Skip to content
Get packs

Agent QA Test Authoring

Lets an agent create, edit, validate and run Agent QA tests, suites and hooks with correct IDs and schemas.

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
2 files

What it does

This skill teaches an AI agent how to write automated quality-assurance tests for the Agent QA testing tool. Once installed, the agent looks up the exact field names and ID formats in a bundled reference file, generates test IDs with the official tooling instead of making them up, and checks every definition before saving or running it. It is built to work through Agent QA's MCP tools or CLI and asks for approval before deleting things or running tests that could change real application data.

Great for

  • QA engineers who maintain Agent QA test suites and want fewer schema errors
  • Developers adding browser or mobile tests for a staging environment
  • Teams that need an agent to draft tests but keep a human approving runs

Skip it if

  • Users without an installed and configured Agent QA workspace, since the skill cannot do anything useful without it
  • Running tests against production systems without careful scoping, because the skill only partly guards against side effects and validation does not prove an environment is safe
  • Teams needing a general-purpose test framework outside Agent QA

Try asking

  • “Add an Agent QA checkout test for the staging target and validate it, but do not run it yet”
  • “Update the login suite to include the new password-reset hook and validate the YAML”
  • “Generate a valid observation ID and check whether an existing test ID is well formed”
  • “Show which Agent QA config fields apply to mobile devices in this workspace”
Step-by-step guide: how to use Agent QA Test AuthoringInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    agent-qa-authoring.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip agent-qa-authoring.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip agent-qa-authoring.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Start with a validation-only request to see the generated definition before any create or run step
  • Confirm the target and environment explicitly when a test could modify real data
  • Do not let the agent install Agent QA via npx at runtime; approve a pinned version first

What's inside

  • references/agent-qa-contracts.json
  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.