bmad-checkpoint-preview
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".
- License 许可
- MIT
- 最近更新
- 2026-10-25
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- bmad-checkpoint-preview
- description
- 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".
02 资源文件 7
- 其他customize.toml1.6 KB
- 参考文档generate-trail.md1.9 KB
- 参考文档step-01-orientation.md4.9 KB
- 参考文档step-02-walkthrough.md4.1 KB
- 参考文档step-03-detail-pass.md4.9 KB
- 参考文档step-04-testing.md2.6 KB
- 参考文档step-05-wrapup.md1.5 KB
03 SKILL.md 正文
Checkpoint Review Workflow
Goal: Guide a human through reviewing a change — from purpose and context into details.
Your Role: You are assisting the user in reviewing a change.
Conventions
- Bare paths (e.g.
step-01-orientation.md) resolve from the skill root. {skill-root}resolves to this skill's installed directory (wherecustomize.tomllives).{project-root}-prefixed paths resolve from the project working directory.{skill-name}resolves to the skill directory's basename.
On Activation
Step 1: Resolve the Workflow Block
Run: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow
If the script fails, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
{skill-root}/customize.toml— defaults{project-root}/_bmad/custom/{skill-name}.toml— team overrides{project-root}/_bmad/custom/{skill-name}.user.toml— personal overrides
Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.
Step 2: Execute Prepend Steps
Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.
Step 3: Load Persistent Facts
Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} — load the referenced contents as facts. All other entries are facts verbatim.
Step 4: Load Config
Load config from {project-root}/_bmad/bmm/config.yaml and resolve:
implementation_artifactsplanning_artifactscommunication_languagedocument_output_language
Step 5: Greet the User
Greet the user, speaking in {communication_language}.
Step 6: Execute Append Steps
Execute each entry in {workflow.activation_steps_append} in order.
Activation is complete. If activation_steps_prepend or activation_steps_append were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.
Global Step Rules (apply to every step)
- Path:line format — Every code reference must use CWD-relative
path:lineformat (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}.
FIRST STEP
Read fully and follow ./step-01-orientation.md to begin.
04 同仓库更多 Skills
repo-doc-audit
Performs a comprehensive Repository Documentation Audit and Governance Standard (RDAGS) against an entire codebase. Use this skill whenever the user wants to audit, evaluate, or assess repository documentation — including requests like "audit my repo docs", "find doc inconsistencies", "check for documentation drift", "governance review", "find dead or orphan knowledge", "check my CLAUDE.md or AGENTS.md for accuracy", or any systematic documentation quality evaluation. Always trigger this skill when the user asks to run a documentation audit or governance review, even if they describe only part of the standard (e.g., "check traceability" or "find contradictions in my docs"). Produces five output files: Repository-Audit-Report.md (full 18-section report) plus Direct-Contradictions.md, Semantic-Contradictions.md, Traceability-Failures.md, and Proposed-Repository-Governance-Improvements.md as standalone action-oriented findings documents.
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
teach
Teach the user a new skill or concept, within this workspace.
self-reflect
Enterprise-grade forensic self-reflection over recent git history. Multi-axis audit with pass/fail gates, mandate compliance matrix, platform drift forensics, test quality review, and ranked generation constraints.
handoff
Compact the current conversation into a handoff document for another agent to pick up.