skills.rest
letuhao
letuhaoCOMMUNITY
Explore all skills by this author →
GitHub

aif-qa-check

Executes QA test cases in human-guided or automated-agent mode and records results.

31|2|Updated Mar 21, 2026
Search Tags:#testing#quality assurance#test automation#qa#verification#browser automation#agent
One-click install
npx skills add https://github.com/letuhao/lore-weave --skill aif-qa-check-letuhao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aif-qa-check
Source: https://github.com/letuhao/lore-weave/tree/main/.cursor/skills/aif-qa-check
Command: npx skills add https://github.com/letuhao/lore-weave --skill aif-qa-check-letuhao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Running QA test cases manually is slow and error-prone, and results often get lost or become stale when code changes. This Skill executes the test cases produced by /aif-qa one at a time, records pass/fail/blocked outcomes in a persistent qa-check.md artifact, and invalidates stale results when the tested revision, worktree, or source cases change. ## Core Features & Use Cases - Dual execution modes: Run cases interactively in human-guided mode, or let an agent verify them automatically through browser automation, CLI commands, test runners, API calls, or file inspection. - Staleness detection: Tracks source digests, per-case digests, tested revision, and worktree state so outdated results are marked Stale and retested instead of silently trusted. - Cross-run QA memory: Maintains reusable agent-context.md and agent-history.md files so future QA runs reuse environment facts, selectors, and lessons without repeating mistakes. - Use Case: After generating test cases for a feature branch, run the skill in agent mode to automatically execute backend tests and browser checks, then hand off only the human-verifiable blocked cases for manual confirmation. ## Quick Start Run the QA check skill in agent mode for the current branch to execute all pending test cases and record the results.

Frequently Asked Questions about aif-qa-check

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run QA test cases automatically with an AI agent?▼

Invoke the skill in agent mode with an optional branch argument. The agent classifies each case by execution surface, then verifies it through browser automation, CLI commands, existing test runners, API calls, or file inspection, recording evidence in qa-check.md.

How do I walk through QA test cases one at a time manually?▼

Use human mode, which shows exactly one test case at a time with its steps and expected result. You answer whether it works, and the skill records Passed or Failed with your comment before moving to the next case.

What happens to QA results when the code changes after testing?▼

The skill tracks the tested revision, worktree digest, and per-case digests. When any of these change, prior results are marked Stale and unchecked, requiring retest so outdated passes are never counted as current.

Can the agent run browser tests without Playwright or a browser tool?▼

No. Browser/UI cases require live browser automation through the in-app Browser capability or Playwright MCP. If neither is available, those cases are marked Blocked while CLI, API, and file-based cases still execute.

Does the QA agent store credentials or secrets in its memory files?▼

No. Passwords, tokens, cookies, and authorization headers are redacted as [REDACTED] before writing to any artifact. Only non-sensitive reusable facts like URLs, roles, and selectors are persisted to agent-context.md.

What are the limitations of automated QA agent execution?▼

The agent cannot invent missing URLs, credentials, commands, or fixtures, and it refuses destructive or production-side-effect actions without explicit authorization. Cases lacking automated coverage or required context remain Blocked rather than guessed.

Related Skills

Explore More Software Engineering Skills→
Young-ZYoung-Z
8

x-ipe-task-based-feature-acceptance-test

Generate acceptance test cases from specification criteria and execute them via Chrome DevTools MCP.

Community
Advanced
jnyrossjnyross

tdd

Writes a failing regression test before fixing a bug with a clear test path.

Community
Intermediate
VirtoCommerceVirtoCommerce
2

qa-seed-data

Automate creation and cleanup of QA test data across Virto Commerce environments.

Official
Advanced
adityaarsharmaadityaarsharma
2

orbit-qa-regression-pack

Manage regression test suites with Playwright and CI pipelines.

Community
Advanced