Thesis research methods
Skill lihongqing2001-gif/chinese-thesis-production-skills/skills/thesis-research-methods
Evidence-first Codex skills for guided Chinese STEM thesis production
npx -y skills add lihongqing2001-gif/chinese-thesis-production-skills --skill thesis-research-methodsAssembled 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
Design and audit reproducible research methods for Chinese STEM thesis chapters, including materials, sample preparation, characterization conditions, controls, replicates, uncertainty, statistical analysis, method-result coverage, and cross-chapter method references. Use when methods are incomplete, detached from results, inconsistent across chapters, or unable to support stated conclusions.
SKILL.md
2.6 KB, as published. Nobody here has run it
Thesis Research Methods
Make every reported result reproducible and every conclusion method-appropriate.
Chapter method workflow
- State the chapter research question and comparison design.
- List only materials, reagents, samples, instruments, software, and standards used in this chapter.
- Record preparation steps with ordered operations, quantities, units, time, temperature, and environment where applicable.
- Record each measurement's instrument/model, conditions, calibration or quality control, replicates, preprocessing, and outputs.
- Define controls, independent versus technical replicates, exclusions, uncertainty, statistics, and significance rules before interpreting results.
- Map every result and claim to the methods and raw evidence that support it.
- When a method is unchanged from an earlier chapter, use an explicit cross-chapter reference rather than an isolated sentence with no identifier.
Read references/method-manifest.md before creating a method record and references/statistical-boundaries.md before using significance language.
Evidence boundaries
- Instrument presence does not establish that all settings were appropriate.
- A characterization method supports only properties within its measurement capability.
- Repeated readings from one preparation are not independent biological/material replicates.
- A fitted curve requires model definition, parameter meaning, goodness-of-fit, and residual checks.
- “Significant” requires a declared statistical test and design; a visible difference alone is not statistical significance.
- Missing conditions must be requested or marked blocked, not reconstructed from generic practice.
Tool
python scripts/audit_method_manifest.py chapters/chapter-2-methods.json \
--project-root . --strict --report reports/chapter-2-methods.json
Completion
Return a complete method manifest, chapter-ready method subsections, method-result-claim coverage, statistical limitations, and exact missing information. Do not write a completed-results narrative while required method conditions or evidence paths are absent.