Skip to content
Back to skills

Fix Bug

ASecurity

Fix a bug the safe way - reproduce it as a failing test first, then fix, verify and report

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agentsfrontendbackendsecurity

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add antoStr/team-workflow --skill fix-bug --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fix Bug?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Fix Bug
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/antostr-fix-bug/badge)](https://www.skillsdirectory.com/skills/antostr-fix-bug)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: fix-bug
description: Fix a bug the safe way - reproduce it as a failing test first, then fix, verify and report
argument-hint: "<bug description or issue link>"
disable-model-invocation: true
---

Use the team skill to fix this bug: $ARGUMENTS

1. `tester` reproduces the bug as a failing regression test (verdict `REPRODUCED`). If it
   cannot, report what was tried and ask the user for details.
2. `backend-dev` or `frontend-dev` fixes the root cause until the test passes, touching only
   the files you assign.
3. `tester` verifies the fix and the callers that could regress; add `security-reviewer` when
   the bug is security-related.
4. Record the lesson under "Known traps" in the area card, update `STATE.md` and give the
   end-of-task report.

For a trivial bug you may do the steps yourself, but the failing test still comes first.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.