Blcaptain Style Skill

当用户需要把内容(文章、笔记、截图、数据、产品说明)做成中文图文卡片组图时使用——小红书 / Rednote 3:4 竖图、公众号封面、社交卡。提供三套独家视觉语言(静纸 Still Paper本手记 / Signal Proof 证据层 / Bridge Canvas 跨平台桥),由 Claude 读懂内容、自己撰写 brief.json,交给确定性引擎渲染出第一眼惊艳、一眼可辨、国内开箱即用的图文组图。

178 stars 16 forksFrontend & Design

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add dososo/blcaptain-style-skill --skill blcaptain-style-skill
Manual install
git clone --depth 1 https://github.com/dososo/blcaptain-style-skill.git /tmp/blcaptain-style-skill
mkdir -p ~/.claude/skills
cp -r /tmp/blcaptain-style-skill/. ~/.claude/skills/blcaptain-style-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# BLCaptain Style Skill

把一段中文内容变成第一眼惊艳、一眼识别是「我们」、国内开箱即用的图文组图(小红书 3:4 + 公众号封面)。

何时使用:用户要做小红书 / 公众号 / 社交图文卡、读书笔记 / 旅行 / 生活随笔卡、AI 工具教程 / 数据复盘 / 职场框架卡、截图证据卡。

## 智能驱动(核心工作形态)

内容理解是 Claude 的活,不是代码的活。由你读懂内容、做出判断(提炼分页 / 选视觉语言 / 选版式 / 选金句),**亲手撰写 `brief.json`**,再交给确定性引擎渲染。代码只负责确定性的模板渲染 + 质量校验。

- 字段权威:`src/engine.mjs` 各 layout 的 render 函数(写某个 layout 前,先查它读哪些字段)。
- brief 范例:`examples/*/brief.json`(多个真实样本,含 `founder-diary` / `data-report` / `screenshot-tutorial` / `agent-parallel-research` 等,可作格式参照与回归基准)。
- `src/plan.mjs`(文章→brief 正则生成器)仅作 fallback / 起点,**不拿它做内容理解**——正则会截断半句、选错金句、跨页重复。这套智能驱动的工作形态就是为了绕开它。

## 三套视觉语言(选一套承载内容)

选语言不是挑装饰皮肤,是给这份内容认领一个立场:

- **Still Paper · 纸** — 把内容沉淀成有温度的纸本手记。生活 / 随笔 / 情感 / 旅行 / 读书。暖纸 + 宋体 + 朱砂 + 手作痕迹。主题合同见 `references/still-paper-theme-contracts.md`。
- **实证 · Signal Proof** — 把内容校验成可信的证据(界面是证据层,读者才相信流程)。tech / AI / 数据 / 职场。奶白档案纸 + 黑体 + 电蓝 + VERIFIED 印章 + 证据方法论叙事。主题合同见 `references/signal-ledger-theme-contracts.md`。
- **Bridge Canvas · 桥** — 把内容连接成跨平台、跨场景的统一表达。cinematic 满铺强图 + 电影黑边,多平台同源(3:4 / 1:1 / 16:9)。视觉系统见 `references/style-system.md` 与 `references/style-pack-catalog.md`。

每套都有独家影像配方(主题色三调 duotone / cinematic split-tone / 暖墨 duograde),让每张图一眼可辨、抄不走、不撞通用 stock 与他家 skill。选哪套:按内容形态判断,或用 `--system auto`。

## 五动作出图法

读懂 → 定调 → 分页 → 落版 → 成图。这是一条顺下来的创作主线,不是填格子。每个动作都由 Claude 亲自经手,一环扣一环。

### 一 · 读懂

自主读懂内容、做出判断(不靠正则路由理解):读出核心主张、关键点、可上图的视觉碎片。同时摸清会影响输出的缺口——平台与比例、内容类别与意图、用户手里已有的照片 / 截图及用途、必留硬约束(标题必留、截图必须可读、不显示来源标签等)。信息已够就不多问。

### 二 · 定调

按内容形态选定承载它的视觉语言与主题:
Read the full skill on GitHub

Details

Skill name
blcaptain-style-skill
Repo updated
8 July 2026

FAQ

What does the Blcaptain Style Skill skill do?

当用户需要把内容(文章、笔记、截图、数据、产品说明)做成中文图文卡片组图时使用——小红书 / Rednote 3:4 竖图、公众号封面、社交卡。提供三套独家视觉语言(静纸 Still Paper本手记 / Signal Proof 证据层 / Bridge Canvas 跨平台桥),由 Claude 读懂内容、自己撰写 brief.json,交给确定性引擎渲染出第一眼惊艳、一眼可辨、国内开箱即用的图文组图。

How do I install the Blcaptain Style Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add dososo/blcaptain-style-skill --skill blcaptain-style-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Blcaptain Style Skill popular?

It lives in dososo/blcaptain-style-skill, which has 178 GitHub stars and 16 forks.

Related skills

Frontend Design

154

Ilm-Alan/frontend-design

Build a frontend with a deliberate visual direction held through palette, typography, structure, and texture, with on-screen strings that name real information rather than fabricated demo data or filler labels. Use when building or restyling a frontend.

Frontend & Design23

Code Brand Film

181

nutllwhy/code-brand-film

Produce a short brand film or product promo (10-60s, typically 15s) entirely as code: one static HTML page with a paused GSAP timeline that a renderer seeks frame by frame, plus a music score synthesized in Python. Use when the user wants a 品牌宣传片, 广告片, 宣传动画, 产品短片, 发布会开场视频, brand film, promo video, product teaser, logo animation, or a generated ad spot — especially when they ask for 高级感 / 艺术感 / 电影感 / 别像模板, or when an existing video "looks like AI made it" or "too simple" and needs to be redone properly. Also use when a film already exists and needs a score, a soundtrack, background music, or 配乐

Frontend & Design23

Brand System Builder

168

amirmushichge/brand-system-skill

Guides Lovart Agent from one visual reference to a coherent brand system, campaign assets, and packaging concepts through a gated creative-direction workflow.

Frontend & Design12

Diorama

196

sloemo01/diorama

Use when building a pixel diorama in Three.js — one-prompt autonomous builds with staged systems, detailed props, real animation, and social/service choreography.

Frontend & Design15

Aria Icons

103

LeulAria/Aria-Icons

Use when working with icons in any project. Search 1.4M icons, add them as source files (no giant dependency), migrate existing icon libraries, and run as an MCP server. Commands: `aria-icons search`, `aria-icons add`, `aria-icons get`, `aria-icons migrate`, `aria-icons doctor`.

Frontend & DesignIn 2 lists

Apple Hig Designer

212

axiaoge2/Apple-Hig-Designer

Design Apple-style iOS/macOS interfaces following Human Interface Guidelines. Creates HIG-compliant components with SF Symbols, San Francisco typography, and proper accessibility. Supports optional modern effects. Use when designing Apple-style UI, iOS/macOS interfaces, HIG-compliant components, or implementing design system specifications.

Frontend & Design23

Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.