review-paper-checks
Run a fast 3-agent mechanical check of an economics paper — spelling and grammar, internal consistency and cross-references, and unsupported claims. Reports fixable errors, not editorial judgment.
claesbackman · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add claesbackman/AI-research-feedback --skill review-paper-checks技能说明
name: review-paper-checks description: Run a fast 3-agent mechanical check of an economics paper — spelling and grammar, internal consistency and cross-references, and unsupported claims. Reports fixable errors, not editorial judgment. argument-hint: [optional: path/to/main.tex] allowed-tools: Read, Write, Edit, Glob, Grep, Bash, Agent disable-model-invocation: true
You are coordinating a mechanical error check of an economics paper. You will run 3 agents in parallel and consolidate their output into a single list of concrete, fixable defects.
What this skill does: finds things that are wrong — misspellings, grammar errors, numbers that disagree between text and tables, terminology that drifts, cross-references that point to nothing, sentences that claim more than the evidence supports.
What this skill does not do: judge the contribution, evaluate the identification strategy, propose additional analyses, or issue a publication recommendation. Those are editorial judgments and belong to /review-paper-light (fast) or /review-paper (full). Do not let the agents drift into them, and do not add such judgments yourself when consolidating.
Phase 1: Discover the Paper
If a file path is provided in $ARGUMENTS, use it as the main LaTeX file. Otherwise, auto-detect:
- Use Glob with pattern
**/*.texto list all .tex files (exclude_minted-*,build/,output/). - Identify the main document among the .tex files containing
\documentclassor\begin{document}. If several candidates match, discard beamer slides and files whose name or folder suggests an old draft or a response letter (response*,letter*,slides*,old*,archive/, etc.), then choose the candidate with the largest include-graph. If still ambiguous, ask the user. - Read the main file and extract all
\input{},\include{}, and\subfile{}references (recursively) to build the paper's include-graph. - Read all component .tex files. The file list passed to the agents is exactly the main file plus its include-graph — do not pass .tex files the paper does not include (old drafts, response letters, slides, notes).
- Use Glob to find table files:
**/Tables/**/*.tex,**/tables/**/*.tex,**/Table/**/*.tex,**/table/**/*.tex, root-level*table*.texand*Table*.tex. Keep only tables that are\input{}/\include{}d from the include-graph. - Use Glob to find the bibliography:
**/*.bib. Keep only files named in a\bibliography{},\addbibresource{}, or\begin{thebibliography}block within the include-graph. If the references are typed directly into a .tex file, note that instead.
Record:
- Full path of each .tex file
- Full path of each referenced table .tex file and .bib file
- Paper title, authors, and abstract
If no table files are found, warn the user: "No table .tex files were found in standard locations. Agent B can only check consistency across the prose, not against table source files."
Phase 2: Launch 3 Agents in Parallel
In a single message, launch all 3 agents using the Agent tool with subagent_type: "general-purpose".
Scope guard — prepend the following block verbatim to all three agents' prompts:
Review ONLY the files listed at the end of this prompt. Do not use Glob, Grep, or directory listings to discover other files, and do not open any file that is not on the list. In particular, ignore any previous review reports (
PAPER_CHECK_*.md,QUICK_REVIEW_*.md,PRE_SUBMISSION_REVIEW_*.md, anything in areviews/folder), referee reports, response letters, notes, README files, and old drafts — none of these may influence your review. Within the listed .tex files, treat%-commented-out lines and\todo{}content as if they do not exist: review only the live text of the paper.
Precision guard — prepend the following block verbatim to all three agents' prompts:
Every issue you report must be anchored to text that actually appears in the files. Quote the exact string from the source, and give the file name and the section or paragraph where it appears. Do not report an issue you cannot quote. Do not speculate about what a table or figure might contain — if you cannot read the value, skip it rather than flagging it. It is better to return five issues you are certain of than thirty you are not. You are checking for errors, not evaluating the paper's contribution, identification strategy, or suitability for publication — stay out of those judgments entirely.
AGENT A — Spelling, Grammar & Academic Style
You are a copy editor at a top economics journal. Read all .tex files in the following list. Ignore LaTeX commands (anything starting with \) unless they cause formatting problems. Focus on the prose.
What to check:
-
Spelling errors: Every misspelled word. Pay special attention to proper nouns (author names, place names, institution names), technical terms, and commonly confused pairs (affect/effect, principal/principle, complement/compliment, discrete/discreet).
-
Grammar errors: Subject-verb agreement, tense consistency (present tense for findings, past tense for what was done), article usage (a/an/the), dangling modifiers, comma splices, run-on sentences, sentence fragments.
-
Spelling convention consistency: Is the paper consistently US or UK English? Flag mixed usage (behavior/behaviour, analyze/analyse, labor/labour) and state which convention dominates.
-
Awkward or convoluted phrasing: Sentences that require re-reading. Quote the sentence and suggest a clearer alternative.
-
Style violations — flag every instance of:
- "interestingly", "importantly", "notably", "it is worth noting", "it is important to note", "needless to say", "obviously", "clearly" — delete these; let the finding speak for itself
- "very unique", "absolutely essential", "completely eliminate" — tautologies
- "significant" used to mean large or important (reserve "significant" for statistical sign