w-debug-browser — Claude Code skill for browser debugging
The w-debug-browser Claude Code skill reproduces and fixes authorized browser issues using runtime evidence. It inspects DOM, network, and console data, then replays the interaction after a fix.
MIT 647 installs ★ 1 updated 2026-10-02
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a claude-codeWhat w-debug-browser does
The skill reproduces a browser issue, gathers DOM, network, and console evidence, traces the failure to a client or server boundary, and makes the smallest authorized change. It first reads the project README and its browser-testing conventions.
After the change, it replays the same interaction, checks relevant failure and empty states, runs affected automated checks, and removes temporary traces. If behavior or commands change, it uses /w-docs. Browser tools are needed for reproduction; when tools or credentials block the check, the skill reports the specific limitation instead of repeating attempts without new evidence.
What it helps with
- reproduce a browser failure and collect DOM, network, and console evidence
- trace a fault to its client or server boundary
- apply an authorized fix and replay the original interaction
- check related failure and empty states
Example prompts for the agent
- Reproduce this authorized browser issue from the affected URL and find its cause.
- Fix the form submission failure and replay the same interaction.
- Check the empty state and run the affected automated tests.
How to install w-debug-browser
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a claude-code2Manually: put the files in place
~/.claude/skills/w-debug-browser/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/w-debug-browser/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a codex2Manually: put the files in place
.agents/skills/w-debug-browser/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a cursor2Manually: put the files in place
.cursor/skills/w-debug-browser/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install blockmatic-icebox/basilic-skills skills/workflow/w-debug-browser2Manually: put the files in place
.github/skills/w-debug-browser/SKILL.md1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a gemini-cli2Platform CLI
gemini skills install https://github.com/blockmatic-icebox/basilic-skills --path skills/workflow/w-debug-browserManually: put the files in place
.devin/skills/w-debug-browser/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -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 w-debug-browser
How do I install w-debug-browser in Claude Code?
Run npx skills add blockmatic-icebox/basilic-skills --skill w-debug-browser -a claude-code. The skill file is at ~/.claude/skills/w-debug-browser/SKILL.md.
What does w-debug-browser do?
It reproduces browser problems, examines DOM, network, and console evidence, then fixes the fault and retests the interaction.
What does w-debug-browser need to run?
It needs available browser tools and any credentials required for reproduction. If either blocks the check, the skill reports the specific limitation.
Source text
SKILL.md · MIT
--- name: w-debug-browser description: Reproduce and resolve an authorized browser issue using runtime evidence. disable-model-invocation: true --- Use the affected URL, expected interaction, and available browser tools. Inspect the app's README and browser-testing conventions first. 1. Reproduce the interaction and collect relevant DOM, network, and console evidence before adding instrumentation. 2. Trace the failure to its owning client or server boundary. Use the repository logger for necessary temporary traces; avoid secrets in captured output. 3. Apply the smallest authorized fix, then replay the same interaction and relevant failure or empty states. 4. Run affected automated checks and remove temporary traces introduced here. Distinguish runtime evidence from automated results. If tools or credentials block reproduction, report the exact limitation rather than looping without new evidence. 5. Docs: `/w-docs` if behavior or commands changed.
© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills