Agent skill

Flux 2 Klein Prompting

by nodetool-ai in nodetool-ai/nodetool

Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and…

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Flux 2 Klein Prompting

skills CLI
$ npx skills add nodetool-ai/nodetool --skill flux-2-klein-prompting -a claude-code

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

GitHub CLI
$ gh skill install nodetool-ai/nodetool flux-2-klein-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/flux-2-klein-prompting .claude/skills/flux-2-klein-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
flux-2-klein-prompting
GitHub stars
560
Token cost
~1.4k tokens
SKILL.md length
653 words
Files
1
Skills in repo
127
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and…

  • Works in 4 steps: Subject — concrete beats abstract. "A… → Environment — lighting, atmosphere,… → Style and mood — direction that guides… → …
  • The model id contains flux-2/klein
  • SKILL.md covers Prompt hierarchy, Parameters, Technique and The five mistakes, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Flux 2 Klein Prompting is an agent skill from nodetool-ai/nodetool. Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its sub-second latency makes practical. Use whenever the model id contains flux-2/klein or flux-2-klein (fal-ai/flux-2/klein/4b, fal-ai/flux-2/klein/9b, their /base, /edit and /lora variants, fal-ai/flux-2/klein/realtime, black-forest-labs/flux-2-klein-4b…

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 AI & LLM Engineering, covering Image generation, Image editing and Fine-tuning. 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 contains flux-2/klein
  • Flux-2-klein (fal-ai/flux-2/klein/4b
  • Fal-ai/flux-2/klein/9b
  • /edit and /lora variants

Example prompts

  • “/flux-2-klein-prompting”

Workflow steps

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

  1. Subject — concrete beats abstract. "A woman in her mid-30s with
  2. Environment — lighting, atmosphere, spatial relationships. "First light
  3. Style and mood — direction that guides without overwhelming
  4. Technical — composition ("rule of thirds"), depth of field ("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

    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

Flux 2 Klein Prompting loads about 1.4k tokens when it runs. Until then it costs about 162 tokens; SKILL.md has 653 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~162
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). 653 words, ~1,350 tokens.

Download SKILL.mdSave it as .claude/skills/flux-2-klein-prompting/SKILL.md (or your agent's skills folder).
name
flux-2-klein-prompting
description
Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its sub-second latency makes practical. Use whenever the model id contains flux-2/klein or flux-2-klein (fal-ai/flux-2/klein/4b, fal-ai/flux-2/klein/9b, their /base, /edit and /lora variants, fal-ai/flux-2/klein/realtime, black-forest-labs/flux-2-klein-4b, black-forest-labs/flux-2-klein-9b) on generate_image, edit_image or a TextToImage node. Not for FLUX.2 pro, flex, max or dev.

FLUX.2 [klein] → structure first, then iterate fast

klein is the small, fast member of the FLUX.2 family: 4B or 9B, sub-second inference, photoreal output and text rendering above its speed tier. The speed is the point. When a generation takes 30 seconds, prompt refinement stalls; here you can change one clause and look again, so the working method below is worth more than any single prompt.

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

Prompt hierarchy

klein reads a prompt in this order, and content words (nouns) move the output more than modifiers do. Write it in the same order:

  1. Subject — concrete beats abstract. "A woman in her mid-30s with shoulder-length auburn hair" over "a person".
  2. Environment — lighting, atmosphere, spatial relationships. "First light filtering through morning mist" gives rendering cues that "morning scene" does not.
  3. Style and mood — direction that guides without overwhelming: "documentary photography", "studio lighting", "cinematic".
  4. Technical — composition ("rule of thirds"), depth of field ("shallow focus on the foreground"), palette ("warm earth tones").

Professional headshot of a male architect in his 40s, salt-and-pepper beard, black-rimmed glasses, charcoal blazer. Modern office background with architectural models visible but softly blurred. Natural window light from the left creating gentle shadows. Corporate photography style, sharp focus on the eyes, neutral grey backdrop.

Parameters

ParameterWhat it tradesWhere to sit
guidance_scalePrompt adherence against creative freedom2–4 for artistic interpretation, 5–8 for product photography and technical illustration
num_inference_stepsQuality against timeLow while developing a prompt, high for print-ready output
accelerationDetail against throughputregular for production, high for maximum speed
seedNothing — it removes noise from the comparisonPin it while testing prompt variations

Aspect ratio follows the deployment: landscape for presentations and web, portrait for social and mobile, square for profiles and balanced compositions.

Technique

  • Emphasis is natural language, not weights. There is no weight syntax. "Prominently featuring", "with particular attention to" and "especially detailed" are how you raise a element's priority.
  • Negative prompts target failure modes, not quality. For portraits: "distorted features, unnatural proportions, extra limbs". For landscapes: "oversaturated colours, artificial lighting, lens distortion". A generic quality list buys nothing.
  • Text renders well when specified. Give the copy, the font class, the colour, the placement and the capitalisation: "a white coffee mug with the text 'GOOD MORNING' in bold sans-serif black letters, centred on the mug". Copy that belongs to the design, in other words — a title or a super on a still headed for a timeline goes on as a text clip afterwards (caption-titles), not into the render.
  • Multi-reference conditioning is the family's edge. "The subject from the first image wearing the jacket from the second image, photographed in the environment from the third image."
Show full SKILL.md (199 more words)Show less

The five mistakes

  • Overloaded prompts. Past roughly 100 words the model starts dropping clauses. Every word should be doing something.
  • Vague style references. "Make it look good" is not a direction. "Shot on Hasselblad medium format" or "impressionist painting technique" is.
  • Missing composition. Prompts describe the subject thoroughly and never say where it sits. Add "centred composition", "rule of thirds with the subject on the left vertical", or "bird's eye view".
  • Conflicting instructions. "Photorealistic portrait" and "watercolour painting style" in one prompt commits to neither.
  • Neglected lighting. Lighting is what makes an image dimensional. Always name it: golden hour, studio softbox, rim lighting creating a silhouette.

