Agent QA Debug Fix

Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.

862 stars 26 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vostride/agent-qa --skill agent-qa-debug-fix
Manual install
git clone --depth 1 https://github.com/vostride/agent-qa.git /tmp/agent-qa
mkdir -p ~/.claude/skills
cp -r /tmp/agent-qa/packages/cli/skills/agent-qa-debug-fix ~/.claude/skills/agent-qa-debug-fix

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# agent-qa Debug Fix

## Workflow

1. Start with evidence collection:
   - `agent_qa_get_run_digest` — the run's verdicts, its post-processing chain, the outcome of its
     steps, and what it produced. This is the triage read over this surface.
   - `agent_qa_get_entity` on the run reference — the run's own card.
   - `agent_qa_get_run_overview` — every test and step with its verdict, and the address of each
     screenshot, evidence document and served record the run recorded.
   - `agent_qa_get_run_evidence` — only what the failure needs, by the overview's addresses: a
     step's console, network, a11y, aria or variables document (`"action": "runs.evidence"`), or a
     screenshot by its sha (`"action": "runs.artifact"`), which comes back as an image.
   - `agent_qa_list_runs` — recent runs, when the question is whether this failure is new.
2. Treat the digest's verdict as a hypothesis, not a conclusion — it is the reading a job produced,
   and the evidence it points at is what settles the question.
3. Identify the failing surface: test definition, hook, application under test, runtime
   infrastructure, or agent behavior.
4. Inspect the relevant application source, tests, suites and hooks directly. Do not infer
   patches from evidence 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. Name the test files
   to `agent_qa_start_run` with `patterns` (paths or globs).
Read the full skill on GitHub

Details

Skill name
agent-qa-debug-fix
Path
packages/cli/skills/agent-qa-debug-fix/SKILL.md
Repo updated
14 November 2026

FAQ

What does the Agent QA Debug Fix skill do?

Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.

How do I install the Agent QA Debug Fix skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add vostride/agent-qa --skill agent-qa-debug-fix. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agent QA Debug Fix popular?

It lives in vostride/agent-qa, which has 862 GitHub stars and 26 forks, and is included in 2 curated skill lists.

Related skills

Agent QA Authoring

862

vostride/agent-qa

Use when creating, editing, validating, or running agent-qa tests, suites, or hooks. Prefer agent-qa MCP tools, enforce canonical agent-qa IDs, and use the bundled schema reference to avoid hallucinated config keys or YAML fields.

Testing & QAIn 2 lists26

Agent QA Knowledge

862

vostride/agent-qa

Use when asked what an agent-qa run did, why a step passed or failed, what a run's screenshots, console or network showed, what knowledge agent-qa learned or served, where a knowledge record came from, or which runs exist. Reads runs, evidence and knowledge through the agent-qa MCP tools or the agent-qa CLI with --json, never through .agent-qa files, SQLite or index files.

Testing & QAIn 2 lists26

Agent QA Plugin Browserstack

862

vostride/agent-qa

Use when configuring agent-qa web or device tests to run on BrowserStack through the BrowserStack plugin, or when a BrowserStack remote is refused.

Testing & QAIn 2 lists26

Agent QA Result Triage

862

vostride/agent-qa

Use when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs. Prefer agent-qa MCP run/artifact tools and produce evidence-backed triage.

AI, LLMs & AgentsIn 2 lists26

Gastown

1.1k

numman-ali/n-skills

Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.

AI, LLMs & Agents109

Autonomous Loops

2k

xu-xiang/everything-claude-code-zh

自主运行 Claude Code 循环的模式与架构 —— 从简单的顺序流水线到 RFC 驱动的多智能体 DAG 系统。

AI, LLMs & Agents332

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.