One Briefing Format, Every Analyst
Get your team to produce consistent briefings from messy sources without writing a manual
You ask two people to summarise the same pile of market reports and get back two documents that cannot be compared. One loves bullet points, the other writes prose, and the third buries key conflicts on page four.
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
Managers who need three analysts to deliver comparable briefings, not three different styles
How it works
The skill file does five things, in this order.
1. Document your briefing sections in a shared note. List the headings you want in every briefing: executive summary, source list, key disagreements, data gaps.
2. Build the template prompt with your team watching. Screen-share while you write the prompt, explain each instruction, and let them suggest the output length and tone.
3. Run the same source batch through the prompt twice. Feed Kimi identical files in two separate sessions to show the team that structure stays constant even when wording varies.
4. Let each person test the prompt on their own sources. Give the team a week to run their current projects through the template and report what sections need adjustment.
5. Store the final prompt where everyone updates the same version. Put it in a shared document with edit history so refinements do not fork into six private copies.
What comes back
Four people upload different reports and produce briefings that follow the same structure, use the same headings, and surface conflicts in the same place
The mistake to avoid
Version the prompt with a date in the file name so you can roll back when someone's edit breaks the output. Review the shared document monthly and archive instructions that no longer serve the team's current work.
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
You are a research analyst producing a standardised briefing from multiple source documents.
I will upload {number} files covering {topic}.
Produce a briefing with exactly these sections:
1. Executive Summary ({word_count} words maximum): the single most important finding across all sources.
2. Source List: title, author, publication date, and document type for every file.
3. Points of Agreement: claims or data points that appear in at least {threshold} sources with minimal variation.
4. Key Disagreements: wherever sources contradict each other on {specific_issue}, state each position and name which source holds it.
5. Data Gaps: questions raised by the sources that none of them answer, or metrics mentioned by one source but missing from others.
6. Methodology Notes: any differences in how sources collected data, defined terms, or scoped their analysis.
Use {heading_style} for section titles. Write in {tone}. Do not editorialize or infer claims not present in the uploaded material. When citing a source, use the file name in brackets.