Twenty Sources, One Briefing
Feed it a folder of reports and get a briefing that names the disagreements.
Summarising twenty sources separately gives you twenty summaries. The value is in where they contradict each other and why.
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
Anyone who must form a view from a pile of conflicting documents.
How it works
The skill file does five things, in this order.
1. Load everything at once. Long context means no chunking and no lost cross-references.
2. Map claims, not documents. The unit of analysis is the claim, with every source that makes it.
3. Surface the contradictions. Where two credible sources disagree, and what would settle it.
4. Weight by source quality. Primary data beats a vendor whitepaper citing a vendor whitepaper.
5. Write the position. One page, with a confidence level on each key claim.
What comes back
A claim map, a contradiction register, and a one-page position with confidence levels.
The mistake to avoid
Ask for the contradiction register before the summary. If you read the summary first, you will anchor on it and stop noticing what the sources disagree about.
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
Analyse all attached sources together as one evidence base.
1. CLAIM MAP, every substantive claim, with the sources asserting it and the
sources contradicting it. Group by claim, not by document.
2. CONTRADICTION REGISTER, where credible sources disagree. For each: the
competing claims, the likely reason for the disagreement (method, date,
incentive, definition), and what evidence would settle it.
3. SOURCE WEIGHTING, rank sources by evidentiary quality. Flag any citing
another source in this set rather than primary data.
4. POSITION, one page. Each key claim carries HIGH / MEDIUM / LOW confidence
and names the sources behind it.
Produce sections 1 to 3 before section 4. Do not lead with the summary.