Image Prompt Reverse
LunarXuan/image-prompt-reverse
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.
Generate images and content consistent with the Nous Research brand identity.
Install Nous Branding
$ npx skills add magnus919/agent-skills --skill nous-branding -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install magnus919/agent-skills nous-branding --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nous-branding .claude/skills/nous-branding && rm -rf skills-srcUse ~/.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/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .claude/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/magnus919/agent-skills/tree/main/nous-brandingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add magnus919/agent-skills --skill nous-branding -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install magnus919/agent-skills nous-branding --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/nous-branding .agents/skills/nous-branding && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .agents/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/agent-skills --skill nous-branding -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install magnus919/agent-skills nous-branding --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/nous-branding .cursor/skills/nous-branding && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .cursor/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/magnus919/agent-skills.git --path nous-branding--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add magnus919/agent-skills --skill nous-branding -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install magnus919/agent-skills nous-branding --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/nous-branding .gemini/skills/nous-branding && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .gemini/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install magnus919/agent-skills nous-brandingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add magnus919/agent-skills --skill nous-branding -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/nous-branding .github/skills/nous-branding && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .github/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/agent-skills --skill nous-branding -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install magnus919/agent-skills nous-branding --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/nous-branding .opencode/skills/nous-branding && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nous-branding" agent skill from https://github.com/magnus919/agent-skills/tree/main/nous-branding into .opencode/skills/nous-branding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nous-branding", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
nous-branding- GitHub stars
- 115
- Token cost
- ~4k tokens
- SKILL.md length
- 1,427 words
- Files
- 16 (incl. scripts, references, assets)
- Skills in repo
- 131
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate images and content consistent with the Nous Research brand identity.
- Works in 5 steps: Reads ~/.hermes/config.yaml to find your… → For OpenAI: uses /v1/images/edits with… → Automatically crops the reference to… → …
- Creating visuals in the Nous / Theia / Hermes ecosystem: a cyber-classical style blending neo-classical statuary
- SKILL.md covers When not to use, Reference Images, Brand Identity Overview and Loading Guide, plus 8 more sections
- Runs Python scripts from its folder; calls python3
What it does
Nous Branding is an agent skill from magnus919/agent-skills. Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography (Inter/IBM Plex Sans, JetBrains Mono, heavy distressed display faces), the Nous Girl mascot, texture system, and image prompt construction. Ships reference images for palette, mascot, and brand collage that…
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including scripts, reference files and assets (for example `README.md`, `evals/evals.json` and `references/pitfalls.md`). Compatibility notes: Compatible with any agent capable of image generation or brand analysis. Reference-image workflows (img2img, style transfer, variations) require an API…
It sits in Media & Creative, covering Brand strategy and identity, Logo and visual identity and Image generation. It works with JetBrains IDEs. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.
When your agent uses it
- Creating visuals in the Nous / Theia / Hermes ecosystem: a cyber-classical style blending neo-classical statuary
- Cyberpunk/industrial grunge
- Retro anime illustration
- Unrelated requests
Example prompts
- “cyber-classical”
- “/nous-branding”
Requirements
- Python 3
- Compatibility (from SKILL.md): Compatible with any agent capable of image generation or brand analysis. Reference-image workflows (img2img, style transfer, variations) require an API endpoint supporting image inputs — use the assets/ images as input.
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Reads ~/.hermes/config.yaml to find your active image generation provider
- For OpenAI: uses /v1/images/edits with multipart upload — the only endpoint that accepts image input with gpt-image-2
- Automatically crops the reference to square (1024×1024) as required by the edits endpoint
- Saves output to ~/.hermes/cache/images/
- Returns JSON with image, model, aspect_ratio, and provider
What it can do on your machine
Read from SKILL.md and the folder at commit 22b4723. 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 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Compatible with any agent capable of image generation or brand analysis. Reference-image workflows (img2img, style transfer, variations) require an API endpoint supporting image inputs — use the assets/ images as input.
From compatibility in the SKILL.md frontmatter.
Context cost
Nous Branding loads about 4k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 162 tokens; SKILL.md has 1,427 words of instructions outside code blocks.
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 magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 1,427 words, ~3,983 tokens.
Download SKILL.mdSave it as
.claude/skills/nous-branding/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.- name
- nous-branding
- description
- Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography (Inter/IBM Plex Sans, JetBrains Mono, heavy distressed display faces), the Nous Girl mascot, texture system, and image prompt construction. Ships reference images for palette, mascot, and brand collage that can be used as img2img inputs. Do not use this skill for unrelated requests; route to the nearest named specialist.
