deck-review-rubric
Review a deck against a rubric instead of taste — the five dimensions (argument, evidence, density, arc, honesty), the severity-sorted feedback that separates broken from suboptimal, and the review conversation that improves the deck without rewriting it in the reviewer's voice. Use when asked review my deck, give feedback on this presentation, is this ready for the board, or our deck reviews are just font opinions. Produces the rubric scores with evidence, the severity-sorted feedback, the two-fixes-that-matter-most call, and the reviewer discipline notes.
npx skills add mohitagw15856/pm-claude-skills --skill deck-review-rubric --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Deck Review Rubric Skill Deck reviews default to taste: font opinions, color takes, and "I'd reorder this" — the reviewer's aesthetic imposed at slide grain while the deck's actual failure (no argument, no ask, dishonest chart) sails through unexamined. The rubric reviews what decks fail at: **argument** (do the headlines make a case — [deck-outline-first](../deck-outline-first/SKILL.md) skim test), **evidence** (does each slide prove its claim — [evidence-grading](../evidence-grading/SKILL.md) weight), **density** (billboard or wall — [slide-density-rules](../slide-density-rules/SKILL.md)), **arc** (does tension carry the room — [deck-narrative-arc](../deck-narrative-arc/SKILL.md)), and **honesty** (axes, claims, caveats — [citation-hygiene](../citation-hygiene/SKILL.md)). Findings sort by severity — broken beats suboptimal beats taste — and the review ends with the only sentence presenters can act on: the two fixes that matter most. ## What This Skill Produces - **The rubric scores** — the five dimensions, each with the evidence for its score (cited slides, not vibes) - **The severity-sorted findings** — 🔴 broken (would fail in the room) / 🟡 suboptimal (costs force) / ⚪ taste
- What This Skill Produces
- Required Inputs
- Framework: The Rubric Rules
- Output Format
- Rubric Scores
- Findings (severity-sorted)
- The Two Fixes
- On Your Stated Worry
- Quality Checks
- Anti-Patterns
What does the deck-review-rubric skill do?
Review a deck against a rubric instead of taste — the five dimensions (argument, evidence, density, arc, honesty), the severity-sorted feedback that separates broken from suboptimal, and the review conversation that improves the deck without rewriting it in the reviewer's voice. Use when asked review my deck, give feedback on this presentation, is this ready for the board, or our deck reviews are just font opinions. Produces the rubric scores with evidence, the severity-sorted feedback, the two-fixes-that-matter-most call, and the reviewer discipline notes.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill deck-review-rubric --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
