BuilderIO/agent-native / .agents/skills/design-editor-repro
design-editor-repro
VerifiedReproduce and verify Design editor issues against the application itself.
Reproduce Design editor issues
Use this skill for defects that need a real Design editor session. Work from a local or production copy of an Agent-Native design and describe the observed application behavior directly.
Setup
- Start the worktree's Design app with .agents/skills/design-editor-repro/harness/start-dev.sh.
- Run node .agents/skills/design-editor-repro/harness/doctor.mjs until the local app and editor session are ready.
- Copy a source design with node .agents/skills/design-editor-repro/scripts/copy-design.mjs . Use a production copy only when DESIGN_TEST_EMAIL and DESIGN_TEST_PASSWORD are configured. Remove that copy when finished.
- Reproduce the reported steps before changing application code. Save only task-relevant files under templates/design/.tmp/editor-repro/.
Investigation
- Use the helpers in harness/dlib.mjs to open the editor, select layers, inspect fields, trigger actions, and read persisted files.
- Prefer Playwright input through the app page. Use the OS input helper only when browser input cannot exercise the reported path.
- Capture screenshots with harness/shot.mjs when visual evidence will help explain the application state. The helper returns local paths for inspection.
- Check the relevant implementation and neighboring tests before changing code. Keep fixes at the application boundary and add a regression test where the existing suite supports it.
- Keep diagnostic data local to the task. Do not commit screenshots, copied user designs, session data, credentials, or temporary exports.
Verification
- Reproduce the original steps on the changed build.
- Run the narrowest relevant unit or browser tests, then the required Design interaction lane when the change affects canvas behavior.
- Inspect the rendered application when the fix changes visible behavior.
- Close the editor page and delete any temporary production copy before reporting completion.
For details, see harness-recipes.md, reference/input-and-osmouse.md, reference/fixing.md, reference/tests-and-blast-radius.md, and reference/performance.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |