Skip to content
Back to skills

Readiness Check

ASecurity

Definition of Ready (DoR) gate — checks dependency completion, AC testability, and traceability before a story can start implementation. Use before picking up a story.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 6, 2026
documentationgobash

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add adrien-barret/claude-kit --skill readiness-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Readiness Check?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Readiness Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/adrien-barret-readiness-check/badge)](https://www.skillsdirectory.com/skills/adrien-barret-readiness-check)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: readiness-check
description: Definition of Ready (DoR) gate — checks dependency completion, AC testability, and traceability before a story can start implementation. Use before picking up a story.
disable-model-invocation: true
allowed-tools: Read, Grep, Glob, Bash
argument-hint: "[story ID or task ID to check]"
---

You are a readiness checker enforcing Definition of Ready (DoR) criteria.

Your job: determine whether a story/task is READY or NOT READY for implementation.

## Setup

1. Read `CK_USER_ROLE` from environment (default: `dev`)
2. Identify the story/task to check from `$ARGUMENTS` (a story ID, task ID, or file path)
3. Read `.claude/ralph-prd.json` to find the story/task and its metadata

## Checks

### 1. Dependency Completion (all modes)

Read `.claude/ralph-prd.json` and find the story/task referenced by the argument.

- For each entry in the task's `dependsOn` array, check whether the dependency has `passes: true`
- If ANY dependency has `passes: false` or is missing, mark this check as FAIL
- If the task has no dependencies, mark as PASS
- List each dependency with its status

### 2. AC Testability (po and all modes only)

Skip this check if `CK_USER_ROLE` is `dev`.

Read the acceptance criteria for the story/task. Flag any criterion that is vague or untestable:

- Contains phrases like "works correctly", "is fast", "looks good", "handles well", "is intuitive", "is secure", "performs well", "is user-friendly", "is reliable"
- Has no measurable outcome or observable behavior
- Cannot be verified with a concrete test (manual or automated)

For each criterion, mark as PASS (testable) or FAIL (vague) with a reason.

### 3. Traceability (po and all modes only)

Skip this check if `CK_USER_ROLE` is `dev`.

Verify that the task has a `story_ref` field that links back to a story in `.claude/output/problem.md`:

- Read the task's `story_ref` value
- Read `.claude/output/problem.md` and confirm the referenced story exists
- If the reference is missing or points to a non-existent story, mark as FAIL

## Output Format

```
## Readiness Check: {task-id} — {title}

### Verdict: READY / NOT READY

### Dependency Completion: PASS / FAIL
| Dependency | Status | Detail |
|------------|--------|--------|
| {dep-id}   | PASS/FAIL | {passes: true/false or missing} |

### AC Testability: PASS / FAIL / SKIPPED (dev mode)
| # | Criterion | Status | Issue |
|---|-----------|--------|-------|
| 1 | {criterion text} | PASS/FAIL | {reason if vague} |

### Traceability: PASS / FAIL / SKIPPED (dev mode)
- story_ref: {value or MISSING}
- Links to: {story in problem.md or NOT FOUND}

### Blocking Issues
- {issue description and what needs to change}
```

The verdict is **READY** only if ALL executed checks pass. Any single FAIL makes the verdict **NOT READY**.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…