The Review That Spots What Numbers Miss
Find the patterns in team updates that explain why metrics moved
You summarise what happened each week, but the real value lies hidden in what keeps appearing across departments. By the time a pattern becomes obvious, you have lost four weeks.
That is the gap this drop closes. It is a operations skill built for Claude, and it takes about ten minutes to set up the first time. After that it runs in under a minute.
Who should use it
Operations managers who already compile weekly reviews but want to extract strategic insights from recurring themes
How it works
The skill file does five things, in this order.
1. Feed Claude four weeks of completed reviews. Paste the last month of your weekly summaries into one conversation.
2. Ask for cross-cutting themes, not summaries. Request recurring blockers, dependencies, or resource mentions that appear in multiple weeks.
3. Map themes to your current metrics. Ask Claude which patterns might explain specific changes in your KPIs or project timelines.
4. Generate questions for next week's check-ins. Turn each pattern into a specific question you can ask team leads to test your hypothesis.
5. Archive the pattern log separately. Keep Claude's theme analysis in a dedicated document that grows each month for quarterly planning.
What comes back
A living document of operational patterns that connects qualitative signals to quantitative results before problems compound
The mistake to avoid
Upload reviews as separate files rather than one long paste so you can reference specific weeks when Claude identifies a pattern. Name each file with the week ending date for faster navigation during follow-up questions.
Running it
Save this as SKILL.md inside a folder named after the skill, then drop the folder into your Claude Code skills directory or upload it to a Claude Project. Claude reads the frontmatter to decide when the skill applies, so keep the description line intact. For a one-off run, paste the prompt block directly.
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 attaching four weekly operations reviews from {date_range}.
Each review summarises updates from {number} teams covering {key_areas}.
Analyse these reviews for cross-cutting patterns:
1. Blockers or constraints mentioned by more than one team
2. Dependencies between teams that appear in multiple weeks
3. Resource mentions (budget, headcount, tools) that recur
4. Timing or deadline themes that affect multiple workstreams
5. External factors (supplier, regulatory, market) referenced repeatedly
For each pattern you identify:
- Note which weeks and which teams mentioned it
- Assess whether the pattern is escalating, stable, or resolving
- Suggest which of our current metrics might be affected
Then review these specific KPI changes from the same period:
{list_your_metrics_and_changes}
Which patterns you identified could plausibly explain these metric movements?
Finally, draft three to five specific questions I should ask team leads in next week's check-ins to test whether these patterns are actual drivers or coincidental.
Format your response as: Pattern name, Evidence (weeks and teams), Trend direction, Possible KPI link, Question to ask.