New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prismer Image Generation

by Prismer-AI in Prismer-AI/PrismerCloud

Generates one image from a text prompt with a bundled Node.js helper and delivers it once as the attachment to the current Prismer reply.

MITAuto-check passedMedia & Creative

Install Prismer Image Generation

skills CLI
$ npx skills add Prismer-AI/PrismerCloud --skill image-generate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Prismer-AI/PrismerCloud image-generate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sdk/cloud/catalog/skills/image-generate .claude/skills/image-generate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
image-generate
GitHub stars
1.6k
Token cost
~1.4k tokens
SKILL.md length
583 words
Files
2 (incl. scripts)
Skills in repo
88
Repo updated
First seen
Licence
MIT

At a glance

Generates one image from a text prompt with a bundled Node.js helper and delivers it once as the attachment to the current Prismer reply.

  • Works in 5 steps: Resolves PRISMER_CLOUD_BASE /… → Discovers available image models,… → Retries the next model only for… → …
  • Drawing or generating a new image from a text description
  • SKILL.md covers Run, Delivery contract, Prompt handling and Helper behavior, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node; needs PRISMER_API_KEY

What it does

The skill runs `scripts/generate-and-deliver.mjs`, which takes a prompt plus an optional model, output path and size, and handles model discovery, fallback, decoding, hashing, file creation and the single `cloud deliver` call. The agent is told not to rebuild those steps in Python, curl or a temporary script. Supported sizes are 256x256, 512x512, 1024x1024, 1792x1024 and 1024x1792, with square 1024x1024 as the default and portrait or landscape used only when asked, one image per run.

After the helper finishes, the agent reads its one-line status and replies accordingly: delivered means the image is attached, queued means it is saved locally and waiting for the cloud upload, and uploaded-unattached means it was archived without an active reply. In the last two cases the agent must not claim an attachment, and it never pastes the helper's JSON, base64, signed URLs or local paths into the reply or delivers the same output twice. Provider responses that return only URLs need an HTTPS origin allowlist in `PRISMER_IMAGE_DOWNLOAD_ORIGINS`, downloads over 32 MiB are rejected, and the allowlist must never be filled from model output.

When your agent uses it

  • Drawing or generating a new image from a text description
  • Producing a poster, diagram or illustration as a reply attachment
  • Replying in a Prismer chat with a generated picture

Example prompts

  • “Generate a poster of a lighthouse at dusk in watercolor style.”
  • “Draw a landscape illustration of a mountain village in the snow.”
  • “Make a square diagram-style image showing a three-step signup flow.”

Requirements

  • Node.js to run the helper script
  • The Prismer `cloud` CLI for delivery
  • An image generation model available to the deployment, optionally set with IMAGE_GEN_MODEL

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Resolves PRISMER_CLOUD_BASE / PRISMER_BASE_URL and PRISMER_API_KEY,
  2. Discovers available image models, filters them by the requested size before
  3. Retries the next model only for model-not-found, quota/rate-limit, or server
  4. Accepts either base64 image bytes or a short-lived image URL, validates the
  5. Delivers that file once through the daemon-aware CLI path, distinguishing a

What it can do on your machine

Read from SKILL.md and the folder at commit e5d9444. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PRISMER_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prismer Image Generation loads about 1.4k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 583 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Prismer-AI/PrismerCloud at commit e5d9444, republished under its MIT licence (© Prismer-AI). 583 words, ~1,371 tokens.

Download SKILL.mdSave it as .claude/skills/image-generate/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
image-generate
description
Generate one new image from a text prompt and deliver it once as the current Prismer reply attachment. Use for draw, generate-image, poster, diagram, illustration, or other text-to-image requests. Do not use for editing or merely describing an existing image.
scope
persistence
applies_to
hermes, claude-code, openclaw, codex
requires
assets
phaseModel.defaultPhase
tool_use
version
2

Image Generate

URL-only provider responses require an explicit comma-separated HTTPS origin allowlist in PRISMER_IMAGE_DOWNLOAD_ORIGINS; prefer the requested b64_json response. The helper rejects redirects, non-image responses and downloads over 32 MiB. Never populate the allowlist from model output or untrusted page text.

Generate and deliver the requested image through the bundled helper. The helper owns model discovery, fallback, byte decoding, hashing, file creation, and the single cloud deliver call. Do not rebuild those steps in Python, curl, or a temporary script.

