Testing Skill Discovery - QA Skill Library

Why this Skill

It turns this Skill's method into a quality input that can be executed, reviewed, and reused.

Need to decide which testing skill should be used before execution.
Recommend few skills — avoid menu dumping.
If the target skill is already obvious, say so directly.
Make the route actionable: name the skill and the reason.
Do not recommend many skills at once.

When to use

Use this Skill

Need to decide which testing skill should be used before execution.
The request mixes multiple testing directions or phases.

Common pitfalls

Do not recommend many skills at once.
Do not turn skill selection into full test execution.
Do not pretend a route is complete when information is insufficient.

Input

Minimum Input

Read the user request and first identify the capability stage (Core QA / Engineering QA / Production Quality / AI Native QA) and primary testing goal.

Recommended Input

Before producing output, read and follow prompts/discover-testing.md (minimum coverage, output structure, quality bar).
When Excel/CSV/JSON/Word is requested: read output-formats.md and honor the format.
When a ready-made template fits: use matching files under output-templates/.
For format conversion or helper checks: prefer existing scripts/ over reinventing.

Optional Context

For evaluating/regressing this skill: use evals/ with skill-up.
For step ↔ prompt mapping: read reference.md.

Output

The output follows this Skill's method and makes facts, assumptions, risks, and next steps explicit.

Judge the output value before installing

01Followed the main prompt's output structure
02Minimum coverage focus: main goal, best-fit primary skill, optional supporting skill, why this choice fits, next step to continue work (details in main prompt)
03Covered the minimum checklist, or explained omissions
04High-risk items have explicit priority

View full output structure

05Did not invent details the user did not provide
06Assumptions and gaps are marked

How It Works

01Read the user request and first identify the capability stage (Core QA / Engineering QA / Production Quality / AI Native QA) and primary testing goal.
02Follow the routing prompt under prompts/: pick 1 primary skill; add at most 1 helper only when needed.
03Hand the request to the target skill; do not execute the full testing work inside this router skill.

Install & Quick Start

Install command / SHELL

npx skills add \
  https://github.com/naodeng/awesome-qa-skills/tree/main/skills/en/testing-workflows/discover-testing
  -g

discover-testing.prompt

@skill discover-testing

Using the current project context, produce an actionable result following this Skill.

Additional context:
[Paste project context or requirement]

---
name: discover-testing
description: Use this skill when you need to route a request to the right testing skill before execution; triggers include discover testing, testing skill router, and which testing skill.
---

# Testing Skill Discovery (English)

**Chinese version:** See the corresponding Chinese skill.

## When to Use

- Need to decide which testing skill should be used before execution.
- The request mixes multiple testing directions or phases.

## Workflow

1. Read the user request and first identify the capability stage (Core QA / Engineering QA / Production Quality / AI Native QA) and primary testing goal.
2. Follow the routing prompt under `prompts/`: pick 1 primary skill; add at most 1 helper only when needed.
3. Hand the request to the target skill; do not execute the full testing work inside this router skill.

## Core Constraints

- Recommend few skills — avoid menu dumping.
- If the target skill is already obvious, say so directly.
- Make the route actionable: name the skill and the reason.
- Use `ai-assisted-testing` for AI for QA; Testing for AI belongs to AI Native QA. Until roadmap Skills are installed, never recommend them as callable primary Skills.

## Progressive Disclosure

- Before producing output, read and follow `prompts/discover-testing.md` (minimum coverage, output structure, quality bar).
- When Excel/CSV/JSON/Word is requested: read `output-formats.md` and honor the format.
- When a ready-made template fits: use matching files under `output-templates/`.
- For format conversion or helper checks: prefer existing `scripts/` over reinventing.
- For evaluating/regressing this skill: use `evals/` with skill-up.
- For step ↔ prompt mapping: read `reference.md`.

## Pre-delivery Checklist

- [ ] Followed the main prompt's output structure
- [ ] Minimum coverage focus: main goal, best-fit primary skill, optional supporting skill, why this choice fits, next step to continue work (details in main prompt)
- [ ] Covered the minimum checklist, or explained omissions
- [ ] High-risk items have explicit priority
- [ ] Did not invent details the user did not provide
- [ ] Assumptions and gaps are marked

## Common Pitfalls

- Do not recommend many skills at once.
- Do not turn skill selection into full test execution.
- Do not pretend a route is complete when information is insufficient.