Agent skill

Dunhuang Aura

by govin-ai in govin-ai/dunhuang-aura-skill

Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style.

MITAuto-check passedMedia & Creative

Install Dunhuang Aura

skills CLI
$ npx skills add govin-ai/dunhuang-aura-skill --skill dunhuang-aura -a claude-code

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

GitHub CLI
$ gh skill install govin-ai/dunhuang-aura-skill dunhuang-aura --agent claude-code

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

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

Facts

Skill name
dunhuang-aura
GitHub stars
108
Token cost
~2.2k tokens
SKILL.md length
1,214 words
Files
14 (incl. scripts, references, assets)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style.

  • Works in 5 steps: Identify the target image. → State the single primary change. → List everything that must remain… → …
  • The user asks for 敦煌美学
  • SKILL.md covers Design read, Choose the operating mode, Non-negotiable visual invariants and Default palette, plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Dunhuang Aura is an agent skill from govin-ai/dunhuang-aura-skill. Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style. Use when the user asks for 敦煌美学, dark cave-wall textures, illuminated mural panels, flowing mineral-color ribbons, or this specific product-stage visual language. Do not use for archaeological restoration, historical reconstruction, or devotional religious imagery.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts, reference files and assets (for example `README.md`, `agents/openai.yaml` and `references/prompt-recipes.md`).

It sits in Media & Creative, covering Social media graphics. The licence is MIT.

When your agent uses it

  • The user asks for 敦煌美学
  • Dark cave-wall textures
  • Illuminated mural panels
  • Flowing mineral-color ribbons

Example prompts

  • “/dunhuang-aura”

Requirements

  • Python 3

Workflow steps

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

  1. Identify the target image.
  2. State the single primary change.
  3. List everything that must remain unchanged.
  4. Apply one edit pass.
  5. Inspect the result against the request and the invariants.

What it can do on your machine

Read from SKILL.md and the folder at commit 4b8ff65. 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/ (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.

Context cost

Dunhuang Aura loads about 2.2k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 1,214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

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 govin-ai/dunhuang-aura-skill at commit 4b8ff65, republished under its MIT licence (© govin-ai). 1,214 words, ~2,244 tokens.

Download SKILL.mdSave it as .claude/skills/dunhuang-aura/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
dunhuang-aura
description
Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style. Use when the user asks for 敦煌美学, dark cave-wall textures, illuminated mural panels, flowing mineral-color ribbons, or this specific product-stage visual language. Do not use for archaeological restoration, historical reconstruction, or devotional religious imagery.

Dunhuang Aura

Create polished commercial imagery that borrows Dunhuang's mineral colors, weathered surfaces, ribbons, lotus geometry, caisson order, caves, mountains, and luminous murals without turning the result into a scenic souvenir poster.

This is a commercial art-direction skill. It is not a license to copy a specific mural, reproduce a religious figure, or paste every Dunhuang motif into one frame.

Design read

Treat the default request as:

A contemporary Chinese commercial key visual for a design-conscious audience, combining cinematic product photography with Dunhuang mineral-pigment materiality.

Default visual dials:

  • Composition variance: 8/10. Prefer layered, asymmetric depth over centered symmetry.
  • Visual density: 7/10 for text-free art, 5/10 when the image must carry a headline.
  • Ornament intensity: 5/10. Motifs support hierarchy; they do not fill every gap.
  • Realism: 8/10 for products and devices, 6/10 for painted landscapes and ribbons.
  • Contrast: high at the focal object, restrained in the background.

If the user gives a reference image, preserve its composition and invariants before applying these defaults.

Choose the operating mode

Generate

Use when no image needs to be preserved. Read:

Edit

Use when the user says remove text, fill the left side, change the object, rebalance the composition, or otherwise refers to an existing image.

Before editing:

  1. Identify the target image.
  2. State the single primary change.
  3. List everything that must remain unchanged.
  4. Apply one edit pass.
  5. Inspect the result against the request and the invariants.

For multi-step edits, read Edit workflows. Do not combine unrelated edits in one pass when drift would be hard to diagnose.

Non-negotiable visual invariants

Apply these unless the user explicitly overrides them:

  1. Use one coherent mineral palette across the image.
  2. Give the scene one obvious primary subject.
  3. Build depth with foreground object, middle mural layer, and background cave or mountain layer.
  4. Make commercial objects physically believable. Product geometry, materials, contact shadows, reflections, and perspective must hold together.
  5. Use ribbons as directional flow, not random decoration.
  6. Use lotus and caisson forms sparingly. One strong occurrence is better than a repeated pattern wall.
  7. Keep gold restrained. It should act as reflected light, a sun disc, edge highlight, or small ornament.
  8. Avoid real brand marks unless the user supplies them and requests their use.
  9. Exclude religious figures by default. Do not generate Buddhas, bodhisattvas, apsaras, worship scenes, or copied mural characters unless the user explicitly requests historically grounded or devotional content.
  10. Never rely on the word "高级" alone. Translate it into composition, spacing, material, lighting, palette, and object-scale decisions.

