Darin Broll Skill

Darin 的外部工具 editorial paper-collage B-roll 提示词工作流。把约 5 秒口播、观点句、小红书/抖音选题或抽象概念压成一个清晰视觉隐喻，再依次输出视觉方向、首帧与尾帧英文提示词、视频生成英文提示词。用户提到“拼贴 B-roll”“纸拼贴视频”“半调拼贴动画”“给这句口播配画面”“首尾帧提示词”或要求把文稿做成编辑拼贴动画时使用。强制执行两次确认：视觉方向确认后才给静帧提示词，静帧提示词确认后才给视频提示词。默认只写提示词，不调用图像或视频生成工具。

10 stars 2 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add jidarin9383/darin-broll-skill --skill darin-broll-skill

Manual install

git clone --depth 1 https://github.com/jidarin9383/darin-broll-skill.git /tmp/darin-broll-skill
mkdir -p ~/.claude/skills
cp -r /tmp/darin-broll-skill/. ~/.claude/skills/darin-broll-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

# Darin Broll

把一句口播压成一个 sharp visual idea，再把它设计成从空色场逐件组装的高级编辑纸拼贴动画。默认交付外部生成工具可直接使用的提示词，不在本 Skill 内生成媒体。

## 工作协议

严格按以下顺序工作，不合并闸门：

1. Gate 1：只给视觉方向，停下等待确认。
2. Gate 2：方向确认后，只给首帧和尾帧英文提示词，停下等待确认。
3. Gate 3：静帧提示词确认后，给视频生成英文提示词。

遵守以下规则：

- 用中文沟通；所有生成提示词用英文。
- 默认不调用内置或外部图像、视频生成工具，不要求用户提供本地文件路径。
- 用户说“确认”“同意”“OK”“可以”“继续”时，只确认当前 Gate。
- 用户修改方向或提示词时，修改当前 Gate 并再次等待确认，不提前进入下一 Gate。
- Gate 2 的确认足以进入 Gate 3，不要额外等待“图片好了”。用户说“图片好了”也视为 Gate 2 已确认。
- 即使用户一开始直接索要完整提示词，也先完成 Gate 1；只有用户明确要求跳过审批时才一次性输出。
- 不模仿具体品牌或活跃艺术家的可识别签名。把“Vox 风格”等请求转译为可描述的编辑拼贴机制：半调网点、平坦色场、卡纸、奶油白 keyline 和逐件组装。

## 视觉语法

每条画面只表达一个清晰命题，并满足：

- 使用 2–4 个大型、可分离的纸片组；不要堆满零碎小物件。
- 把主体控制在画面中部约 70% 范围，保留充足纯色负空间。
- 使用强烈、平坦、均匀的纸张色场，不用渐变、暗角或写实环境。
- 以黑白 halftone photographic cut-outs 为骨架，只用少量彩色卡纸建立信息层级。
- 所有纸片具有清晰裁切边、细奶油白 keyline、低透明度柔和纸影和细微非涂布纸纹。
- 默认 9:16、约 5 秒、锁定镜头、无声、从空场逐件组装。
- 禁止字幕、口播全文、可读文字、数字、logo、水印、真实平台 UI、假通知和无关装饰。

### 色彩语义

按内容选择背景，不要固定使用单一颜色：

| 背景 | 适用语义 | 建议色值 |
|---|---|---|
| 焦橙 / 红 | 时间消耗、劳动、失败、紧迫 | `#D95D39` / `#C9433F` |
| 芥末黄 | 工具、警示、经验、踩坑 | `#D3A72C` |
| 深青 / 墨绿 | 判断、认知、协作、恢复掌控 | `#174F52` / `#274C3B` |
| 深紫 | 规范、沉淀、长期记忆 | `#493A68` |

点色优先使用暖奶油白 `#F1E6CF`、芥末黄、焦橙和少量浅青。同一批内容保持纸张、半调和 keyline 一致，但可随叙事更换背景色。

## Gate 1：视觉方向

先提取：

- 核心意思：观众最终要看懂什么。
- 情绪：例如疲惫、紧迫、反讽、笃定、释然或重新振作。
- 动作动词：例如跌倒、爬起、堆叠、阻断、连接、穿过、打开或归档。
- 视觉关系：什么主体通过什么动作表达核心意思。

