Skip to content
Agentmart
Submit a tool

panel-artist

Use only for fallback page-art generation when finished-page image2 output has failed text, layout, or repair requirements.

Skill by lhfer

IndexedMIT★ 25
Write a review

Chalk Labs

Need help deploying panel-artist?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lhfer-panel-artist

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use only for fallback page-art generation when finished-page image2 output has failed text, layout, or repair requirements.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/panel-artist

What's inside

Skill name
panel-artist
Description
Use only for fallback page-art generation when finished-page image2 output has failed text, layout, or repair requirements.
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Panel Artist

This is a fallback role. The default production role is `manga-page-director`, which sends image2 a whole-page finished comic brief including panels and text.

Use this role only when the user chooses separate layers or finished-page image2 output fails text/layout badly enough that a clean no-text art layer is needed.

Read `chapters/chNN/director-briefs/page-NNN-director-brief.md`, `visual-bible/style.md`, `visual-bible/characters/`, and `visual-bible/settings/`.

For each fallback page, prepare one image2 task that generates the complete no-text page art with multiple panels already arranged.

- target output path, such as `chapters/chNN/page-art/page-001.png`
- page layout, such as `splash`, `2x2`, or `3x2`
- every panel beat on that page
- selected reference images
- reference image purpose
- source span, character version, setting version, and key prop requirements
- image2 prompt
- page aspect ratio
- A4 portrait production target, 2480x3508 px or higher, minimum short edge 2048 px
- explicit instruction: no text, captions, SFX, signs, subtitles, or speech bubbles inside the fallback image

Use AI's visual advantage. Each page should feel worth pausing on: richer background detail, stronger lighting, more expressive gestures, and clearer magical/action effects than a rushed human production page. Do not let detail destroy readability; preserve clean silhouettes, focal hierarchy, and lettering space.

Reference priority:

1. character `face-canonical.png`
2. matching wardrobe view
3. expression reference if needed
4. setting reference if available

When reference count is too high, keep main characters, their approved face/wardrobe references, and story-critical settings first.

Panel-level image generation is only a fallback for diagnostics. The default production path is whole-page finished-page generation from director briefs.

Leave practical lettering space in the art. The page should be visually exciting, but faces, hands, major action silhouettes, and key props cannot be covered by the later text layer.

From lhfer/codex-novel-to-comic-studio, MIT.

More from lhfer/codex-novel-to-comic-studio

Signals

Stars
25
Forks
5
Open issues
0
Last commit (this folder)
May 19, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from lhfer

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get panel-artist running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying panel-artist?

CallGet help
Cite this page

panel-artist skill. Agent Mart. https://agentmart.dev/skills/lhfer-panel-artist (last updated 2026-10-24)