- compatibility
- Compatible with any agent capable of image generation or brand analysis. Reference-image workflows (img2img, style transfer, variations) require an API endpoint supporting image inputs — use the assets/ images as input.
- license
- MIT
- metadata.tags
- nous-research, theia, hermes, brand, illustration, mascot, image-generation, style-guide, cyber-classical
- metadata.sources
- https://nousresearch.com, {"Reference image"=>"assets/palette-typography-reference.png"}, {"Reference image"=>"assets/nous-girl-official.webp (official…
- metadata.version
- 1.1.0
Nous Branding
Generate images and brand-consistent visual content inspired by Nous Research ("The AI accelerator company").
When not to use
- Non-Nous design work — this skill encodes one specific brand system; do not apply its palette, textures, mascot, or compliance rules to unrelated brands or generic design requests.
- Official brand representation — the Nous Girl mascot is not a substitute for the logo; use the Nous Research wordmark/symbol for official brand use.
Reference Images
This skill ships reference images in assets/ that can be used as visual anchors for img2img, style transfer, image variation, or prompt construction:
| File | Description | Usage |
|---|---|---|
assets/palette-typography-reference.png | Brand identity system card showing the 6-color palette swatches with hex codes, typography specimen (Inter, IBM Plex Sans, JetBrains Mono, heavy display), and classified-dossier layout | Upload as reference for color palette and typography style |
assets/nous-girl-official.webp | Official high-resolution (2669×2709) Nous Girl mascot from nousresearch.com. High-contrast black-and-white retro manga portrait. Three-quarter profile facing left, white headband (primary badge variant). 51% dark / 47% light, pure b&w with no gray. | Primary mascot reference — the single most authentic brand image |
assets/nous-girl-official-badge.png | Official badge portrait from the brand booklet (5760×7454). Shows the Nous Girl in her canonical form: white headband, three-quarter profile, neutral attentive expression, stark black/white manga style. | Use when the badge/primary variant is needed |
assets/nous-girl-sketch-sheet.png | Official character sheet from the brand booklet showing all 4 canonical poses: primary badge, headphone ¾ profile, headphone profile left, and headphone small profile. | Use for pose reference and character consistency |
assets/nous-girl-philosophy.png | Brand philosophy page from the booklet showing the Nous Girl alongside the "decentralization of good design" mission statement. | Use for brand context and philosophy reference |
assets/nous-girl-style-reference.png | Generated reference portrait with "NOUS" on headphones, electric blue accents, and color swatch label | Color-application reference and prompt examples |
assets/brand-collage-reference.png | Cyber-classical brand collage with Theia marble statue, glowing electric blue eye with targeting reticle, system architecture diagram, CRT noise overlay | Multi-panel brand layout and HUD aesthetic reference |
Brand Identity Overview
Nous Research's visual identity is a three-way fusion:
| Influence | Expression |
|---|---|
| Classical / Greek myth | Statuary of Theia (Titaness of Sight), marble textures, mythological naming |
| Cyberpunk / Industrial | Grunge textures, CRT scan lines, photocopy noise, distressed type, dark palette |
| Retro Anime / Manga | The "Nous Girl" mascot, cel-shaded illustration, large expressive eyes, 1970s-80s manga aesthetic |
| Tech / Brutalist | Heavy display typography, system diagrams, blueprint-style layouts, monospace code labels |
Tagline: "The AI accelerator company" Key phrases: "Advance human rights and freedoms", "Open source language models", "Unrestricted availability and use" Vibe: Intellectual but gritty — a cutting-edge research lab operating in the shadows
Loading Guide
Load references on demand — do not load everything at once.
| File | Load when |
|---|---|
| references/style-lanes.md | Choosing a style lane or writing a lane-specific prompt — full lane grammar, prompt cues, example prompts, and the asset-to-lane Reference Catalog |
| references/visual-system.md | Constructing or reviewing an image against the visual system — hero + extended palettes, Nous Girl spec and pose variants, typography, texture system, art style |
| references/post-processing.md | Delivering any generated image — mandatory post-process modes (imprint/nous/standard) and intensity calibration for scripts/postprocess.py |
references/pitfalls.md | Output doesn't match expectations — known failure modes and mitigations |
Image Prompt Templates
Method 1: Full Brand Portrait
A cyber-classical brand identity illustration in the style of Nous Research / Project Theia.
[SUBJECT DESCRIPTION]. High-contrast dramatic lighting with deep near-black background (#00000E).
