BM

bmad-checkpoint-preview

Assists humans in systematically reviewing and verifying code changes through a structured checkpoint process.

Install

mkdir -p .claude/skills/bmad-checkpoint-preview && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9736" && unzip -o skill.zip -d .claude/skills/bmad-checkpoint-preview && rm skill.zip

Installs to .claude/skills/bmad-checkpoint-preview

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".
189 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Review implementation changes
  • Validate artifacts
  • Walk through complex PRs
  • Verify code checkpoints

How it works

It guides the user through a structured review process using pre-configured artifacts and context-aware steps.

Inputs & outputs

You give it
Code change or PR
You get back
Review summary and validation results

When to use bmad-checkpoint-preview

  • Reviewing code changes
  • Testing implementation artifacts
  • Walking through complex PRs
  • Checkpoint-based code verification

About this skill

Checkpoint Review Workflow

Goal: Guide a human through reviewing a change — from purpose and context into details.

You are assisting the user in reviewing a change.

Global Step Rules (apply to every step)

  • Path:line format — Every code reference must use CWD-relative path:line format (no leading /) so it is clickable in IDE-embedded terminals (e.g., src/auth/middleware.ts:42).
  • Front-load then shut up — Present the entire output for the current step in a single coherent message. Do not ask questions mid-step, do not drip-feed, do not pause between sections.
  • Language — Speak in {communication_language}. Write any file output in {document_output_language}.

INITIALIZATION

Load and read full config from {project-root}/_bmad/bmm/config.yaml and resolve:

  • implementation_artifacts
  • planning_artifacts
  • communication_language
  • document_output_language

FIRST STEP

Read fully and follow ./step-01-orientation.md to begin.

When not to use it

  • For trivial code changes
  • When no implementation artifacts exist

Prerequisites

config.yaml

Limitations

  • Requires pre-configured config.yaml
  • Follows specific step-by-step orientation

How it compares

It provides a consistent, human-in-the-loop review framework instead of ad-hoc code reading.

Compared to similar skills

bmad-checkpoint-preview side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
bmad-checkpoint-preview (this skill)04moNo flagsIntermediate
python-testing-patterns772moReviewIntermediate
dependency-upgrade265moReviewIntermediate
test-cases577moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry