Thesis literature review
Skill lihongqing2001-gif/chinese-thesis-production-skills/skills/thesis-literature-review
Evidence-first Codex skills for guided Chinese STEM thesis production
npx -y skills add lihongqing2001-gif/chinese-thesis-production-skills --skill thesis-literature-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Plan, search, verify, synthesize, and deepen a Chinese STEM thesis literature review using authoritative reviews, primary studies, standards, statistics, and traceable figure candidates. Use for field mapping, subsection research, review structure, contradiction analysis, source-packet drafting, or controlled handoffs to ChatGPT and other web research interfaces.
SKILL.md
2.3 KB, as published. Nobody here has run it
Thesis Literature Review
Build the review from verified questions and evidence, not from generated prose.
Workflow
- Confirm the subsection question, scope, exclusions, audience, and link to the thesis design.
- Search public academic databases for candidates. Do not scrape Google Scholar result pages.
- Use authoritative reviews to map vocabulary, mechanisms, debates, and landmark work.
- Use primary studies, standards, or official statistics for narrow and quantitative claims.
- Route candidates through
thesis-evidence-engineering; only verified Zotero/BibTeX records may enter final prose. - Build a claim-centered synthesis using references/review-synthesis.md.
- Register publication figures as candidates with source, Figure number, panel meaning, relevance, and limitations.
- Audit whether the review establishes the unresolved question that the thesis actually addresses.
ChatGPT/web research
Read references/chatgpt-handoff.md. Generate a sanitized handoff package rather than pasting a private thesis or asking for “more references.” Treat every returned citation and figure as unverified.
python scripts/build_research_handoff.py research-brief.json \
--output-dir literature/web-handoff
Writing rules
- Organize by concept, mechanism, method, scale, design variable, or disagreement.
- Do not write a paper-by-paper catalog.
- Do not use one review to prove a primary experimental detail it merely cites.
- Do not claim that a figure supports a mechanism until every panel and condition has been inspected.
- Distinguish consensus, unresolved disagreement, method limitation, and thesis opportunity.
Completion
Return the search strategy, candidate pool, verified source packet, evidence matrix links, proposed review structure, figure candidate register, contradiction list, and unresolved evidence gaps.