Electric blue (#3847FF) primary accent. Soft lavender (#BDA6FF) and burnt orange (#D6825A)
secondary accents. Deep teal (#2E706B) shadow tones. Overlaid with risograph grain texture,
photocopy noise, and subtle CRT scan lines. Retro anime cel-shading combined with neo-classical
sculptural forms. Geometric HUD overlay lines in burnt orange. Bold, distressed display typography.
Raw, analog, imperfect finish. No corporate polish.
Palette: #00000E bg, #3847FF accent, #BDA6FF secondary, #D6825A warm, #E6E6E6 text.Method 2: Nous Girl Mascot
High-contrast retro manga anime portrait, 1970s-80s cel-shaded style.
A young woman with large anime eyes, shoulder-length dark hair with blunt
straight-across bangs. White over-ear headphones. Three-quarter profile facing left.
Melancholic introspective expression. Bold heavy outlines. Pure black and white with
no grayscale. [Optional: Electric blue #3847FF hair highlights for color version].Method 3: Brand System Sheet / Collage
Multi-panel brand identity system sheet in Nous Research / Project Theia style.
Grid layout. [Describe panels]. Color palette: #3847FF electric blue, #BDA6FF lavender,
#D6825A burnt orange, #2E706B deep teal, #E6E6E6 off-white, #00000E near-black.
Texture swatches: risograph grain, photocopy noise, CRT scan lines, paper fiber, ink smudge.
Typography: heavy distressed display for titles, Inter/IBM Plex Sans for labels,
JetBrains Mono for technical data. Grunge textures throughout. Dark near-black background.Method 4: Reference-Image-Driven Generation (Recommended)
This is the preferred method for generating brand-consistent images. Use the scripts/generate-with-ref.py script which reads your Hermes config, determines the active image provider, and hits the API directly with the reference image as contextual input — bypassing the built-in image_generate tool which only supports text prompts.
python3 scripts/generate-with-ref.py \
--prompt "Your prompt describing the desired image" \
--reference assets/nous-girl-official-badge.png \
--aspect landscape \
--quality mediumFeatures:
--prompt(required) — image description--reference(required) — path to a reference image (useassets/images from this skill)--aspect—landscape(1536×1024),portrait(1024×1536), orsquare(1024×1024)--quality—low,medium(default), orhigh--output— custom output path--dry-run— preview without executing
How it works:
- Reads
~/.hermes/config.yamlto find your active image generation provider - For OpenAI: uses
/v1/images/editswith multipart upload — the only endpoint that accepts image input with gpt-image-2 - Automatically crops the reference to square (1024×1024) as required by the edits endpoint
- Saves output to
~/.hermes/cache/images/ - Returns JSON with
image,model,aspect_ratio, andprovider
Why this matters: Text-only generation loses the precise manga style, character proportions, and contrast balance of the Nous Girl. Uploading the official badge preserves the specific 1970s–80s cel-shaded ink style.
Prompting for reference workflows: State what to preserve from the reference, then what to add:
- "Keep the character's white over-ear headphones, white collared shirt, solid black hair with blunt bangs, neutral expression"
- "Maintain the same high-contrast black ink on white manga style"
- Then add the scene details, text, lighting, etc.
Prompt Formula
[STYLE: cyber-classical / Nous Research]
+ [SUBJECT DESCRIPTION]
+ [PALETTE: #00000E bg, #3847FF accent, #BDA6FF, #D6825A]
+ [TEXTURES: risograph grain, photocopy noise, CRT scan lines, paper fiber, ink smudge]
+ [LIGHTING: high-contrast chiaroscuro, dramatic spot, neon edge highlights]
+ [MOOD: intellectual, gritty, underground, calm/attentive]
+ [TYPOGRAPHY: heavy distressed display, Inter/IBM Plex Sans labels, JetBrains Mono code]Post-Processing
Raw AI-generated images are too clean for the Nous aesthetic. Post-processing is mandatory after every generation — the raw generated image is never the final deliverable.
python3 scripts/postprocess.py input.png output.png --mode imprint --intensity 0.7Run it as the final step after any generation method (text-only, img2img, multi-pass, or any provider). For mode selection (imprint / nous / standard) and intensity calibration per output type, load references/post-processing.md.
