Partner Review Checklist
SkillAI & modelsRuns a deck through a partner-grade review checklist covering story, titles, exhibits, layout, and consistency, returning a prioritized fix list before review.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Partner Review Checklist skill
What this skill tells your AI
The instructions your AI receives, as published by andreworia/claude-powerpoint-skills in skills/partner-review-checklist/SKILL.md and read by ahel’s review.
When to use
Use this before sending a deck to a partner, MD, or client. Use it as a self-review on your own deck after building. Use it when you have an hour before a review and need to know what to fix first.
What it does
It evaluates a deck against the standard a senior reviewer applies and returns a prioritized list of fixes. It checks the argument first, then the slide craft, so the most important problems surface before cosmetic ones.
Method
A partner reviews top-down: story before slides, message before format. Apply the checklist in that order so the prioritized list reflects real impact.
-
Story and answer. Is there one clear recommendation, stated up front? Does the deck answer the audience's actual question? Read the executive summary alone; can the decision be made from it?
-
Title chain. Read the action titles in sequence. Do they argue the case with no gaps? Is every title a claim, not a topic? Does each title match what its slide proves?
-
MECE and logic. Within each grouping slide, are the categories non-overlapping and complete? Does each section ladder up to a summary point? Any orphan slide that supports nothing?
-
Exhibit fit. Does each exhibit match its message (right relationship, right chart)? Is the one insight highlighted? Is there a comparison anchor? Any chart that implies a different conclusion than its title?
-
Slide craft. Alignment to a grid, consistent spacing, consistent type scale, brand palette, accent used once per slide for meaning, icons from one family, chart junk removed.
-
Density. One message per slide. Any overloaded slide to split, any thin slide to merge, detail pushed to backup.
-
Consistency across the deck. Same category in the same color and label everywhere. Consistent footnote and source style. Consistent number formatting and rounding.
-
Evidence and honesty. Every number on a slide traceable to a source. No claim beyond what the data shows. No invented figure. Assumptions stated where they matter.
-
The ask and next steps. Does the deck end with a clear decision or action? Is the ask explicit?
-
Prioritize. Sort findings: blockers (story or logic broken), majors (exhibit or title wrong), minors (alignment, color). Fix blockers first.
Inputs
- The full deck or a section of it.
- The audience and the decision being sought.
- The brand standard, if one applies.
Output format
Return findings grouped as Blockers, Majors, and Minors, each as a specific, actionable fix tied to a slide number. Lead with a one-line verdict on whether the deck is review-ready. End with the three highest-impact fixes to do first.
Example
Verdict: not yet review-ready, story is sound but two exhibits undercut their titles. Blockers: none. Majors: slide 6 title claims causation but the scatter only shows correlation, add the controlled comparison or soften the title; slide 9 pie chart with 11 slices, switch to a sorted bar. Minors: slides 3 and 12 use different colors for the same segment; round all currency to whole millions. Do first: fix slide 6 logic, fix slide 9 exhibit, unify segment color.
Signals
- GitHub stars
- 20
- Forks
- 5
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
partner-review-checklist- Source
- github.com/andreworia/claude-powerpoint-skills