The loop klein is for

Start with subject, environment and style. Generate. Pin the seed. Change one element — add lighting detail, refine the subject, move the composition — and generate again. One variable at a time is what tells you which clause drove which change; the sub-second turnaround is what makes that affordable.

Keep the prompts that worked. A library of formulas per use case, with the guidance and step values that suited each, is the output of this loop as much as the images are.

Adapted from fal's FLUX.2 [klein] prompt guide: https://fal.ai/learn/devs/flux-2-klein-prompt-guide

© 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/flux-2-klein-prompting of nodetool-ai/nodetool.

Open the folder on GitHubat commit 339f069

Compare with similar skills

Flux 2 Klein 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.

Flux 2 Klein Prompting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flux 2 Klein Prompting this skillnodetool-ai/nodetool560—~1.4kAutomated safety check: PassAGPL-3.0
Fal Trainnexu-io/open-design100k—~293Automated safety check: PassApache-2.0
Workflow Template BuilderMooshieblob1/MooshieUI207—~640Automated safety check: PassAGPL-3.0
Flux2 Klein PromptingAnastasiyaW/codex-claude-code-config154—~2.8kAutomated safety check: PassMIT
Flux Imagedanielmeppiel/agentic-sdlc-handbook1581 repos~778Automated safety check: PassCustom licence
Character Design with genmediafal-ai-community/skills251—~1.3kAutomated safety check: PassNone

Similar skills

  • Fal Train

    nexu-io/open-design

    Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.

    100k GitHub stars~293 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Workflow Template Builder

    Mooshieblob1/MooshieUI

    Builds or modifies ComfyUI workflow JSON templates in MooshieUI's Rust backend (src-tauri/src/templates).

    207 GitHub stars~640 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Flux2 Klein Prompting

    AnastasiyaW/codex-claude-code-config

    Expert prompt engineering for FLUX.2 [klein] image generation and editing model.

    154 GitHub stars~2.8k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Flux Image

    danielmeppiel/agentic-sdlc-handbook

    Generate images with FLUX models (Black Forest Labs) via inference.sh CLI.

    158 GitHub starsUsed in 1 repo~778 tokens
    AI & LLM EngineeringAuto-check passed
  • 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
  • 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

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 Flux 2 Klein Prompting

What does Flux 2 Klein Prompting do?

Prompt Black Forest Labs' FLUX.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and…. Flux 2 Klein Prompting is an agent skill from nodetool-ai/nodetool.2 [klein] — the subject/environment/style/technical hierarchy it processes in order, guidance-scale and step choices, negative prompts aimed at real failure modes, and the seed-locked one-variable-at-a-time loop its sub-second latency makes practical.

When should I use Flux 2 Klein Prompting?

Flux 2 Klein Prompting fits situations like: the model id contains flux-2/klein; flux-2-klein (fal-ai/flux-2/klein/4b; fal-ai/flux-2/klein/9b; /edit and /lora variants.

How do I install Flux 2 Klein Prompting in Claude Code?

Run `npx skills add nodetool-ai/nodetool --skill flux-2-klein-prompting -a claude-code`. Or copy the skill folder (packages/system-skills/flux-2-klein-prompting in nodetool-ai/nodetool) into .claude/skills/flux-2-klein-prompting in your project. Claude Code loads it when a task matches its description.

How do I install Flux 2 Klein Prompting in Codex?

Run `npx skills add nodetool-ai/nodetool --skill flux-2-klein-prompting -a codex`. Or copy the skill folder (packages/system-skills/flux-2-klein-prompting in nodetool-ai/nodetool) into .agents/skills/flux-2-klein-prompting in your project. Codex loads it when a task matches its description.

Can I use Flux 2 Klein 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 flux-2-klein-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/flux-2-klein-prompting, .gemini/skills/flux-2-klein-prompting, .github/skills/flux-2-klein-prompting and .opencode/skills/flux-2-klein-prompting in your project.

What does Flux 2 Klein Prompting need to run?

SKILL.md names no scripts, command-line tools or credentials: Flux 2 Klein Prompting is instructions for the agent only.

Does Flux 2 Klein Prompting access the network?

SKILL.md names 1 domain. As links in the text: fal.ai. This is read from the text; nothing was executed.

Is Flux 2 Klein 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 Flux 2 Klein Prompting use?

Flux 2 Klein 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 Flux 2 Klein Prompting use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Flux 2 Klein Prompting?

Skills that share tags, products or a category with Flux 2 Klein Prompting: Fal Train (nexu-io/open-design, 100k stars), Workflow Template Builder (Mooshieblob1/MooshieUI, 207 stars), Flux2 Klein Prompting (AnastasiyaW/codex-claude-code-config, 154 stars) and Flux Image (danielmeppiel/agentic-sdlc-handbook, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flux 2 Klein 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.