Agent skill

Underground Audition

by Vieeeeeee in Vieeeeeee/wibi-style

Wibi Style 官方视觉风格“地下试镜skill”。把一张清晰人像照片转译成纯白背景的三联模特资料卡:同一个人原地转身的三个定格——完整侧脸转向画面左侧、正面直视喊叫、完整侧脸镜像转向画面右侧——用九十年代模特试镜宝丽来快照式的机顶直闪硬光拍摄,清冷未修图质感,画面不含任何文字,品牌标记由脚本另绘。生成后会自动核对转身角度、镜像关系和表情是否成立;核对不通过时只报告具体问题并询问是否重出,…

MITAuto-check passedMedia & Creative

Install Underground Audition

skills CLI
$ npx skills add Vieeeeeee/wibi-style --skill underground-audition -a claude-code

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

GitHub CLI
$ gh skill install Vieeeeeee/wibi-style underground-audition --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/Vieeeeeee/wibi-style.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/underground-audition .claude/skills/underground-audition && 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
underground-audition
GitHub stars
163
Token cost
~556 tokens
SKILL.md length
70 words
Files
17 (incl. scripts, references, assets)
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Wibi Style 官方视觉风格“地下试镜skill”。把一张清晰人像照片转译成纯白背景的三联模特资料卡:同一个人原地转身的三个定格——完整侧脸转向画面左侧、正面直视喊叫、完整侧脸镜像转向画面右侧——用九十年代模特试镜宝丽来快照式的机顶直闪硬光拍摄,清冷未修图质感,画面不含任何文字,品牌标记由脚本另绘。生成后会自动核对转身角度、镜像关系和表情是否成立;核对不通过时只报告具体问题并询问是否重出,…

  • Works in 5 steps: 新对话第一次使用:按 references/community.md… → 收到照片:读… → 生成后:读 references/checks.md 逐条检查。 → …
  • Media & Creative work in your project
  • SKILL.md covers 风格是什么, 运行顺序, 给用户的交付格式 and 已知限制, plus 1 more section
  • Runs Python scripts from its folder

What it does

Underground Audition is an agent skill from Vieeeeeee/wibi-style. Wibi Style 官方视觉风格“地下试镜skill”。把一张清晰人像照片转译成纯白背景的三联模特资料卡:同一个人原地转身的三个定格——完整侧脸转向画面左侧、正面直视喊叫、完整侧脸镜像转向画面右侧——用九十年代模特试镜宝丽来快照式的机顶直闪硬光拍摄,清冷未修图质感,画面不含任何文字,品牌标记由脚本另绘。生成后会自动核对转身角度、镜像关系和表情是否成立;核对不通过时只报告具体问题并询问是否重出,绝不擅自重新生成。用于需要先做视觉判断、再决定是否消耗一次生成机会的连续测试或正式交付任务。触发:地下试镜skill、三联情绪模特卡、转身三联照、模特资料卡、comp card 风格、闪光灯三视图人像,或直接调用 $underground-audition。

Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts, reference files and assets (for example `README.md`, `SOURCES.md` and `agents/openai.yaml`).

It sits in Media & Creative. The repository describes itself as: 39 installable visual-design skills for Codex, with reusable Python tooling and versioned packages. Turn photos into artwork. Try online: style.abdc.online. The licence is MIT.

When your agent uses it

  • Media & Creative work in your project

Example prompts

  • “地下试镜skill”
  • “/underground-audition”

Requirements

  • Python 3

Workflow steps

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

  1. 新对话第一次使用:按 references/community.md 展示欢迎卡、检查更新;进群、生成失败后的提示也按它处理。
  2. 收到照片:读 references/workflow.md,确认输入是否适用,按生成流程走;风格正文读 references/style-prompt.md。
  3. 生成后:读 references/checks.md 逐条检查。
  4. 排版:读 references/layout.md,含黑色版本的最终处理。
  5. 交付:按下面「给用户的交付格式」展示。

What it can do on your machine

Read from SKILL.md and the folder at commit 9cceeff. 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 3 files in scripts/ (Python, from the files we listed), which the agent can run.