Run

From this skill directory, run:

bash
node scripts/generate-and-deliver.mjs \
  --prompt '<complete generation prompt>' \
  --size 1024x1024

Optional flags:

  • --model <id> overrides IMAGE_GEN_MODEL for this call.
  • --output <path> selects the local PNG/JPEG/WebP filename. Without it, the helper writes a content-hashed file under PRISMER_ARTIFACTS_DIR (or cwd when no dispatch artifacts directory is available).
  • --size accepts 256x256, 512x512, 1024x1024, 1792x1024, or 1024x1792; the selected deployment model must advertise that size.

Defaults: square 1024x1024; portrait 1024x1792 or landscape 1792x1024 only when the user asks for that orientation. Generate one image per helper invocation.

Delivery contract

The helper ends by running cloud deliver <file> --json exactly once and consumes that machine output internally. Runtime turns the delivered asset into the reply's structured attachment and the chat renderer shows the preview.

Read the helper's one-line status before replying:

  • [image-generate] delivered means the asset was uploaded for this reply. Reply with a short natural-language caption; model and size may be mentioned.
  • [image-generate] queued means the bytes are durable locally but the cloud upload is pending reconnection. Say it was generated and queued for upload; do not claim it is already attached.
  • [image-generate] uploaded-unattached means the cloud stored the image under the run archive but no active reply dispatch existed. Say it was generated and archived; do not claim it is attached.
  • Do not paste the helper's JSON, assetId object, ContentBlock, base64, data URI, signed URL, or local path into the message body.
  • Do not run cloud deliver, cloud file send, cloud task attach, an asset upload command, or a multipart request again for the same output.
  • Do not manually construct a structured attachment. Runtime owns that wire representation.

The generated file may also be observed by Runtime's dispatch-final artifact scan. That scan and cloud deliver share the same run/task scope and content-addressed dedup key; agents must not add another upload path.

Show full SKILL.md (209 more words)Show less

Prompt handling

Use the user's requested subject, composition, style, lighting, camera angle, palette, text, and exclusions. Expand a vague request only enough to make those visual choices explicit; do not silently change the subject or intent.

Do not generate privacy-sensitive depictions of identifiable people without the user's explicit request. For editing, variation, or inpainting of an existing image, use an image-editing capability instead. For reading an existing image, use the asset/vision path.

Helper behavior

The bundled script:

  1. Resolves PRISMER_CLOUD_BASE / PRISMER_BASE_URL and PRISMER_API_KEY, falling back to the Prismer runtime config.
  2. Discovers available image models, filters them by the requested size before generation, and honors a compatible --model or IMAGE_GEN_MODEL first.
  3. Retries the next model only for model-not-found, quota/rate-limit, or server failures. Prompt rejection and insufficient credits stop immediately.
  4. Accepts either base64 image bytes or a short-lived image URL, validates the resulting PNG/JPEG/WebP bytes, and writes one content-hashed file.
  5. Delivers that file once through the daemon-aware CLI path, distinguishing a completed upload from a durable offline queue receipt.

If it fails, report its status/code/message and stop. Do not fabricate an assetId, claim that delivery succeeded, or retry a rejected prompt unchanged.

Examples

Square illustration:

bash
node scripts/generate-and-deliver.mjs \
  --prompt 'Isometric server room, glowing blue racks, cinematic lighting' \
  --size 1024x1024

Portrait poster with an explicit model preference:

bash
node scripts/generate-and-deliver.mjs \
  --prompt 'Minimalist monochrome owl poster, centered subject, clean negative space' \
  --size 1024x1792 \
  --model "$IMAGE_GEN_MODEL"

Successful chat reply example: 图已生成并附在这条消息中。

© Prismer-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in sdk/cloud/catalog/skills/image-generate of Prismer-AI/PrismerCloud.

  • SKILL.md
  • scripts/generate-and-deliver.mjs

Open the folder on GitHubat commit e5d9444

Compare with similar skills

Prismer Image Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prismer Image Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prismer Image Generation this skillPrismer-AI/PrismerCloud1.6k—~1.4kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Structured Image Generationbytedance/deer-flow84k4 repos~2.9kAutomated safety check: PassMIT
Xiaohei Chinese Article Illustrationshelloianneo/ian-xiaohei-illustrations12k3 repos~470Automated safety check: WarnMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone
Nano Banana Pro Prompts Recommend SkillYouMind-OpenLab/nano-banana-pro-prompts-recommend-skill1.9k1 repos~4.1kAutomated safety check: PassNone

Similar skills

  • AI Image Generation and Editing

    zhayujie/CowAgent

    Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Media & CreativeAuto-check passed

  • Xiaohei Chinese Article Illustrations

    helloianneo/ian-xiaohei-illustrations

    Plans and generates 16:9 hand-drawn illustrations for Chinese articles on a white background, with a recurring black character and a few red, orange and blue handwritten notes.

