task-qa

Execute mandatory tests and record failure classifications for QA evidence.

1|Updated Jun 15, 2025
One-click install
npx skills add https://github.com/einja-inc/einja-management-template --skill task-qa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-qa
Source: https://github.com/einja-inc/einja-management-template/tree/main/.claude/skills/einja-task-qa
Command: npx skills add https://github.com/einja-inc/einja-management-template --skill task-qa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The task QA Skill automates the verification of acceptance criteria by executing mandatory tests, analyzing results, and recording evidence for traceability, reducing manual QA effort and accelerating feedback loops.

Core Features & Use Cases

  • Automated test orchestration: runs unit tests, E2E tests, lint checks, builds, and type checks to confirm integrity of changes.
  • QA-result logging: saves evidence under qa-tests/, records outcomes, and provides clear pass/fail metrics.
  • Failure classification: automatically categorizes failures into A (implementation) / B (requirements) / C (design) / D (environment) and directs subsequent actions.

Quick Start

Use the skill to run QA for docs/specs/tasks/user-auth/1-1 by invoking: claude skill task-qa --spec-dir docs/specs/tasks/user-auth/ --task-group-id 1.1

Frequently Asked Questions about task-qa

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

FAQPage Schema
How do I automate QA testing to verify task implementations meet acceptance criteria?

Automate QA testing by orchestrating unit, e2e, lint, build, and typecheck tests to verify task implementations meet acceptance criteria. The skill executes mandatory tests, records outcomes, and preserves evidence under qa-tests/ for traceability and audits.

What is the best way to log QA results and classify test failures for actionable feedback?

Log QA results and classify test failures by recording outcomes and evidence under qa-tests/. The skill automatically categorizes failures into A (implementation), B (requirements), C (design), or D (environment) to direct subsequent actions.

How do I run unit, integration, and end-to-end tests for a specific task group?

Run unit, integration, and end-to-end tests for a specific task group by invoking the skill with a spec directory and task group ID. It executes mandatory tests tracked in qa-tests and saves evidence for audit readiness.

Does automated test orchestration support lint checks, builds, and type checks alongside unit and e2e tests?

Automated test orchestration supports lint checks, builds, and type checks alongside unit and e2e tests. It runs these mandatory tests to confirm the integrity of changes and provides clear pass or fail metrics for feedback.

Why do I need to classify test failures into implementation, requirements, design, and environment categories?

Classifying test failures into implementation, requirements, design, and environment categories is needed to direct subsequent actions effectively. The skill automatically categorizes failures into A, B, C, or D types to provide actionable feedback.

Can I use this QA automation skill for tasks tracked in docs and specs directories without additional dependencies?

You can use this QA automation skill for tasks tracked in docs and specs directories without additional dependencies. It requires no dependencies to execute mandatory tests, analyze results, and record evidence for traceability.