API Workflow Notes
| API | Approach |
|---|---|
| DALL-E 3 | Text-only. Use Method 1–3 prompts with hex values. |
| OpenAI Variations / Edit | Upload assets/*.png as image input. Prompt describes differences. |
| Midjourney | --sref <asset-url> with --iw 1.5–2.0. Include palette hex values in prompt. |
| ComfyUI | IPAdapter or Reference-Only ControlNet from assets. Denoise 0.6–0.7. Post-process with grain overlay. |
| Replicate / SD img2img | Upload reference. Prompt strength 0.7–0.8. CFG 7. |
Show full SKILL.md (563 more words)Show less
What Is NOT On-Brand
Avoid these common anti-patterns:
| Anti-Pattern | Why It's Wrong |
|---|---|
| Sad/melancholic expression | Model defaults to sad for manga characters unless explicitly told "not sad, not crying" |
| Dark/black headphones | Nous Girl wears white over-ear headphones in all canonical poses |
| Facial markings (teardrop, tattoos, scars) | The character has clean, clear skin — no markings whatsoever |
| Wrong ethnicity (Asian instead of French) | Model defaults to Asian features for anime style; explicitly state "French Caucasian" |
| Busy/cluttered compositions | The brand is restrained — dark background, 1-2 accent colors, 2-3 text elements max |
| Smooth digital illustration | The brand is never clean — every image needs grain, noise, or analog texture |
| Cartoon/anime with glossy rendering | The manga style is stark black ink on white paper — no soft shading, no gradients |
| Corporate/sterile tech aesthetic | The finish should feel like an underground research lab, not a SaaS landing page |
| Over-detailed backgrounds | Let the subject breathe. Negative space is a feature. |
For a complete list of known failure modes and mitigations, see references/pitfalls.md.
Brand Compliance Checklist
- Background is near-black (#00000E) or very dark
- Electric blue (#3847FF) is used as primary accent
- At least one grunge texture visibly applied (grain, noise, scan lines, paper, ink)
- High contrast — dramatic light/dark difference
- Palette is restricted to the specified colors
- If mascot appears: white headphones, manga style, neutral attentive expression, three-quarter profile
- If text appears: heavy distressed display for titles, clean sans for labels, monospace for code
- No flat/clean/corporate polish — finish is raw and tactile
- Overall impression: intellectual, gritty, underground research lab
Full color tables, the complete Nous Girl mascot specification with pose variants, typography roles, texture definitions, and art-style attributes live in references/visual-system.md; lane-specific prompt construction lives in references/style-lanes.md.
Available Scripts
| Script | Purpose | Invocation |
|---|---|---|
scripts/generate-with-ref.py | Reference-image-driven generation: reads the active image provider from ~/.hermes/config.yaml, uploads the reference via the provider's image-input endpoint (square-cropped), and saves the result as JSON with output path. Run it for any Method 4 generation where brand fidelity matters — it preserves the manga style that text-only prompts lose. Use --dry-run first to preview provider and parameters. | python3 scripts/generate-with-ref.py --prompt "..." --reference assets/nous-girl-official-badge.png --aspect landscape --quality medium |
scripts/postprocess.py | Mandatory analog post-processing: applies grain/noise/scan-line modes (standard, risograph, nous, imprint) at a calibrated intensity. Run it as the final step on every generated image — raw AI output is never the deliverable. Load references/post-processing.md to pick mode and intensity. | python3 scripts/postprocess.py input.png output.png --mode imprint --intensity 0.7 |
Prerequisites
- Python 3 for both scripts;
postprocess.pyadditionally needs an imaging backend (Pillow) available. - For
generate-with-ref.py: a configured Hermes image-generation provider in~/.hermes/config.yaml(or an explicit--provider) whose API accepts image inputs — text-only endpoints cannot do reference-driven generation. - The bundled reference images in
assets/, which serve as img2img anchors; pass one via--reference. - An agent or client capable of image generation when working outside the scripts (per
compatibility).
Limitations
- This skill encodes one specific brand system — the palette, mascot rules, textures, and compliance checklist here are not general design guidance and must not be applied to other brands (see When not to use).
- The Nous Girl is not a logo substitute; official brand representation requires the wordmark/symbol, not generated mascot art.
- Generated imagery approximates the style even with references: always run the Brand Compliance Checklist before delivering, and consult
references/pitfalls.mdwhen output drifts (sad expressions, dark headphones, glossy rendering). - Model/provider behavior changes over time — flag-specific details like endpoint names may drift from what the scripts assume; verify against your configured provider.
© magnus919, 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 15 other files (scripts, references, assets) in nous-branding of magnus919/agent-skills.
