Agent skill

Seedream Prompting

by nodetool-ai in nodetool-ai/nodetool

Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must…

AGPL-3.0Auto-check passedMedia & Creative

Install Seedream Prompting

skills CLI
$ npx skills add nodetool-ai/nodetool --skill seedream-prompting -a claude-code

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

GitHub CLI
$ gh skill install nodetool-ai/nodetool seedream-prompting --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/nodetool-ai/nodetool.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/system-skills/seedream-prompting .claude/skills/seedream-prompting && 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
seedream-prompting
GitHub stars
560
Token cost
~1.4k tokens
SKILL.md length
748 words
Files
1
Skills in repo
127
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must…

  • Works in 6 steps: Format — the deliverable. "Fashion… → Subject — identity, wardrobe, materials,… → Composition — where things sit and how… → …
  • The model id names Seedream 4
  • SKILL.md covers Six layers, in this order, Word budget, Text in the image and Editing: pin before you change, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Seedream Prompting is an agent skill from nodetool-ai/nodetool. Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing up to ten references by content instead of by index, and the size to iterate at versus the size to deliver. Use whenever the model id names Seedream 4 or 5 (bytedance/seedream/v5/pro/text-to-image, bytedance/seedream/v5/lite/edit, fal-ai/bytedance/seedream/v4.5/edit…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Image generation and Image editing. It works with fal. The repository describes itself as: Agent-first Creative Workspace. The licence is AGPL-3.0.

When your agent uses it

  • The model id names Seedream 4
  • 5 (bytedance/seedream/v5/pro/text-to-image
  • Bytedance/seedream/v5/lite/edit
  • Fal-ai/bytedance/seedream/v4.5/edit

Example prompts

  • “/seedream-prompting”

Workflow steps

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

  1. Format — the deliverable. "Fashion editorial magazine cover", "packshot
  2. Subject — identity, wardrobe, materials, styling. Concrete beats
  3. Composition — where things sit and how the frame is cut. "Subject on the
  4. Lighting — direction and quality. "Hard key from camera left, deep
  5. In-image text — the exact copy, in quotes, with its position.
  6. Style — the aesthetic anchor. "Editorial photorealism, 85mm, shallow

What it can do on your machine

Read from SKILL.md and the folder at commit 339f069. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • fal.ai
    • runware.ai

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Seedream Prompting loads about 1.4k tokens when it runs. Until then it costs about 196 tokens; SKILL.md has 748 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~196
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); files beside SKILL.md are not scanned.

SKILL.md

The full file from nodetool-ai/nodetool at commit 339f069, republished under its AGPL-3.0 licence (© nodetool-ai). 748 words, ~1,429 tokens.

Download SKILL.mdSave it as .claude/skills/seedream-prompting/SKILL.md (or your agent's skills folder).
name
seedream-prompting
description
Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing up to ten references by content instead of by index, and the size to iterate at versus the size to deliver. Use whenever the model id names Seedream 4 or 5 (bytedance/seedream/v5/pro/text-to-image, bytedance/seedream/v5/lite/edit, fal-ai/bytedance/seedream/v4.5/edit, fal-ai/bytedance/seedream/v4/text-to-image, bytedance/seedream-v5.0-pro/edit, bytedance/seedream-v4.5, seedream/5-pro-image-to-image, seedream/4.5-text-to-image, bytedance/seedream-4.5) on generate_image, edit_image or a TextToImage node. Not for Seedream 3.

Seedream → a production brief, not a caption

Seedream rewards a brief written the way you would hand one to a retoucher: what the deliverable is, who is in it, where everything sits, how it is lit, what it says, and what it looks like. Captions get caption results.

Reach it with find_model for text_to_image or image_to_image, then generate_image / edit_image.

Six layers, in this order

Earlier clauses carry more weight, so the order is part of the instruction.

  1. Format — the deliverable. "Fashion editorial magazine cover", "packshot on plain white", "streaming poster".
  2. Subject — identity, wardrobe, materials, styling. Concrete beats flattering: "a woman in her 40s, close-cropped grey hair, oversized charcoal wool coat" over "a stylish woman".
  3. Composition — where things sit and how the frame is cut. "Subject on the left vertical third, product centred at the lower edge, generous headroom".
  4. Lighting — direction and quality. "Hard key from camera left, deep falloff, one bounce card filling the shadow side".
  5. In-image text — the exact copy, in quotes, with its position.
  6. Style — the aesthetic anchor. "Editorial photorealism, 85mm, shallow focus, muted film grade".