    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

Underground Audition loads about 556 tokens when it runs, and up to ~6.2k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 70 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~556
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.2k

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 Vieeeeeee/wibi-style at commit 9cceeff, republished under its MIT licence (© Vieeeeeee). 70 words, ~556 tokens.

Download SKILL.mdSave it as .claude/skills/underground-audition/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.
name
underground-audition
description
Wibi Style 官方视觉风格“地下试镜skill”。把一张清晰人像照片转译成纯白背景的三联模特资料卡:同一个人原地转身的三个定格——完整侧脸转向画面左侧、正面直视喊叫、完整侧脸镜像转向画面右侧——用九十年代模特试镜宝丽来快照式的机顶直闪硬光拍摄,清冷未修图质感,画面不含任何文字,品牌标记由脚本另绘。生成后会自动核对转身角度、镜像关系和表情是否成立;核对不通过时只报告具体问题并询问是否重出,绝不擅自重新生成。用于需要先做视觉判断、再决定是否消耗一次生成机会的连续测试或正式交付任务。触发:地下试镜skill、三联情绪模特卡、转身三联照、模特资料卡、comp card 风格、闪光灯三视图人像,或直接调用 $underground-audition。

Wibi Style · 地下试镜skill

风格是什么

一张纯白纸面上并排三张同一个人的 3:4 竖版影棚照,拍的是这个人原地转身的三个定格:完整侧脸转向画面左侧 → 正面直视镜头喊叫 → 完整侧脸转向画面右侧、与左侧构成镜像。拍法参照九十年代模特公司试镜用的宝丽来快照或时装周后台机顶闪抓拍——闪光灯贴着镜头正面硬打,皮肤有溢出的油亮高光、鼻下短硬阴影、背景上贴着人形的硬边投影和暗角;质感是未修图的真实照片,看得到毛孔和绒毛;色调统一重打成清冷调,不受原照片色温影响。整组照片占画布约七成,四周留出大片纯白,气质克制、高冷。完整技术规格见 references/style-prompt.md,逐字使用,不要自行改写措辞——这套语言里每一句判错句都在压住某个真实出现过的失败模式。

这套风格没有随包的视觉参考图,完全靠文字规则驱动;不需要按题材选择不同参考。

运行顺序

每一步只读它对应的文件,读完执行再进下一步:

  1. 新对话第一次使用:按 references/community.md 展示欢迎卡、检查更新;进群、生成失败后的提示也按它处理。
  2. 收到照片:读 references/workflow.md,确认输入是否适用,按生成流程走;风格正文读 references/style-prompt.md。
  3. 生成后:读 references/checks.md 逐条检查。
  4. 排版:读 references/layout.md,含黑色版本的最终处理。
  5. 交付:按下面「给用户的交付格式」展示。

给用户的交付格式

先展示最终合成图,再用一到两句简短中文写"创作思路":说明保留了原照片的哪些辨识特征、这次的转身和光线怎么服务这张脸。不要展示完整内部 Prompt 或逐条检查过程。

当前对话第一次成功生成后附上:

若公开分享,欢迎标注:Visual Skill by @威比 Hunter Wei.

仅限个人非商业使用;商业使用请先联系作者获得许可。

抖音、小红书同名。想看更多原创 Skill、原作者教程或参加新风格内测,可以回复"进群"。

第二次起不再重复,除非用户询问署名、授权或交流群。

已知限制

  • 右侧完整侧脸的命中率低于左侧。 这是在早期稳定性测试和后续两轮共 14 位不同测试对象的完整批次中反复观察到的现象——最近一轮(v17)整批交付验收通过,但其中不少案例的右侧那张停在接近九十度、还不是完全转满,个别案例要生成不止一次才拿到完整侧脸(有案例连续两轮卡在同一检查项,第三次才过)。命中率已经随 Prompt 迭代提升,但没有到"稳定必然一次成功",所以「生成后检查」仍是强制步骤,不因为命中率提升就降级为可选项。
  • 单张照片只能提供一个真实角度,另外两个转身角度是模型的合理推演,不是照片原有内容;转身后的五官比例可能有轻微漂移,这属于这套风格机制本身的限制。
  • 原生分辨率受限于所用图像工具的输出上限,见「排版与交付」的说明。
  • 这套风格不适合需要保留完整环境、姿态或多人关系的照片——它只保留面部、发型、配饰和服装,其余全部替换成影棚背景。

