# Review Task

> Use to verify that a task has been completed according to its intent and criteria. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

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

---


# Review Task

## Usage

`/at:review-task <task-path> [further user instructions]`

## Goal

Verify that a task has been completed according to its intent and criteria.

## Context

This skill is typically run as part of a larger workflow:

```text
create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task
```

As steps (e.g. clarify, plan, impl, review) typically run in new sessions, it's imperative that the task file plus repo state carry everything the next agent needs.

Task files live in the project's task store. Project config can override its location and other defaults: read `.claude/auto-task.config.md` (project, committed) and `.claude/auto-task.config.local.md` (personal overrides — win on conflict) if they exist. `/at:config` owns the defaults and the precedence rules.

## Guidance (DO NOT IGNORE!)

<!-- Curate as we go along. -->

These rules govern how to perform the review. Internalise and follow them throughout.

- Flag issues — do not attempt to fix them; let the user decide.

## Step 1: Build Context

Read the task and the code that was implemented. Ensure you fully understand the task's intent, criteria and what was implemented.

## Step 2: Verify ACs

For each acceptance criterion, determine: **pass**, **fail**, or **unclear**.

A criterion passes when you can point to **specific evidence** — for example, a test that exercises it, observable behaviour in the code, or output from running it. "The code looks like it would work" is not evidence; a passing test is.

## Step 3: Verify Intent

In addition to checking ACs:

- Check that the implementation truly matches the *why* in the description. It's easy to meet every AC but miss the intent.
- If there were deviations from the plan, check that they are justified.

## Step 4: Summarise

Say whether the review passed or, if not, present a summary of your findings and wait for user input.

## Step 5: Wrap Up

Once there are no findings left, or the user has asked you to proceed, remember to set the task status to `ready-for-signoff` — by default, edit the frontmatter `status:` field and commit with a `(task/NNN)` subject suffix; if the project config defines a task-status command, use that instead.