An omitted layer is a decision handed to the model's defaults, and its defaults are centred, evenly lit and generic.

Word budget

Aim for 30–100 words on Seedream 4.x. Seedream 5 accepts a much longer brief and starts scattering attention past roughly 600 English words. Specificity buys more than length: past the budget the model drops clauses, and which ones it drops is not yours to choose.

Text in the image

Put the literal copy in quotation marks and say where it goes. Anything you describe rather than quote, the model writes for you.

Fashion editorial cover, 3:4. Masthead "ATRIUM" in tall thin capitals across the top edge, one cover line "The Quiet Season" in small italics at the lower left. A model in a raw-edged linen coat against a bare plaster wall, three- quarter turn, looking off-frame right. Soft north light from the left, long shadow across the plaster. Editorial photorealism, medium format, muted palette. No other text.

Closing with "no other text" is what stops the model filling the margins with invented lettering. Quote copy only when it belongs to the deliverable itself; a keyframe for a timeline or a video clip keeps its titles and supers off the image and gets them as text clips afterwards (caption-titles), where they stay editable.

Show full SKILL.md (350 more words)Show less

Editing: pin before you change

Reference-guided editing takes up to ten images — send more and only the last ten are used. The failure mode is not the edit — it is everything you did not mention drifting. State the pins:

Change only the bottle's label to matte black with "SERIES 04" in white sans-serif capitals. Keep the exact bottle silhouette, the exact camera angle, the exact backdrop and the exact studio lighting from the reference.

Address references by what they contain, not by position: "the tan leather journal", not "the second image". Content descriptions survive re-ordering and disambiguate two references that look alike. For product identity, feed packshots on white — a lifestyle photo carries a scene the model will try to keep.

Seedream 5 Pro adds region-precise editing and layer separation, which is what makes it the pick when one element must change and the rest of the frame must be provably untouched.

Size and tiers

image_size runs from 1024×1024 to 2048×2048 total pixels, aspect ratios 1:16 to 16:1, and defaults to auto_2K. Work the composition at the smaller tier while you iterate and render the deliverable at 2K. Match the ratio to the brief rather than defaulting to square: 3:4 for a cover, 9:16 for a poster, 4:3 for a still life.

Symptoms

What went wrongWhat to change
Subject differs from what you describedMove the subject description earlier and make its defining features concrete
An unwanted illustrative styleName the style you want and negate the one you got explicitly
Elements land in the wrong placeState spatial relationships; cut the number of things in the frame
Copy is paraphrased or inventedQuote it exactly, place it, and close with "no other text"
An untouched region changed in an editAdd the pins — silhouette, angle, backdrop, lighting
Clauses at the end were ignoredYou are over budget; cut to the layers that matter

Grade the result with critique_image and score_image_adherence rather than eyeballing it, and compare_images when you are choosing between candidates.

Adapted from fal's Seedream v4.5 prompt guide and Runware's Seedream 5.0 Pro prompting guide: https://fal.ai/learn/devs/seedream-v4-5-prompt-guide https://runware.ai/docs/models/bytedance-seedream-5-0-pro/guides/prompting

© nodetool-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/system-skills/seedream-prompting of nodetool-ai/nodetool.

Open the folder on GitHubat commit 339f069

Compare with similar skills

Seedream Prompting 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.

Seedream Prompting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Seedream Prompting this skillnodetool-ai/nodetool560—~1.4kAutomated safety check: PassAGPL-3.0
Character Design with genmediafal-ai-community/skills251—~1.3kAutomated safety check: PassNone
Remix Graphic Ad From Referencegooseworks-ai/goose-skills1.2k1 repos~4.8kAutomated safety check: PassMIT
fal.ai Models Catalogfal-ai-community/skills251—~717Automated safety check: PassNone
Image Generation Gatewayscalesthio/generative-media-skills197—~20kAutomated safety check: PassMIT
Fal AIhoodini/ai-agents-skills282—~2.1kAutomated safety check: NotesNone

Similar skills

  • Character Design with genmedia

    fal-ai-community/skills

    Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

    251 GitHub stars~1.3k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • Remix Graphic Ad From Reference

    gooseworks-ai/goose-skills

    Recreate a static graphic ad (Pinterest pin, IG/FB feed image, poster) from a reference image, swapping in a new brand's product and new copy while keeping the reference's layout, composition, and…

    1.2k GitHub starsUsed in 1 repo~4.8k tokens
    Media & CreativeAuto-check passed
  • fal.ai Models Catalog

    fal-ai-community/skills

    Routes image, video, 3D, audio and text-extraction tasks to a suitable fal.ai endpoint using per-modality reference lists instead of blind model searches.

