verify`. ## 1. Open the real source Open the reference itself: the live page, the installed app, the design file or the screenshot. Rebuilding from memory is `match-inspect-the-source`. When the reference is a native or desktop app, look at that app, not its website. Judging a desktop app by its marketing page is `match-same-platform`. ## 2. Read the values Read computed styles, design tokens or measurements from the source. Write down sizes, spacing, radius, colours, type, durations and easing. A radius chosen by eye is `match-read-computed-values`. ## 3. Inventory the states List every state the reference has: hover, pressed, focus, open, empty, loading, error, selected and disabled. Then list its transitions. Rebuilding the resting state alone is `match-inventory-states`. ## 4. Copy the named part Rebuild the part the user named and nothing around it. Asked for the sidebar, copying the whole layout is `match-copy-the-named-part`. Carry the idea, not the brand. Their logo, product names and colours stay behind unless the user asked for them. That is `match-concept-not-brand`. ## 5. Compare side by side Put the reference and the rebuild next to each other at the same size and in the same state. Name every difference left. "Looks close" with no comparison is `match-side-by-side`. Capture both in every state from step 3 at one size and one device scale factor. Copy [compare.html](compare.html) to `.match/<part>/index.html`, an ignored folder and never the source tree. Write `compare.js` beside it in the shape its header comment shows, with captures in `img/`, then open it. The compare page ships with the skill, so write data only. A page with its own markup or styles is `match-shipped-compare`. Mark each value Match, Differs or Not Verified. The user sends what is left back with Copy Differences. ## The pair Every check is a pair. The broken line sits beside the line that replaces it. | Rule | Broken | Replacement | | --- | --- | --- | | `match-inspect-the-source` | A menu rebuilt from memory | The live menu opened and inspected | | `match-same-platform` | A desktop app judged by its website | The installed app opened | | `match-read-computed-values` | `border-radius: 8px` by eye | The `6px` read from computed styles | | `match-inventory-states` | The resting state only | Hover, pressed, open, empty and error rebuilt | | `match-copy-the-named-part` | The whole layout copied for "the sidebar" | The sidebar only | | `match-concept-not-brand` | Their logo and accent colour shipped | The pattern in the project's tokens | | `match-side-by-side` | "Looks close" | Both at one size, differences listed | | `match-shipped-compare` | A compare page written from scratch | `compare.html` copied, only `compare.js` written | ## Reporting **Severity.** `HIGH` is a rebuild made without opening the source, or a missing state the user named. `MEDIUM` is a guessed value under "one to one", a part copied beyond the ask or a hand-written compare page. `LOW` is a remaining difference that was found and named. **Format.** One finding per root cause: ``` file:line - [rule-id] what is wrong ``` Then a `Rule | Count | Severity` summary. `Block` when any `HIGH` remains, `Approve` otherwise. Mark every value you could not read from the source as `Not verified`.
© raphaelsalaja · MIT · raphaelsalaja/skills