academic-research-skills / cites-review
AGENTS.md4 starsChanged 7 months agoMITView on GitHub
Review, format, and organize academic references following GB/T 7714-2015. Extract literature from CNKI. Cross-check and renumber citations. Document codes: [J] journal, [M] book, [D] thesis, [C] conference, [R] report, [S] standard, [P] patent, [N] newspaper, [EB/OL] web Rules: - Citation order numbering [1], [2], [3]... - English: half-width punctuation; Chinese: full-width - Max 3 authors, then 等 (CN) / et al. (EN) - No abbreviated author names - Watch for accidental spaces in English refs Required fields: author, title, type…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository10 other files it gives its agents.
- skills/docx-thesis-format/AGENTS.mdAGENTS.md
- skills/markdown-to-word/AGENTS.mdAGENTS.md
- authorial-rewriteSkill
- cites-reviewSkill
- docx-thesis-formatSkill
- html-slideSkill
- literature-reviewSkill
- markdown-to-nbu-mpaSkill
- markdown-to-wordSkill
- word-flowchartSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Document codes: [J] journal, [M] book, [D] thesis, [C] conference, [R] report, [S] standard, [P] patent, [N] newspaper, [EB/OL] web
- Distinctive: line 25
No abbreviated author names
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Citation & Reference Review
Review, format, and organize academic references following GB/T 7714-2015. Extract literature from CNKI. Cross-check and renumber citations.
When to Use
- User needs to check/fix reference formatting
- User wants to extract references from CNKI (知网)
- User needs to renumber references after document restructuring
- User wants to cross-check in-text citations vs reference list
GB/T 7714-2015 Quick Reference
Document codes: [J] journal, [M] book, [D] thesis, [C] conference, [R] report, [S] standard, [P] patent, [N] newspaper, [EB/OL] web
Format:
[序号] 作者.题名[类型].刊名/出版社.出版年,卷(期): 页码.Rules:
- Citation order numbering
[1], [2], [3]... - English: half-width punctuation; Chinese: full-width
- Max 3 authors, then
等(CN) /et al.(EN) - No abbreviated author names
- Watch for accidental spaces in English refs
Validation Checklist
Required fields: author, title, type code, year + type-specific fields (journal/volume/pages for [J], publisher/city for [M], institution for [D], URL+access date for [EB/OL])
Cross-check: grep -oP '\[(\d+)\]' paper.md | sort -un then compare against reference list.
CNKI Extraction Tools
Browser script (cnki_literature_extractor.js):
const extractor = new CNKILiteratureExtractor();
extractor.extractListPageInfo() // list page
extractor.extractCurrentDetailPage() // detail page + citations
extractor.getQuotes() // GB/T 7714, elearning, EndNote formats
extractor.exportToCSV() / .exportToJSON()Playwright (python/cnki_playwright_extractor.py):
extractor = CNKIPlaywrightExtractor(headless=False, delay=2000)
await extractor.init_browser()
await extractor.extract_list_page(url="...")MCP Server (lunwen/cnki-mcp-server/):
Node.js MCP server for Claude integration with CNKI.
Pandoc Citation Integration
pandoc paper.md --citeproc --bibliography=refs.bib --csl=gb-t-7714-2015-numeric.csl -o paper.docxDependencies
- pandoc (citeproc), playwright (Python), Node.js
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

