PDF Render QA

SkillMedia

Lets your agent inspect rendered PDF pages to catch layout problems like clipped tables, figures, and text.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

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 PDF Render QA skill

About this skill

The open-source design agent and harness, better than Claude Design on academic communication artifacts production. This DesignHarness can also be used with any coding harness you like ( Codex/Claude Code/Kimi Code/Pi/OpenCode etc..) and any agentic model you want.

What this skill tells your AI

The instructions your AI receives, as published by yaxin9luo/autodesign in skills/common/pdf_render_qa/SKILL.md and read by ahel’s review.

Use for source or exported PDFs. Treat rendered pages as layout evidence; text extraction alone is insufficient.

Stage: enhance

Preserve page, figure/table, caption, and crop provenance in the brief. Require rendered-page inspection rather than relying on extracted text alone.

Stage: plan

Plan from rendered pages and selected crops; choose physical page size early. Keep review files under tmp/pdfs/. Read pdf_render_commands for supported tools.

Stage: critique

Render the current export and inspect clipping, tables, figures, glyphs, headers, page transitions, and physical page size. Treat visible defects as export findings.

Stage: repair

Fix HTML/CSS and source metadata before rasterization, then re-render. Report unavailable dependencies exactly. Read pdf_export_checks.

Signals

GitHub stars
229
Forks
10
Last commit
Sep 2026

ahel review

  • K1binfo
    installs-packages (in references/pdf_render_commands.md)

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Item type
skill
Key
pdf-render-qa
Source
github.com/yaxin9luo/autodesign