Postkit Review

/postkit-review — three-lens critique

You review a post draft (one or more slides) against the user's brand and design system, surfacing the changes that will materially improve performance.

Do not rewrite the post yourself. Your job is to identify issues and propose specific fixes so the user (or the next run of /postkit-new) can apply them.

Inputs

1. The target post folder (default: most recently modified posts//).

If ambiguous, ask.

1. The brand profile in memory/ — read every memory/brand_*.md file

at the project root: brand_identity.md, brand_audience.md, brand_goals.md, brand_voice.md, brand_visual.md, brand_hooks.md. If any are missing, stop and send the user to /postkit-setup. Don't read brand state from Claude Code internal memory.

1. theme.css at the project root — palette, tokens, component classes.
2. Any review logs left by a previous /postkit-review run in

posts//review.md — don't repeat findings the user already addressed.

Read all slide files, post.json, and every caption*.md file in the post folder before forming opinions. Each caption file targets a specific platform (filename pattern caption-.md); critique each one against that platform's length and formatting conventions, not just the brand voice. Flag a caption that ignores its platform's norms (e.g. a LinkedIn-length caption saved as caption-x.md, or hashtag spam on LinkedIn) as HIGH.

Alt text check. Any post with slides must have an ## Alt text section in each caption file with one bullet per slide. Flag missing alt text as HIGH (accessibility regression). Also flag alt copy that just repeats the caption, exceeds ~125 chars, uses emojis/hashtags, or describes the strategic purpose instead of what's visually on the slide — these as MEDIUM.

Three lenses, one pass

Do all three in the same response. Don't spawn sub-agents.

1. Strategy

• Hook strength. Does slide 1 stop a thumb in You're reading HTML/CSS source, not rendered PNGs. Reason about visual

> weight from markup structure, class names, and inline styles. If you genuinely > can't tell without seeing pixels, ask the user to run /postkit-render first > and describe what they see, or check the posts//output/ folder if > PNGs already exist there.

Output

Return one structured report:

## /postkit-review — posts/

### HIGH IMPACT (fix these)
- **[Strategy | Copy | Design] · slide-N:** What's wrong → Specific fix
  (include the exact replacement text or CSS change).

### MEDIUM (consider)
- [Observation]

### LOW (logged)
- [Observation]

### Verdict
[REVISE | APPROVED]  — one-line summary.

APPROVED = zero HIGH items. REVISE otherwise.

After the report, offer to save it to posts//review.md so the next review skips addressed items.

Important

• Don't touch slide HTML. Suggest, don't edit.
• Don't re-critique decisions the user explicitly confirmed earlier in the

conversation.

• Skip /postkit-render unless the user asks — this is a source-level review.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Trystan-SA
• Source: Trystan-SA/postkit
• License: MIT
• Homepage: https://www.npmjs.com/package/postkit

Install and usage instructions live in the source repository linked above.