skills.rest
Lia-Creative
Lia-CreativeOFFICIAL
Explore all skills by this author →
WebsiteGitHub

testing-lead

Orchestrates QA test planning, case execution, hostile testing, and quality report verdicts for merged work.

1|Updated Jun 30, 2026
Search Tags:#qa#agent workflow#quality report#test planning#bug triage#test orchestration#uat gate
One-click install
npx skills add https://github.com/Lia-Creative/lia-plugins --skill testing-lead-lia-creative
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: testing-lead
Source: https://github.com/Lia-Creative/lia-plugins/tree/main/lia-tools/skills/testing-lead
Command: npx skills add https://github.com/Lia-Creative/lia-plugins --skill testing-lead-lia-creative

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Merged code that passes code review can still break when a real user touches it, and without an owned QA stage, founders and human testers end up finding trivial bugs themselves. This Skill owns the QA stage end to end: it turns merged work into a test plan, dispatches the right testing seats, files findings as bugs, and delivers a quality report that gates promotion to UAT. ## Core Features & Use Cases - Test plan ownership: Shapes the test plan from the epic's stories, acceptance criteria by index, and walked scenarios, with every case cited by number so verdicts are checkable. - Bench orchestration: Spawns separate test-analyst, tester, and rogue seats so case writing, execution, and hostile testing never collapse into one context. - Bug and verdict handling: Files findings as Bug tickets on the feature epic in bug-writer's shape, returns them to the dev lane, and writes a quality report with a pass/fail/blocked census and a gate verdict. - Use Case: After a feature epic merges, ask for a QA run; the lead plans coverage, dispatches the bench, disposes of every blocked case, and posts a quality report on the epic that the PM and founder read before promoting to UAT. ## Quick Start Ask the agent to be the testing lead and run QA on the merged feature epic, producing a quality report before UAT promotion.

Frequently Asked Questions about testing-lead

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

FAQPage Schema
How do I run QA on a merged feature before UAT?▼

Invoke the testing lead on the merged epic. It shapes a test plan from the acceptance criteria, spawns test-analyst for cases, tester for the run, and rogue for a hostile pass, then writes a quality report with the verdict on the epic.

What is the difference between code review and QA testing?▼

Code review checks code against its acceptance criteria before merge, while QA tests the behavior of the merged build as a user meets it. Code that satisfies its criteria can still break in real use, which is what this stage catches.

Why are test cases written and run by different agents?▼

A context that wrote the cases cannot honestly run them, and one that ran them cannot honestly attack them. Separating test-analyst, tester, and rogue into distinct spawned seats preserves the three-way independence the bench exists for.

What happens when a test case is blocked?▼

Blocked is a real verdict naming what blocked the case. The quality report opens with a pass, fail, and blocked census, and each blocked case must be disposed of as re-run, waived with a reason and owner, or carried as a known gap.

Does the QA lead fix the bugs it finds?▼

No. Findings become Bug tickets on the feature epic and return to the engineering lane that built the work. A tester who fixes the defect has disqualified themselves from retesting it.

When should QA testing not use mocks or local simulations?▼

Always test the merged build at its real stage from the release register with real data. A pass against a simulation is only evidence about the simulation; unreachable environments are named as report boundaries instead.

Related Skills

Explore More Software Engineering Skills→
MathematicGuyMathematicGuy

bmad-agent-dev

Implements approved stories with test-first discipline as a senior software engineer persona.

Community
Intermediate
happier-devhappier-dev
1.4k

happier-release-promote

Promote validated release candidates across preview and production lanes after explicit human approval.

Official
Advanced
arthur0824haoarthur0824hao

skill-system-review

Convert Prometheus plan markdown into TKT bundle commands and generate review prompts.

Community
Advanced
garethrhughesgarethrhughes
5

create-feature

Coordinate feature delivery from intake through proposal, implementation, review, and pull request preparation.

Community
Advanced