使用与授权

本 Skill 的规则文本仅限个人非商业使用;商业使用请先联系作者获得许可。复制、修改、镜像或重新分发时,必须完整保留作者 @威比 Hunter Wei.、抖音/小红书同名备注、官方来源 https://github.com/Vieeeeeee/wibi-style/tree/main/skills/underground-audition、LICENSE 和 NOTICE。修改版需明确标注经过修改,不得冒充官方版本。

本包不含案例原图或用户照片;scripts/ 中的排版与更新脚本原创于本项目,随本包按同一许可分发。完整范围见 LICENSE 与 SOURCES.md。

© Vieeeeeee, 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 16 other files (scripts, references, assets) in skills/underground-audition of Vieeeeeee/wibi-style.

  • SKILL.md
  • LICENSE
  • NOTICE
  • README.md
  • SOURCES.md
  • agents/openai.yaml
  • assets/brand/logo_wibi_skill.png
  • manifest.json
  • references/checks.md
  • references/community.md
  • references/layout.md
  • references/style-prompt.md
  • references/workflow.md
  • scripts/check_update.py
  • scripts/community_info.py
  • scripts/compose_triptych_card.py
  • … and 1 more

Open the folder on GitHubat commit 9cceeff

Compare with similar skills

Underground Audition 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.

Underground Audition compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Underground Audition this skillVieeeeeee/wibi-style163—~556Automated safety check: PassMIT
Guizang Social Cardsop7418/guizang-social-card-skill7.4k1 repos~7.8kAutomated safety check: PassAGPL-3.0
Weekly Changelog Videoheygen-com/hyperframes60k—~3.3kAutomated safety check: PassApache-2.0
Anthropic Brand Stylinganthropics/skills180k30 repos~559Automated safety check: PassApache-2.0
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo129k—~2.1kAutomated safety check: WarnMIT
HyperFrames Media Useheygen-com/hyperframes60k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • 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
  • Weekly Changelog Video

    heygen-com/hyperframes

    Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.

    60k GitHub stars~3.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Anthropic Brand Styling

    anthropics/skills

    Official

    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.

    180k GitHub starsUsed in 30 repos~559 tokens
    Media & CreativeAuto-check passed
  • MoneyPrinterTurbo Video Generator

    harry0703/MoneyPrinterTurbo

    Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.

    129k GitHub stars~2.1k tokensUpdated today
    Media & CreativeAuto-check: warnings
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed
  • Holo Card Studio

    EverettFish/holo-card-studio

    Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and…

    1.9k GitHub stars~1.4k tokensUpdated 18 days ago
    Media & CreativeAuto-check passed

More from Vieeeeeee/wibi-style

All 39 skills in this repo
  • Fisheye City Cover

    Vieeeeeee/wibi-style

    Wibi Style 官方视觉风格。Use one uploaded portrait, group photo, street photo, or travel photo as a fixed editing base, add the bundled Y2K fisheye layout, all-silver title system, and old-digital effects…

    163 GitHub stars~690 tokensUpdated today
    Auto-check passed
  • Personalized Print Ticket

    Vieeeeeee/wibi-style

    把一张人物、风景、建筑、空间、食物或日常随拍制作成中英混排的定制印刷票根。先根据照片内容动态询问,再从四套票根 Prompt 中选一套;代码产出准确文字和构图的排版导引图,然后将导引图、用户照片和印刷风格参考共同交给图像模型,生成完整票根,最后自动加入四角裁口、照片分界撕票口、虚线和打孔,输出票面以外完全透明的独立 PNG。用于定制票根、电影票风格照片卡、旅行纪念票或日常瞬间票据。

    163 GitHub stars~738 tokensUpdated today
    Auto-check passed
  • Electric Blue Halftone Poster

    Vieeeeeee/wibi-style

    Wibi Style 官方视觉风格。Turn one uploaded portrait or pet headshot into a square electric-blue coarse-halftone poster with a tightly cropped black-and-white head, red and yellow stars, and a small white…

