check-review-alignment

Check Review Alignment

Coordination agreement with bensz-collect-bugs

• When a bug caused by a design flaw in this skill occurs in the user's environment, prioritize using bensz-collect-bugs to record it according to the specification in ~/.bensz-skills/bugs/, and strictly prohibit directly modifying the source code of skills already installed in the user's local Claude Code / Codex.
• If the AI can still complete the user's task through a workaround, it should first record the bug, then continue completing the current task.
• When the user explicitly requests public reporting actions such as "report bensz skills bugs", call the local gh and bensz-collect-bugs, and only upload new bugs to huangwb8/bensz-bugs; do not pull / clone the entire bug repository.

Positioning

• Used to check whether the body citations of an existing {主题}_review.tex truly match the content of the corresponding papers.
• Only perform minimal rewriting of "the sentence containing that citation" when a fatal error is confirmed.
• Rendering PDF/Word depends on systematic-literature-review; preparing structured input does not depend on this skill.

Input

• work_dir: includes *_review.tex and .bib
• Optional --tex: specify the tex file name

Output

• {work_dir}/.check-review-alignment/ai_alignment_report.md
• {work_dir}/.check-review-alignment/ai_alignment_input.json
• Modified {主题}_review.tex
• Newly generated {主题}_review.pdf
• Newly generated {主题}_review.docx

Modification boundaries

• P0: Must fix; minimal rewriting or correction of an erroneous bibkey is allowed
• P1: Warning only; do not rewrite
• P2: Skip entirely
• Prohibited:
  • Rewriting sentences that do not contain citations
  • Rewriting the entire paragraph
  • Introducing new bibkeys (unless fixing an erroneous key)
  • Fabricating paper content

Workflow

1. Dependency check

• Only enforce checking systematic-literature-review
• If it is only --prepare, rendering dependencies are not required to be available

2. Pre-check and positioning

• Find *_review.tex and the corresponding .bib
• Stop immediately when any core file is missing

3. Structured context extraction

cd /path/to/check-review-alignment
python3 scripts/run_ai_alignment.py --work-dir "/path/to/work_dir" --prepare

• Generate ai_alignment_input.json
• The input must include at least: sentence, bibkey, bibliographic metadata, DOI/URL, PDF abstract paragraph or BibTeX abstract

4. AI semantic verification

• Evidence priority: PDF abstract paragraph > BibTeX abstract/title > inferred from the sentence alone
• Each citation must be judged as one of:
  • fake_citation
  • wrong_citation
  • contradictory_citation
  • weak_support
  • overclaim
  • style_issue
• When it cannot be confirmed, keep it as is and record it in Warnings

5. Report

• The report must include at least:
  • Summary
  • Specific details
  • Critical Fixes (P0)
  • Warnings (P1)
  • Rendering Result
• The details for each citation must include at least: title, DOI, original sentence, actual literature content, reasonableness assessment, issue level

6. Rendering

cd /path/to/check-review-alignment
python3 scripts/run_ai_alignment.py --work-dir "/path/to/work_dir" --render

Core principles

• Do not change for the sake of changing
• Do not touch when it cannot be confirmed
• Only change necessary sentences
• Preserve all LaTeX command structures

References and verification

• See configuration in config.yaml
• Script entry point:scripts/run_ai_alignment.py
• Rendering dependencies:systematic-literature-review