image-poster — Claude Code skill: what it does, how to install
image-poster builds structured prompts for posters and cover art, then runs a local CLI dispatcher. Saves finished PNG files directly to your project folder.
Apache-2.0 229 installs ★ 108,855 updated 2026-10-25
npx skills add nexu-io/open-design --skill image-poster -a claude-codeWhat image-poster does
The skill handles single-image creation for editorial covers and posters. Instead of calling provider APIs directly, the agent structures prompts across five layers: subject composition, lighting, palette anchors, camera settings, and negative constraints.
It defaults to gpt-image-2 while working with backends like Flux or Midjourney through upstream tools. Canvas ratios and active models are pulled from project metadata (imageModel, imageAspect). Missing $OD_BIN or $OD_PROJECT_ID environment variables will cause the generation call to fail.
The workflow yields one image per turn. The dispatcher writes the file directly to the project folder, followed by a brief summary from the agent.
What it helps with
- draft structured prompts for editorial posters and covers
- render single graphic assets with strict aspect ratios
- suppress AI image artifacts with targeted negative constraints
- dispatch render commands to a unified local media CLI
Example prompts for the agent
- Create an indie film festival poster with a bold silhouette on textured paper
- Generate cover art with soft studio lighting in a 16:9 aspect ratio
- Render a dark-toned visual asset for an upcoming music release
How to install image-poster
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill image-poster -a claude-code2Manually: put the files in place
~/.claude/skills/image-poster/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image-poster/
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill image-poster -a codex2Manually: put the files in place
.agents/skills/image-poster/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill image-poster -a cursor2Manually: put the files in place
.cursor/skills/image-poster/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nexu-io/open-design design-templates/image-poster/SKILL.md2Manually: put the files in place
.github/skills/image-poster/SKILL.md1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill image-poster -a gemini-cli2Platform CLI
gemini skills install https://github.com/nexu-io/open-design --path design-templates/image-posterManually: put the files in place
.devin/skills/image-poster/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill image-poster -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about image-poster
How do I install image-poster in Claude Code?
Run npx skills add nexu-io/open-design --skill image-poster -a claude-code in your terminal. This saves the skill definition to ~/.claude/skills/image-poster/SKILL.md.
What does the image-poster skill do?
It turns a design brief into a five-part structured prompt and runs your media dispatcher command. The generated graphic file lands straight in your project directory.
What dependencies does this skill require?
You need the project media dispatcher configured with $OD_BIN, $OD_NODE_BIN, and $OD_PROJECT_ID. The skill relies on this CLI layer instead of querying upstream APIs directly.
Source text
SKILL.md · Apache-2.0
---
name: image-poster
description: |
Single-image generation skill for posters, key art, and editorial
illustrations. Defaults to gpt-image-2 but is provider-agnostic — the
same workflow drives Flux, Imagen, or Midjourney via the active
upstream tooling. Output is one or more PNG/JPEG files saved to the
project folder.
triggers:
- "poster"
- "key art"
- "illustration"
- "image"
- "cover art"
- "海报"
- "插画"
od:
mode: image
surface: image
scenario: design
preview:
type: html
entry: example.html
design_system:
requires: false
example_prompt: |
Editorial poster for an indie film festival — one bold abstract
silhouette over a warm, slightly grainy paper background; hand-set
sans serif title at the top, festival dates and venue at the bottom
in monospace. Muted ochre + ink palette.
---
# Image Poster Skill
Produce **one** finished image asset per turn unless the user asks for
variations. Image generation rewards a tight, structured prompt — your
job is to assemble that prompt from the user's brief, then dispatch.
## Resource map
```
image-poster/
├── SKILL.md ← you're reading this
└── example.html ← what the resulting card looks like in Examples
```
## Workflow
### Step 0 — Read the project metadata
The active project carries `imageModel`, `imageAspect`, and (optional)
`imageStyle` notes. Use them as the upstream model + canvas + style
anchor. When a value is not provided, infer a safe default from the brief and
media contract. Ask only when the choice would materially change the requested
result and no safe default can be inferred.
### Step 1 — Compose the prompt
Plan in this exact order before calling any tool:
1. **Subject + composition** — what is in the frame, where, at what
scale; eye-line and crop.
2. **Lighting + mood** — natural / studio / moody; warm / cool; key
plus rim plus fill; time of day if outdoor.
3. **Palette + textures** — hex anchors when the user gave a brand
palette; otherwise a 3-word mood tag (e.g. "muted ochre + ink").
4. **Camera / lens** — only if the user wants photographic realism
("85mm portrait, shallow DOF") or a specific film stock.
5. **What to avoid** — common AI-slop patterns ("no extra fingers, no
warped text, no logo placeholders").
### Step 2 — Dispatch via the media contract
Use the unified dispatcher — do **not** call upstream provider APIs by
hand. Run from your shell tool:
```bash
"$OD_NODE_BIN" "$OD_BIN" media generate \
--project "$OD_PROJECT_ID" \
--surface image \
--model "<imageModel from metadata>" \
--aspect "<imageAspect from metadata>" \
--output "<short-descriptive-name>.png" \
--prompt "<the full assembled prompt from Step 1>"
```
The command prints one line of JSON: `{"file": {"name": "...", ...}}`.
The daemon writes the bytes into the project folder; the FileViewer
picks it up automatically.
### Step 3 — Hand off
Reply with a one-paragraph summary of the prompt you used and the
filename returned by the dispatcher (e.g. *I generated `hero-poster.png`
with `gpt-image-2` at 1:1.*). Do **not** emit an `<artifact>` tag.
## Hard rules
- One image per turn unless asked for variations.
- Honor `imageAspect` exactly — the upstream cost is the same; matching
the aspect avoids a re-render.
- No filler typography in the image itself unless the user asked for
in-frame text. Real copy beats lorem.
- Save every render — never describe an image without producing the
file. The user expects something to open in the file viewer.
© nexu-io · Apache-2.0 · nexu-io/open-design