Compare Methods Sections Across Papers
Spot methodological differences and gaps when reviewing multiple studies at once
Reading five papers on the same topic reveals contradictory results, but you cannot explain why without re-reading every methods section in detail. Manual comparison tables take hours and you still miss subtle differences in sample size, measurement tools or statistical tests.
That is the gap this drop closes. It is a data & analysis skill built for Kimi, and it takes about ten minutes to set up the first time. After that it runs in under a minute.
Who should use it
Researchers, analysts and consultants who need to synthesise findings from multiple technical papers for reports or decisions
How it works
The skill file does five things, in this order.
1. List your comparison dimensions. Decide which methodological elements matter for your question: sample characteristics, data collection method, analysis technique, controls, timeframe.
2. Feed papers with structured extraction. Upload each paper and ask Kimi to extract only your chosen dimensions in a consistent format, one paper at a time.
3. Request a comparison table. Ask Kimi to combine all extractions into a single table with papers as rows and your dimensions as columns.
4. Identify outliers and patterns. Scan the table for papers that differ significantly on key dimensions, then ask Kimi to explain how those differences might affect results.
5. Generate a methodology critique. Ask Kimi to draft two paragraphs describing which studies used stronger methods and which limitations matter most for your context.
What comes back
A comparison table showing methodological variation across studies, plus a written assessment of which differences explain conflicting findings
The mistake to avoid
Keep your dimension list under seven items or the table becomes unreadable. If papers use different terminology for the same concept, give Kimi synonyms in your extraction prompt so it can normalise entries.
Running it
Paste the prompt block into a new Kimi chat and attach your files in the same message. Kimi's long context means you should upload everything at once rather than in batches, splitting the input is what causes it to lose cross-references between documents.
Where this fits
On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.
In the file
I am comparing methodology across multiple research papers on {research_topic}. I need you to extract specific methodological details in a consistent format.
For the paper I am uploading, extract the following dimensions:
1. Sample size and composition: {e.g. number of participants, demographics, inclusion criteria}
2. Data collection method: {e.g. survey, interview, experiment, observational}
3. Measurement instruments: {e.g. specific scales, tools, metrics used}
4. Analysis technique: {e.g. regression, thematic analysis, statistical tests}
5. Control variables: {e.g. what factors were controlled for}
6. Study timeframe: {e.g. cross-sectional, longitudinal duration}
7. {add your own dimension if needed}
For each dimension, provide:
- The exact detail from the paper
- Page number or section where found
- Note if the information is not reported
Use consistent terminology across papers. If the paper uses synonyms like "questionnaire" and "survey", standardise to one term.
Format as a simple list, not prose. Mark any ambiguous or unclear methodological choices.
After I provide all papers, I will ask you to create a comparison table.