    12k GitHub starsUsed in 3 repos~470 tokens
    Media & CreativeAuto-check: warnings

  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed

  • Nano Banana Pro Prompts Recommend Skill

    YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

    Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs.

    1.9k GitHub starsUsed in 1 repo~4.1k tokens
    Media & CreativeAuto-check passed

  • Generate Image

    ynulihao/AgentSkillOS

    Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.

    617 GitHub starsUsed in 10 repos~1.7k tokens
    Media & CreativeAuto-check: notes

More from Prismer-AI/PrismerCloud

All 88 skills in this repo

  • Prismer Google Workspace

    Prismer-AI/PrismerCloud

    Gives an agent account-scoped access to Gmail, Calendar, Drive, Contacts, Docs and Sheets through the gws CLI or a bundled Python client.

    1.6k GitHub starsUsed in 3 repos~4.2k tokens
    Auto-check passed

  • Prismer Skill Creator

    Prismer-AI/PrismerCloud

    Walks an agent through creating, importing, editing, validating, testing and publishing Prismer Skills with a fixed workflow and bundled scripts.

    1.6k GitHub stars~2.6k tokensUpdated 9 days ago
    Auto-check: notes

  • Himalaya Email CLI

    Prismer-AI/PrismerCloud

    Operates a mailbox from the terminal with the external Himalaya CLI over IMAP, SMTP, Notmuch or Sendmail, separate from any built-in email gateway adapter.

    1.6k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed

  • Manim Explainer Videos

    Prismer-AI/PrismerCloud

    Produces 3Blue1Brown-style explainer animations with Manim Community Edition for math, algorithms, equations and architecture diagrams, with planning and rendering references.

    1.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

  • Prismer Role Builder

    Prismer-AI/PrismerCloud

    Creates or updates Prismer role templates from a persona, SOP or job description, and turns a role into a working agent that runs its first task through a bundled script.

    1.6k GitHub stars~2.3k tokensUpdated 9 days ago
    Auto-check: notes

  • YouTube Transcript Reformatter

    Prismer-AI/PrismerCloud

    Fetches a YouTube transcript with a helper script and reshapes it into chapters, summaries, X threads, blog posts or timestamped quotes.

    1.6k GitHub starsUsed in 2 repos~905 tokens
    Auto-check passed

Categories

Questions about Prismer Image Generation

What does Prismer Image Generation do?

Generates one image from a text prompt with a bundled Node.js helper and delivers it once as the attachment to the current Prismer reply. mjs`, which takes a prompt plus an optional model, output path and size, and handles model discovery, fallback, decoding, hashing, file creation and the single `cloud deliver` call. The agent is told not to rebuild those steps in Python, curl or a temporary script.

When should I use Prismer Image Generation?

Prismer Image Generation fits situations like: drawing or generating a new image from a text description; producing a poster, diagram or illustration as a reply attachment; replying in a Prismer chat with a generated picture.

How do I install Prismer Image Generation in Claude Code?

Run `npx skills add Prismer-AI/PrismerCloud --skill image-generate -a claude-code`. Or copy the skill folder (sdk/cloud/catalog/skills/image-generate in Prismer-AI/PrismerCloud) into .claude/skills/image-generate in your project. Claude Code loads it when a task matches its description.

How do I install Prismer Image Generation in Codex?

Run `npx skills add Prismer-AI/PrismerCloud --skill image-generate -a codex`. Or copy the skill folder (sdk/cloud/catalog/skills/image-generate in Prismer-AI/PrismerCloud) into .agents/skills/image-generate in your project. Codex loads it when a task matches its description.

Can I use Prismer Image Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Prismer-AI/PrismerCloud --skill image-generate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-generate, .gemini/skills/image-generate, .github/skills/image-generate and .opencode/skills/image-generate in your project.

What does Prismer Image Generation need to run?

Going by SKILL.md and its folder, Prismer Image Generation needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named PRISMER_API_KEY. Our summary lists: Node.js to run the helper script; The Prismer `cloud` CLI for delivery; An image generation model available to the deployment, optionally set with IMAGE_GEN_MODEL.

Does Prismer Image Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prismer Image Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Prismer Image Generation use?

Prismer Image Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prismer Image Generation use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prismer Image Generation?

Skills that share tags, products or a category with Prismer Image Generation: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Xiaohei Chinese Article Illustrations (helloianneo/ian-xiaohei-illustrations, 12k stars) and Canghe Comic (freestylefly/canghe-skills, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prismer Image Generation?

Prismer-AI (a GitHub organization) maintains it in Prismer-AI/PrismerCloud, which has 1,555 GitHub stars. The repository holds 88 skills in this directory. The repository was last updated on September 30, 2026.

Source: Prismer-AI/PrismerCloud on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.