The Data Analysis Handover Brief
Give your team the context, structure and standards to run analysis without you
You have built a useful analysis process, but every time someone else tries to run it, they make different assumptions or miss steps. The output quality varies wildly depending on who does the work.
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
Analysts and managers preparing colleagues to run recurring data work independently
How it works
The skill file does five things, in this order.
1. Document the business question behind each metric. Write why each data point matters, not just what it measures, so the team knows what decisions depend on it.
2. List the judgment calls you make during analysis. Capture how you handle outliers, incomplete data, seasonal adjustments and edge cases so others can replicate your reasoning.
3. Create a quality checklist with pass or fail criteria. Define specific thresholds for data completeness, sample size, variance and other quality markers before sharing results.
4. Build an interpretation guide for common patterns. Show what normal fluctuations look like versus signals that need action, with examples from past periods.
5. Schedule review sessions after the first three handovers. Compare outputs side by side, discuss where interpretations differed, and update your documentation based on real confusion points.
What comes back
A handover document that captures not just process steps but the thinking framework, so analysis quality stays consistent across team members
The mistake to avoid
The first person to take over your analysis will find gaps you did not document because they were obvious to you. Treat their questions as free quality assurance for your handover brief.
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 helping me create a handover brief for a data analysis process that my team will run regularly.
Analysis description:
{brief description of what the analysis does and what decisions it supports}
Current process:
{outline of steps currently followed}
Data sources:
{list of data sources, systems, or files used}
Known complications:
{list any data quality issues, seasonal factors, or edge cases you currently handle manually}
Please create a structured handover document that includes:
1. Business context: why this analysis exists and what decisions depend on it
2. Judgment call guide: specific rules for handling outliers, missing data, thresholds, and edge cases
3. Quality checklist: measurable criteria that must be met before results are shared
4. Interpretation framework: what normal variation looks like versus actionable signals, with numeric examples
5. Common mistakes: errors you have seen or made, and how to avoid them
6. Review questions: what the person running this should ask themselves before finalizing
Format this as a reference document that someone can follow independently. Use specific numbers and examples rather than general principles where possible.