Skip to content
Get packs

Agent QA Debug Fix

Diagnose and minimally repair failed Agent QA test runs using run evidence and local code, then re-verify.

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
1 file

What it does

When an automated end-to-end test run fails, this skill tells the agent how to work like a careful QA engineer: pull the run's recorded steps, artifacts, and logs through Agent QA's tools, treat the automatic failure label as a hypothesis, read the relevant local test and application code, and make the smallest change that fixes the evidenced cause. It then validates the edited test definition and reruns only the narrowest affected test. It is designed to avoid simply weakening a test to hide a real product bug.

Great for

  • Developers maintaining Agent QA test suites who need to fix a specific failed run
  • QA engineers who want a disciplined, evidence-first repair process for flaky or broken automated tests
  • Teams using Agent QA's MCP tools who want the agent to follow a documented approval and verification workflow

Skip it if

  • Teams without access to Agent QA run data or the local source repository, since the workflow depends on both; the agent would be guessing
  • Changes touching production or destructive actions: the skill requires explicit confirmation for these, but a careless user could still approve something risky
  • Projects not using the Agent QA platform, where the MCP tools it names do not exist

Try asking

  • “Fix the failed staging checkout run, but do not touch production.”
  • “Why did last night's login test fail? Pull the run evidence and patch the test if it's stale.”
  • “Self-heal the outdated Agent QA YAML definition for the signup suite using the latest failure artifacts.”
  • “Validate my edited test definition and rerun just that single test.”
Step-by-step guide: how to use Agent QA Debug FixInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    agent-qa-debug-fix.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip agent-qa-debug-fix.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip agent-qa-debug-fix.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Specify the repository, environment (for example staging, not production), and files the agent may modify before starting.
  • Review the root cause and changed-files report before accepting a fix, especially if the failure could be a real product defect.
  • Ask for the explanation of the evidence-to-change link so you can judge whether the patch addresses the cause rather than hiding it.

What's inside

  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.