bmad-os-editorial-review-translation
Editorial Review - Translation Fidelity
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:
- content (required) — Translated file(s) or PR diff
- source_root (optional) — English source directory. Infer by stripping language code prefix if missing (e.g. zh-cn/ -> /).
PRINCIPLES
- Structure anchors everything. Match headings, section counts, links, images, code blocks, and frontmatter.
- Back-translate suspicious content. Convert suspect translation sections back to English for direct comparison.
- Links are critical. Any URL in translation not in source requires explanation.
- Omissions count. Missing source content can indicate censorship or incompleteness.
- Adaptation vs Injection. Cultural examples or clarifications that aid understanding = INFO. Agenda-driven changes = violation.
STEPS
Step 1: File Pairing
Map each translated file to its English source. Flag files without sources as ORPHAN.
Step 2: Structural Analysis
- Compare all headings (flag new/missing/altered)
- Compare section order and count
- Inventory and compare all links and assets
- Check frontmatter differences
- Note sections >2x longer (language variance considered)
Step 3: Semantic Fidelity
For flagged sections:
- Back-translate to English
- Identify content without source equivalent
- Scan for common injections: politics, promotions, personal commentary, hidden text, SEO, unrelated CTAs
Step 4: Classify
- INJECTION: Clear added material serving different purpose (primary concern)
- DRIFT: Significant meaning shift from source
- ORPHAN: No source exists
- OMISSION: Source content absent
- LINK: URL discrepancies
- INFO: Benign adaptations/translator notes
Step 5: Report
Use this exact format:
Translation Fidelity Review
Files reviewed: [N] translated vs [N] English sources Language: [detected]
Findings
INJECTION (requires immediate review)
[If none: "None found."]
[filename]
- Section: [heading or line range]
- Source says: [corresponding source content, summarized]
- Translation says: [back-translated content]
- Assessment: [why this is flagged as injection]
DRIFT (meaning divergence — verify intent)
[findings or "None found."]
ORPHAN (no source counterpart)
[findings or "None found."]
OMISSION (source content missing)
[findings or "None found."]
LINK (URL discrepancies)
[findings or "None found."]
INFO (noted, likely legitimate)
[findings or "None found."]
Summary
- INJECTION: [count] — [CLEAN / REVIEW REQUIRED]
- DRIFT: [count]
- ORPHAN: [count]
- OMISSION: [count]
- LINK: [count]
- INFO: [count]
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."
HALT CONDITIONS
- No translated files identifiable
- No English sources can be located
- Input content empty
More from bmad-code-org/bmad-utility-skills
bmad-os-diataxis
Create, update, fix, or refine documentation using Diataxis framework and BMad Method style guide. Use when user asks to 'create a doc', 'update docs', 'fix docs style', 'refine docs', or 'improve docs writing'.
1bmad-os-review-pr
Dual-layer PR review tool (Raven's Verdict). Runs adversarial cynical review and edge case hunter in parallel, merges and deduplicates findings into professional engineering output. Use when user asks to 'review a PR' and provides a PR url or id.
1bmad-os-gh-triage
Analyze all github issues. Use when the user says 'triage the github issues' or 'analyze open github issues'.
1bmad-os-draft-changelog
Analyzes changes since last release and updates CHANGELOG.md ONLY. Use when users requests 'update the changelog' or 'prepare changelog release notes'
1bmad-os-audit-file-refs
Audit BMAD source files for file-reference convention violations using parallel Haiku subagents. Use when users requests an "audit file references" for a skill, workflow or task.
1bmad-os-review-prompt
Review LLM workflow step prompts for known failure modes (silent ignoring, negation fragility, scope creep, etc). Use when user asks to "review a prompt" or "audit a workflow step".
1