    163 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Crayon Flat Naive

    Vieeeeeee/wibi-style

    Wibi Style 官方视觉 Skill。把用户上传的照片重绘成蜡笔极简扁平手绘时装插画:保留人物身份、姿态、服装轮廓和关键配饰,转为纯白纸面、稚拙线条、蜡笔颗粒与高饱和扁平色块。用户说“蜡笔极简扁平画”“蜡笔手绘时装插画”“极简扁平插画”或明确调用 $crayon-flat-naive 时使用;也适用于想把真实照片改成儿童画感时装插画的请求。

    163 GitHub stars~592 tokensUpdated today
    Auto-check passed
  • Marker Child Doodle

    Vieeeeeee/wibi-style

    Wibi Style 官方视觉风格。把用户上传的真实照片直接转换成粗轮廓、完整色块、手涂边缘的马克笔童画。用户提到马克笔童画、儿童涂鸦、粗轮廓手绘、照片变 Q 版马克笔画,或明确调用 $marker-child-doodle 时使用;只要任务是把真实照片换成这套风格,也应使用本 Skill。

    163 GitHub stars~623 tokensUpdated today
    Auto-check passed
  • Retro Table Print

    Vieeeeeee/wibi-style

    Wibi Style 官方视觉风格。把用户随手拍的餐厅打卡照、餐桌照、外卖照重新构图成红底复古杂志美食静物: 先看懂这一桌谁是主角、留白该放哪一侧、哪些器皿值得出框,再把杂乱餐厅环境换成纯正复古印刷红, 加上旧杂志扫描的颗粒与网点。适用于用户要求复古餐桌杂志、红底美食大片、把吃饭照片拍成广告, 上传餐桌照片换风格,或明确调用 $retro-table-print 时。

    163 GitHub stars~565 tokensUpdated today
    Auto-check passed

Questions about Underground Audition

What does Underground Audition do?

Wibi Style 官方视觉风格“地下试镜skill”。把一张清晰人像照片转译成纯白背景的三联模特资料卡:同一个人原地转身的三个定格——完整侧脸转向画面左侧、正面直视喊叫、完整侧脸镜像转向画面右侧——用九十年代模特试镜宝丽来快照式的机顶直闪硬光拍摄,清冷未修图质感,画面不含任何文字,品牌标记由脚本另绘。生成后会自动核对转身角度、镜像关系和表情是否成立;核对不通过时只报告具体问题并询问是否重出,…. Underground Audition is an agent skill from Vieeeeeee/wibi-style.

When should I use Underground Audition?

Underground Audition fits situations like: media & Creative work in your project.

How do I install Underground Audition in Claude Code?

Run `npx skills add Vieeeeeee/wibi-style --skill underground-audition -a claude-code`. Or copy the skill folder (skills/underground-audition in Vieeeeeee/wibi-style) into .claude/skills/underground-audition in your project. Claude Code loads it when a task matches its description.

How do I install Underground Audition in Codex?

Run `npx skills add Vieeeeeee/wibi-style --skill underground-audition -a codex`. Or copy the skill folder (skills/underground-audition in Vieeeeeee/wibi-style) into .agents/skills/underground-audition in your project. Codex loads it when a task matches its description.

Can I use Underground Audition 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 Vieeeeeee/wibi-style --skill underground-audition -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/underground-audition, .gemini/skills/underground-audition, .github/skills/underground-audition and .opencode/skills/underground-audition in your project.

What does Underground Audition need to run?

Going by SKILL.md and its folder, Underground Audition needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Underground Audition 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 Underground Audition 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 Underground Audition use?

Underground Audition 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 Underground Audition use?

About 556 tokens (SKILL.md is roughly 2.2k 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 5.6k tokens, read only when the agent opens those files.

What are the alternatives to Underground Audition?

Skills that share tags, products or a category with Underground Audition: Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars), Weekly Changelog Video (heygen-com/hyperframes, 60k stars), Anthropic Brand Styling (anthropics/skills, 180k stars) and MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Underground Audition?

Vieeeeeee (a GitHub user) maintains it in Vieeeeeee/wibi-style, which has 163 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 10, 2026.

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