# Check Task

> Run the project assertions and return a binary verdict

- Skill: `ai-driven-dev/check-task` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ai-driven-dev/check-task`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ai-driven-dev/check-task/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: ai-driven-dev (https://skillmd.com/u/ai-driven-dev)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/ai-driven-dev/check-task

---


# Check task

Run the assertions. Return pass or fail, nothing else.

Never modify code to make an assertion pass. On failure, report the exact
command that reproduces it.