Default palette

Use role-based color language first; include hex values only when the workflow needs precise art direction.

  • Charcoal cave black: dominant architectural base.
  • Sand mineral white: illuminated mural panels and product surfaces.
  • Cinnabar red: primary flowing ribbon.
  • Malachite green: secondary ribbon and small product accents.
  • Lapis blue: cool balance in mountains and fine accents.
  • Ochre gold: sun disc, reflected light, thin edges, and small highlights.

Read Visual system before building a brand-wide palette or multiple related images.

Composition rules

Text-free 5:2 cover
  • Fill the entire frame with meaningful imagery.
  • Do not reserve a title block unless the user asks for later typography.
  • Give both left and right thirds visible subject matter.
  • Keep an open path through the center so the panorama does not become a wall of objects.
  • Vary scale: one large foreground object, two or three middle-depth panels, one distant architectural opening.
  • Use a continuous ribbon system to connect the frame.
5:2 cover with text
  • Reserve 38% to 48% of the frame for the title.
  • Keep the title zone materially rich but visually quiet.
  • Concentrate the product or visual-production scene in the opposite half.
  • Use no more than two text lines unless the user supplies a longer title.
  • Preserve safe margins and check legibility at X/Twitter thumbnail size.
Product hero
  • Show one product unless the brief specifies a set.
  • Keep the full silhouette visible.
  • Place the product on a real support surface with a contact shadow.
  • Let the mural language appear behind or on the packaging, not over the product edge.
  • Reserve space only when copy will actually be added.
UI or device showcase
  • Use the device as a commercial object, not a fake dashboard collage.
  • Keep the screen perspective and bezel geometry believable.
  • If no exact UI copy is supplied, use image-led screen content with no readable placeholder text.
  • Do not place random microcopy, version labels, metrics, or decorative status dots.
Show full SKILL.md (462 more words)Show less
Multi-asset visual suite
  • Lock the palette, ribbon width, edge treatment, shadow language, and grain.
  • Vary the layout family across assets.
  • Do not turn a suite into four identical cards with different crops.

More layouts and failure cases are in Visual system.

Text policy

Determine one of three states before generation:

  • Exact text: reproduce only the supplied text, once, with explicit placement.
  • Placeholder-free: generate the image without any readable text, then add typography in a layout tool.
  • Text-free: prohibit all letters, numbers, labels, logos, watermarks, and interface microcopy.

For text-free requests, repeat the prohibition in both the primary request and constraints. Inspect product labels, device screens, background signage, frames, and decorative seals for accidental glyphs.

Prompt construction

Build prompts in this order:

  1. Use case and asset type.
  2. Primary request.
  3. Scene and backdrop.
  4. Subjects with exact counts and positions.
  5. Composition and depth.
  6. Style and realism.
  7. Lighting.
  8. Palette and materials.
  9. Text state.
  10. Invariants.
  11. Avoid list.

Use visible nouns and measurable relationships. Replace "more premium" with instructions such as:

  • Increase the main product to 32% of frame width.
  • Reduce ornamental motifs to two families.
  • Use a 45-degree warm key light from upper left.
  • Keep gold below 10% of visible color area.
  • Separate foreground, middle panels, and background opening.

Use Prompt recipes as adaptable starting points, not as fixed incantations.

Image-tool workflow

When an image-generation or image-editing tool is available:

  1. Generate at the requested aspect ratio.
  2. Inspect the complete frame, especially edges and corners.
  3. Check subject counts and placement.
  4. Check for accidental text and logos.
  5. Check product geometry, device geometry, reflections, and contact shadows.
  6. Make one targeted correction if a visible defect blocks the brief.
  7. Preserve the accepted image non-destructively when creating variants.

When no image tool is available, output a production-ready prompt and a compact QA checklist. Do not pretend an image was generated.

Required output behavior

For a generated image, report:

  • final aspect ratio;
  • whether text is included or prohibited;
  • the final prompt or a concise prompt summary;
  • saved path when the asset belongs to a project.

For an edited image, also report the change made and the invariants preserved.

Quality gate

Before delivery, read and run QA checklist. A result fails when any of these are true:

  • the user asked for no text but glyphs remain;
  • one side of a full-frame composition is unintentionally empty;
  • the product changes shape or floats without contact shadow;
  • ribbons collide with the subject edge or hide essential detail;
  • gold dominates the whole image;
  • the image reads as a tourist poster, fantasy game splash screen, or generic luxury cosmetics ad;
  • religious figures appear without an explicit request;
  • the requested aspect ratio is wrong.

