# Visual Package

> Build a visual sequence that proves, explains, and supports decisions.

- Skill: `lionelndong/visual-package` (Agent Skill)
- Install (CLI): `npx skillmds@latest add lionelndong/visual-package`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lionelndong/visual-package/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: lionelndong (https://skillmd.com/u/lionelndong)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/lionelndong/visual-package

---


# Visual Package

## Rules

- Every publish requires a topic-specific SFW 16:9 cover/OG with no fake text, watermark, garbled lettering, or generic stock treatment.
- Product-led articles require a real product screenshot or action-shot; never fake product UI with generated imagery.
- Visuals must be useful, not decorative or table-only.
- Articles over 1,500 words use at least three roles; use the length minimums: under 1,200 words: 5; 1,200–2,000: 6; 2,000–3,000: 8; over 3,000: 10.

## Method

1. Produce the planned role mix: cover, proof, explanation, comparison/decision support, and evidence where relevant.
2. Verify files exist, load, have non-zero dimensions, and have accurate alt text or a documented decorative exception.
3. Store generated-image prompts when used and inspect output for malformed diagrams, unreadable labels, and generic visuals.
4. Build a manifest listing file, role, location, alt text, source/proof, and validation result.

## Output

All visual assets, manifest, cover/OG choice, and visual-proof score.