---
name: Agent Qa Debug Fix
slug: agent-qa-debug-fix
category: Quality
description: Agent Qa Debug Fix uses MCP evidence, logs, artifacts, and local code changes to diagnose a failed agent-qa run and patch the root cause. Use it after a run fails and you need to verify the fix with the narrowest relevant test or hook.
github: "https://github.com/vostride/agent-qa/tree/main/skills/agent-qa-debug-fix"
language: TypeScript
stars: 934
forks: 15
install: "npx degit https://github.com/vostride/agent-qa/tree/main/skills/agent-qa-debug-fix ~/.claude/skills/agent-qa-debug-fix"
installs_to: ~/.claude/skills/agent-qa-debug-fix
source_path: skills/agent-qa-debug-fix/SKILL.md
collection_size: 3
category_size: 1354
collection_url: "https://dirskills.com/collections/vostride/agent-qa"
added: 2026-08-22T05:20:21.065Z
last_synced: 2026-08-22T05:20:21.065Z
canonical_url: "https://dirskills.com/skills/agent-qa-debug-fix"
---

# Agent Qa Debug Fix

Agent Qa Debug Fix uses MCP evidence, logs, artifacts, and local code changes to diagnose a failed agent-qa run and patch the root cause. Use it after a run fails and you need to verify the fix with the narrowest relevant test or hook.

**Install:**

```bash
npx degit https://github.com/vostride/agent-qa/tree/main/skills/agent-qa-debug-fix ~/.claude/skills/agent-qa-debug-fix
```

## README

# agent-qa Debug Fix

## Workflow

1. Start with evidence collection:
   - `agent_qa_get_run`
   - `agent_qa_get_run_steps`
   - `agent_qa_get_run_artifact`
   - `agent_qa_get_run_logs`
   - `agent_qa_get_run_execution_logs`
2. Call `agent_qa_classify_failure` and treat its category as a hypothesis, not a verdict.
3. Identify the failing surface: test definition, hook, application under test, runtime infrastructure, or agent behavior.
4. Inspect the relevant local files directly. Do not infer patches from artifacts alone.
5. Apply the smallest code or YAML change that explains the evidence.
6. Re-run the narrowest affected agent-qa test, suite, hook, or unit test.
7. Report the root cause, changed files, verification command, and any remaining risk.

## Fix Rules

- Do not invent selectors, screen states, screenshots, logs, or source files.
- Do not rewrite a test just to make it pass if the artifact shows a product or runtime defect.
- Preserve canonical agent-qa IDs when editing tests, suites, hooks, or memory files.
- Prefer `agent_qa_validate_test`, `agent_qa_validate_suite`, and `agent_qa_validate_definition` before re-running edited YAML.
- When MCP is unavailable, use dashboard REST APIs or local `.agent-qa` artifacts and state that MCP evidence was unavailable.