    251 GitHub stars~717 tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • Image Generation Gateways

    calesthio/generative-media-skills

    Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts…

    197 GitHub stars~20k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Fal AI

    hoodini/ai-agents-skills

    Generate images, videos, and audio with fal.ai serverless AI.

    282 GitHub stars~2.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes
  • 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

More from nodetool-ai/nodetool

All 127 skills in this repo
  • Beat Sync Editing

    nodetool-ai/nodetool

    Cut a NodeTool timeline to music and shape its pacing — detect the beat grid, place cuts on phrases, pick a cut type, build speed ramps with time remap, and give the piece an arc.

    560 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Caption Titles

    nodetool-ai/nodetool

    Add and animate a consistent text layer on an existing NodeTool timeline.

    560 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Color Motion

    nodetool-ai/nodetool

    Choose and animate colour on a NodeTool timeline, including shape and text gradients, colour grades, 3D LUTs, and dither.

    560 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Commercial Beat Sheet

    nodetool-ai/nodetool

    Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot.

    560 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Elevenlabs Audio Prompting

    nodetool-ai/nodetool

    Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead…

    560 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Frame Composition

    nodetool-ai/nodetool

    Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave.

    560 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

Works with

Questions about Seedream Prompting

What does Seedream Prompting do?

Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must…. Seedream Prompting is an agent skill from nodetool-ai/nodetool. Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing up to ten references by content instead of by index, and the size to iterate at versus the size to deliver.

When should I use Seedream Prompting?

Seedream Prompting fits situations like: the model id names Seedream 4; 5 (bytedance/seedream/v5/pro/text-to-image; bytedance/seedream/v5/lite/edit; fal-ai/bytedance/seedream/v4.5/edit.

How do I install Seedream Prompting in Claude Code?

Run `npx skills add nodetool-ai/nodetool --skill seedream-prompting -a claude-code`. Or copy the skill folder (packages/system-skills/seedream-prompting in nodetool-ai/nodetool) into .claude/skills/seedream-prompting in your project. Claude Code loads it when a task matches its description.

How do I install Seedream Prompting in Codex?

Run `npx skills add nodetool-ai/nodetool --skill seedream-prompting -a codex`. Or copy the skill folder (packages/system-skills/seedream-prompting in nodetool-ai/nodetool) into .agents/skills/seedream-prompting in your project. Codex loads it when a task matches its description.

Can I use Seedream Prompting 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 nodetool-ai/nodetool --skill seedream-prompting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedream-prompting, .gemini/skills/seedream-prompting, .github/skills/seedream-prompting and .opencode/skills/seedream-prompting in your project.

What does Seedream Prompting need to run?

SKILL.md names no scripts, command-line tools or credentials: Seedream Prompting is instructions for the agent only.

Does Seedream Prompting access the network?

SKILL.md names 2 domains. As links in the text: fal.ai and runware.ai. This is read from the text; nothing was executed.

Is Seedream Prompting 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. Review the folder before installing.

What licence does Seedream Prompting use?

Seedream Prompting is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Seedream Prompting use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Seedream Prompting?

Skills that share tags, products or a category with Seedream Prompting: Character Design with genmedia (fal-ai-community/skills, 251 stars), Remix Graphic Ad From Reference (gooseworks-ai/goose-skills, 1.2k stars), fal.ai Models Catalog (fal-ai-community/skills, 251 stars) and Image Generation Gateways (calesthio/generative-media-skills, 197 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seedream Prompting?

nodetool-ai (a GitHub organization) maintains it in nodetool-ai/nodetool, which has 560 GitHub stars. The repository holds 127 skills in this directory. The repository was last updated on October 10, 2026.

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