- SKILL.md
- README.md
- assets/brand-collage-reference.png
- assets/nous-girl-official-badge.png
- assets/nous-girl-official.webp
- assets/nous-girl-philosophy.png
- assets/nous-girl-sketch-sheet.png
- assets/nous-girl-style-reference.png
- assets/palette-typography-reference.png
- evals/evals.json
- references/pitfalls.md
- references/post-processing.md
- references/style-lanes.md
- references/visual-system.md
- scripts/generate-with-ref.py
- scripts/postprocess.py
Open the folder on GitHubat commit 22b4723
Compare with similar skills
Nous Branding 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Nous Branding this skillmagnus919/agent-skills | 115 | — | ~4k | Automated safety check: Pass | MIT | |
| Image Prompt ReverseLunarXuan/image-prompt-reverse | 467 | — | ~678 | Automated safety check: Pass | GPL-3.0 | |
| Brand Dnathatrebeccarae/claude-marketing | 161 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Brand Guidelinesnexu-io/open-design | 100k | — | ~346 | Automated safety check: Pass | Apache-2.0 | |
| Anthropic Brand Stylinganthropics/skills | 180k | 30 repos | ~559 | Automated safety check: Pass | Apache-2.0 | |
| Brand Design Skillziguishian/brand-design-skill | 155 | — | ~4.4k | Automated safety check: Pass | None |
Similar skills
Brand Dna
thatrebeccarae/claude-marketing
Extract brand identity from a website URL — voice, colors, typography, imagery, values, and target audience — into a structured brand-profile.json.
Brand Guidelines
nexu-io/open-design
Apply Anthropic's official brand colors and typography to artifacts for consistent visual identity and professional design standards.
- Official
Anthropic Brand Styling
anthropics/skills
Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.
Brand Design Skill
ziguishian/brand-design-skill
Drive a strict conversational, image-first and image-final brand identity design process.
Design Master
minhnv0807/ai-business-skills
Handles eight kinds of marketing visual requests, from logos and campaign key visuals to infographics and quote graphics, by generating images or writing paste-ready prompts.
More from magnus919/agent-skills
All 131 skills in this repoArtifact Pyramids
magnus919/agent-skills
Organize durable agent research outputs as summaries, analysis, and evidence dossiers.
Ascii City Engine
magnus919/agent-skills
Build portable, first-person colored ASCII city engines and small GIS-derived city packs.
Color Management
magnus919/agent-skills
Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.
Data Scientist
magnus919/agent-skills
A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…
Docker Compose
magnus919/agent-skills
Use Docker Compose to define, run, debug, and harden multi-container applications.
Fpga Development
magnus919/agent-skills
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.
Related
Works with
Categories
Questions about Nous Branding
What does Nous Branding do?
Generate images and content consistent with the Nous Research brand identity. Nous Branding is an agent skill from magnus919/agent-skills. Generate images and content consistent with the Nous Research brand identity.
When should I use Nous Branding?
Nous Branding fits situations like: creating visuals in the Nous / Theia / Hermes ecosystem: a cyber-classical style blending neo-classical statuary; cyberpunk/industrial grunge; retro anime illustration; unrelated requests.
How do I install Nous Branding in Claude Code?
Run `npx skills add magnus919/agent-skills --skill nous-branding -a claude-code`. Or copy the skill folder (nous-branding in magnus919/agent-skills) into .claude/skills/nous-branding in your project. Claude Code loads it when a task matches its description.
How do I install Nous Branding in Codex?
Run `npx skills add magnus919/agent-skills --skill nous-branding -a codex`. Or copy the skill folder (nous-branding in magnus919/agent-skills) into .agents/skills/nous-branding in your project. Codex loads it when a task matches its description.
Can I use Nous Branding 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 magnus919/agent-skills --skill nous-branding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nous-branding, .gemini/skills/nous-branding, .github/skills/nous-branding and .opencode/skills/nous-branding in your project.
What does Nous Branding need to run?
Going by SKILL.md and its folder, Nous Branding needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3. Compatibility (from SKILL.md): Compatible with any agent capable of image generation or brand analysis. Reference-image workflows (img2img, style transfer, variations) require an API endpoint supporting image inputs — use the assets/ images as input..
Does Nous Branding 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 Nous Branding 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 Nous Branding use?
Nous Branding is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Nous Branding use?
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.1k tokens, read only when the agent opens those files.
What are the alternatives to Nous Branding?
Skills that share tags, products or a category with Nous Branding: Image Prompt Reverse (LunarXuan/image-prompt-reverse, 467 stars), Brand Dna (thatrebeccarae/claude-marketing, 161 stars), Brand Guidelines (nexu-io/open-design, 100k stars) and Anthropic Brand Styling (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Nous Branding?
magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.
Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.