优先使用可见动作，不要只摆放象征物。人物、设备和界面都必须服务于同一个动作关系。

创作者和数码题材可使用：人物、电脑、手机、相机、耳机、键盘、抽象视频缩略图、播放窗口、发布按钮轮廓、失败导出卡片、草稿纸堆和规则门槛。平台主页必须画成抽象频道网格或无字缩略图墙，不出现真实 logo、平台名称、可读标题、粉丝数字或完整 UI 截图。

### 稳定性规则

Read the full skill on GitHub

Details

Skill name: darin-broll-skill
Repository: jidarin9383/darin-broll-skill
License: MIT
Repo updated: 21 July 2026

FAQ

What does the Darin Broll Skill skill do?

How do I install the Darin Broll Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jidarin9383/darin-broll-skill --skill darin-broll-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Darin Broll Skill popular?

It lives in jidarin9383/darin-broll-skill, which has 10 GitHub stars and 2 forks.

Related skills

Math Research Activator

the-thinker0/math-skill

数学研究助手：将 AI 研究目标转成数学对象、可实现机制和可验证结论；用于架构/算子构造、理论分析、跨数学领域思路发现与结构迁移、研究相关数学查询，以及密码学定义、构造、归约与协议审查。纯实现型 debug、重构、调参和一般代码审查不触发。 English: Turn AI research goals into mathematical formulations, implementable mechanisms, and testable conclusions. Use for architecture/operator construction, theoretical analysis, cross-field mathematical discovery, math-to-AI transfer, research-related mathematics, and cryptographic definitions, constructions, reductions, or protocol reviews. Exclude implementation-only debugging, refactoring, tuning, and general code review.

Research & Science

Paper2ppt

wp-a/paper2ppt

Use when a user wants an editable PowerPoint or PPTX made from a scientific or academic paper, paper PDF, DOI, PMID, arXiv link, article text, abstract with figure legends, or research notes for a journal club, group meeting, lab meeting, paper sharing, thesis seminar, or research talk; also when they ask for 论文转PPT, 文献汇报, 组会PPT, or 论文解读PPT. Not for general-purpose slide decks, business presentations, slide-image reconstruction, or paper-search-only requests.

Research & Science

Deep Research

24601/agent-deep-research

Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structured JSON output, adaptive polling. Universal skill for 30+ AI agents including Claude Code, Amp, Codex, and Gemini CLI.

Research & Science

Amazon Product Research Skill

shen169/amazon-product-research-skill

Amazon Best Sellers category analysis for e-commerce product research and selection decisions. Activates when users analyze Amazon categories, find black horse products, research competitors, or evaluate market entry opportunities. Triggers on phrases like analyze Amazon category, find high-potential products, Amazon Best Sellers research, product selection analysis, competitor analysis, market opportunity scan. Supports macro category analysis (price tiers, brand concentration, monopoly risk), micro product analysis (potential score calculation), AI-powered product labeling (category type, fo

Research & Science

Apple Health Analysis

labrinyang/apple-health-analysis

Clinical-grade deep analysis of Apple Health export data. Parses the XML from iPhone's Health app export and produces a comprehensive clinical-quality health assessment report using 20+ peer-reviewed statistical methods including Granger Causality, Transfer Entropy, Convergent Cross Mapping, Sample Entropy, DFA, Cosinor analysis, Kovatchev glucose risk indices, Bayesian change-point detection, and biological age estimation. Use this skill whenever the user mentions Apple Health data, health export, health XML, CGM data, wants to analyze their fitness/sleep/heart rate/glucose/weight trends, or

Research & Science

Researcher Recruiting Skill

LofiSu/recruiting-skills

Use when finding authors and public professional evidence for an arXiv paper or exact paper title, or when enriching a filtered batch of researcher candidates handed off by research-talent-scout.

Research & Science

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