visual-edit-precision — Claude Code skill: UI edits from screenshots
Skill for targeted UI changes when you show elements on a screenshot or point them out in code. Edits only what you selected, without refactoring the entire component.
/plugin marketplace add wshobson/agents
/plugin install skill-forge-essentials@claude-code-workflowsWhat visual-edit-precision does
visual-edit-precision helps with frontend changes guided by how they look. Show a screenshot with a highlighted button, icon, or field — the agent finds the exact element in code and changes only its styles or markup. Everything else stays put.
The skill follows a minimalist principle: if you point at one card, it won't rewrite the whole component or touch global styles. It checks that changes render without side effects and preserves accessibility — aria attributes, role, tabindex remain untouched.
Use it when spatial context matters — you reference elements by position, size, or neighbors rather than class name alone. Helps avoid conflicts when multiple edits touch different elements in one component.
What it helps with
- change one button's style without affecting others
- edit a card from a screenshot without refactoring the component
- apply several visual edits to different elements at once
- preserve accessibility and event handlers during markup changes
Example prompts for the agent
- Change this icon color to green (here's a screenshot)
- The input field looks too narrow in the screenshot. Make it twice as wide
- Add left padding to the paragraph inside this modal (see the screenshot)
How to install visual-edit-precision
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install skill-forge-essentials@claude-code-workflowsThis installs the whole skill-forge-essentials plugin with all its skills
2Skills CLI (Vercel)
npx skills add wshobson/agents --skill visual-edit-precision -a claude-code3Manually: put the files in place
~/.claude/skills/visual-edit-precision/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/visual-edit-precision/
1Skills CLI (Vercel)
npx skills add wshobson/agents --skill visual-edit-precision -a codex2Manually: put the files in place
.agents/skills/visual-edit-precision/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wshobson/agents --skill visual-edit-precision -a cursor2Manually: put the files in place
.cursor/skills/visual-edit-precision/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wshobson/agents visual-edit-precision2Manually: put the files in place
.github/skills/visual-edit-precision/SKILL.mdPlatform CLI
gemini skills install https://github.com/wshobson/agents --path plugins/skill-forge-essentials/skills/visual-edit-precisionManually: put the files in place
.devin/skills/visual-edit-precision/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set213
The whole set →Similar
Questions about visual-edit-precision
How do I install visual-edit-precision in Claude Code?
Run /plugin marketplace add wshobson/agents, then /plugin install skill-forge-essentials@claude-code-workflows. Alternatively, run npx skills add wshobson/agents --skill visual-edit-precision -a claude-code or copy ~/.claude/skills/visual-edit-precision/SKILL.md manually.
What does visual-edit-precision do?
It lets you direct the agent via screenshots and visual element selection. The agent finds the element in code, makes a minimal change, and leaves everything else alone. Useful when describing what you want in text is harder than pointing at it.
Will it work if I show a Figma screenshot?
Yes, if the screenshot helps pinpoint an element in your actual codebase. If it's a design mockup that doesn't exist in the project yet, the agent can suggest markup but won't edit existing files.
Source text
SKILL.md · MIT
--- name: visual-edit-precision description: >- Use when making UI/frontend changes guided by visual context, when the user selects elements visually, draws annotations, or provides screenshots alongside change requests. Also use when editing components where spatial context (element identity, DOM references, layout data) supplements text instructions. --- # Visual Edit Precision ## Overview When visual context accompanies a change request (element selections, annotations, screenshots), make targeted, minimal edits. Precision over ambition: change exactly what was indicated, preserve everything else. ## Process When visual context is provided: 1. **IDENTIFY** - What exact element(s) were indicated? Which component file owns them? 2. **SCOPE** - Change ONLY what was pointed at. Don't refactor surrounding code. 3. **PRESERVE** - Keep existing styles, classes, and behavior. Only modify what was asked. 4. **TARGETED** - Make the minimal CSS/markup change that achieves the visual result. 5. **VERIFY** - Confirm the change renders correctly without side effects. ## Key Principles ### Precision Over Ambition Visual context gives a SPECIFIC element. Don't: - Refactor the entire component when only one style was requested - Change the component's API when only its appearance was pointed at - Touch logic when only visuals were selected Do: - Find the exact file and line for the selected element - Make the minimal edit that achieves the described visual change - Preserve all existing behavior, event handlers, accessibility ### Multiple Edits When multiple visual edits arrive: - Each targets its own element independently - Don't wait for one to finish before processing another - If two edits conflict (same element, different requests), handle the most recent ## Common Mistakes - Rewriting an entire component when the user pointed at one button - Changing global config when only one element's color needs adjusting - Breaking responsive behavior by adding fixed widths to match a selection - Ignoring specificity (user indicated ONE card, agent changed ALL cards) - Removing accessibility attributes (aria-*, role, tabindex) during visual edits
© Adit Jain · MIT · wshobson/agents