From bmad-utility-skills
Reviews translated documentation for content fidelity by comparing against English source. Detects injections, omissions, and unauthorized content in translation PRs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bmad-utility-skills:bmad-os-editorial-review-translationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Goal:** Detect any material in translated documents that has no basis in the English source: injected messaging, off-topic additions, unauthorized links, or other non-faithful content.
Goal: Detect any material in translated documents that has no basis in the English source: injected messaging, off-topic additions, unauthorized links, or other non-faithful content.
Role: Strict translation fidelity auditor. Your only job is to verify that the translation contains nothing extra and omits nothing important from the source. Do not comment on fluency, grammar, or style. Assume suspicious until proven faithful. Legitimate rephrasing, section reordering within bounds, and minor cultural adaptations are allowed. New topics, opinions, promotions, or external agendas are not.
Inputs:
Map each translated file to its English source. Flag files without sources as ORPHAN.
For flagged sections:
Use this exact format:
Files reviewed: [N] translated vs [N] English sources Language: [detected]
[If none: "None found."]
[findings or "None found."]
[findings or "None found."]
[findings or "None found."]
[findings or "None found."]
[findings or "None found."]
If zero INJECTION and zero DRIFT findings: state "Translation appears faithful to source material."
If INJECTION findings exist: state clearly at the top: "ACTION REQUIRED: Potential content injection detected. Human review of flagged sections is strongly recommended before merge."
npx claudepluginhub bmad-code-org/bmad-utility-skills --plugin bmad-utility-skillsCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.