Index of every page on this site: llms.txt
All skills
wshobson avatar

/visual-edit-precision

@4220308
by Seth Hobsonwshobson/agents43k stars
4,518
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/wshobson/agents/visual-edit-precision

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈82 tokens for metadata: the name and description. ≈455 when used: this file.

Description uses 4.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈330 characters, or 4.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    This skill provides instructions for AI agents to perform precise UI edits based on visual context such as screenshots or annotations. It emphasizes targeted modifications and code preservation. No security issues were detected.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at 4220308. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 5 months ago

README badge

README badge for wshobson/agents/visual-edit-precision