The bundled validator checks prompt completeness before generation:

bash
python3 scripts/check_prompt.py prompt.txt --mode text-free --ratio 5:2

© govin-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 13 other files (scripts, references, assets) in the repository root of govin-ai/dunhuang-aura-skill.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • agents/openai.yaml
  • assets/example-5x2-text-free.png
  • references/prompt-recipes.md
  • references/qa-checklist.md
  • references/style-system.md
  • references/workflows.md
  • scripts/check_prompt.py
  • tests/invalid-vague.txt
  • tests/test_check_prompt.py
  • tests/valid-text-free.txt

Open the folder on GitHubat commit 4b8ff65

Compare with similar skills

Dunhuang Aura 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.

Dunhuang Aura compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dunhuang Aura this skillgovin-ai/dunhuang-aura-skill108—~2.2kAutomated safety check: PassMIT
Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill135k1 repos~3.5kAutomated safety check: PassMIT
Slack GIF Creatoranthropics/skills180k29 repos~2kAutomated safety check: PassApache-2.0
Guizang Social Cardsop7418/guizang-social-card-skill7.4k1 repos~7.8kAutomated safety check: PassAGPL-3.0
Video Cover Imageitwanger/toBeBetterJavaer18k—~3.3kAutomated safety check: PassNone
Ccfddl X Postsccfddl/ccf-deadlines9.4k—~5.6kAutomated safety check: PassMIT

Similar skills

  • Brand and Design Toolkit

    nextlevelbuilder/ui-ux-pro-max-skill

    Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.

    135k GitHub starsUsed in 1 repo~3.5k tokens
    Media & CreativeAuto-check passed
  • Slack GIF Creator

    anthropics/skills

    Official

    Provides Slack size and frame limits, Python animation helpers and validators for building animated GIFs sized for emoji and messages.

    180k GitHub starsUsed in 29 repos~2k tokens
    Media & CreativeAuto-check passed
  • Guizang Social Cards

    op7418/guizang-social-card-skill

    Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.

    7.4k GitHub starsUsed in 1 repo~7.8k tokens
    Media & CreativeAuto-check passed
  • Video Cover Image

    itwanger/toBeBetterJavaer

    Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.

    18k GitHub stars~3.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Ccfddl X Posts

    ccfddl/ccf-deadlines

    Prepare and, with a verified authenticated publishing route and authorization, publish daily conference-deadline countdown posts for @ccfddl on X/Twitter.

    9.4k GitHub stars~5.6k tokensUpdated today
    Media & CreativeAuto-check passed
  • Web Asset Generator

    alonw0/web-asset-generator

    Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn.

    514 GitHub starsUsed in 1 repo~6.6k tokens
    Media & CreativeAuto-check passed

Questions about Dunhuang Aura

What does Dunhuang Aura do?

Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style. Dunhuang Aura is an agent skill from govin-ai/dunhuang-aura-skill. Create or edit commercial key visuals, product advertising, social graphics, and 5:2 covers in a contemporary Dunhuang mineral-pigment style.

When should I use Dunhuang Aura?

Dunhuang Aura fits situations like: the user asks for 敦煌美学; dark cave-wall textures; illuminated mural panels; flowing mineral-color ribbons.

How do I install Dunhuang Aura in Claude Code?

Run `npx skills add govin-ai/dunhuang-aura-skill --skill dunhuang-aura -a claude-code`. Or copy the skill folder (the govin-ai/dunhuang-aura-skill repository) into .claude/skills/dunhuang-aura in your project. Claude Code loads it when a task matches its description.

How do I install Dunhuang Aura in Codex?

Run `npx skills add govin-ai/dunhuang-aura-skill --skill dunhuang-aura -a codex`. Or copy the skill folder (the govin-ai/dunhuang-aura-skill repository) into .agents/skills/dunhuang-aura in your project. Codex loads it when a task matches its description.

Can I use Dunhuang Aura 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 govin-ai/dunhuang-aura-skill --skill dunhuang-aura -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dunhuang-aura, .gemini/skills/dunhuang-aura, .github/skills/dunhuang-aura and .opencode/skills/dunhuang-aura in your project.

What does Dunhuang Aura need to run?

Going by SKILL.md and its folder, Dunhuang Aura needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Dunhuang Aura 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 Dunhuang Aura 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 Dunhuang Aura use?

Dunhuang Aura is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dunhuang Aura use?

About 2.2k tokens (SKILL.md is roughly 9k 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 5.8k tokens, read only when the agent opens those files.

What are the alternatives to Dunhuang Aura?

Skills that share tags, products or a category with Dunhuang Aura: Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 135k stars), Slack GIF Creator (anthropics/skills, 180k stars), Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars) and Video Cover Image (itwanger/toBeBetterJavaer, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dunhuang Aura?

govin-ai (a GitHub user) maintains it in govin-ai/dunhuang-aura-skill, which has 108 GitHub stars. The repository was last updated on September 12, 2026.

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