agentmods.dev

gbro-collage-broll

gbro-collage-broll is a skill for Codex from happycapy-ai/Happycapy-skills. It costs 264 tokens per session (8,735 once invoked), scanned B, original, MIT.

A workflow for turning spoken scripts, opinion statements, or abstract ideas into short editorial-style paper-collage animation clips. It plans the segments, visual metaphors, still images, and final video in stages.

In plain words
What is it for?
Creating one 5–10 second collage B-roll clip or combining several clips into an advertisement, with segmentation, visual concepts, generated stills, video creation, and quality checks.
Why use it?
An abstract message can be difficult to translate into a consistent visual sequence, and generating every clip immediately can waste time and resources. The staged approvals let the user confirm timing, ideas, and still images before video generation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Codex.

not rated 139repo +2 9d ago B scan SkillSpector: warn 264 tokens original MIT

Good fit Creating one 5–10 second collage B-roll clip or combining several clips into an advertisement, with segmentation, visual concepts, generated stills, video creation, and quality checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happycapy-ai/happycapy-skills/gbro-collage-broll
View source ↗ happycapy-ai/Happycapy-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add happycapy-ai/Happycapy-skills --skill gbro-collage-broll
Clone the repo
git clone --depth 1 https://github.com/happycapy-ai/Happycapy-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gbro-collage-broll

README.md
[![agentmods](https://agentmods.dev/badge/skills/happycapy-ai/happycapy-skills/gbro-collage-broll/github.svg)](https://agentmods.dev/skills/happycapy-ai/happycapy-skills/gbro-collage-broll)
Your own site
<a href="https://agentmods.dev/skills/happycapy-ai/happycapy-skills/gbro-collage-broll"><img src="https://agentmods.dev/badge/skills/happycapy-ai/happycapy-skills/gbro-collage-broll/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gbro-collage-broll

Your own site · 80×15
<a href="https://agentmods.dev/skills/happycapy-ai/happycapy-skills/gbro-collage-broll"><img src="https://agentmods.dev/badge/skills/happycapy-ai/happycapy-skills/gbro-collage-broll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 264 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,735 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Privilege Escalation · line 42
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Rogue Agent · line 260
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00264 $0.08735
Opus 5 $0.00132 $0.04367
Sonnet 5 $0.00053 $0.01747
Haiku 4.5 $0.00026 $0.00873

Measured 13d ago against content hash 353c51dce733, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

gbro-collage-broll scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/check_setup.sh, scripts/estimate_duration.py, scripts/generate_still_gateway.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo apt-get install -y ffmpeg`（Debian/Ubuntu）。征得用户同意后可直接安装。

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **拿到真实 logo 文件**：如果用户给的是一个网页链接（官网/文档站）而不是文件，先用 WebFetch 抓一遍确认品牌信息，但**WebFetch 的 markdown 转换经常漏掉 `<img>` 标签**（尤其是 React/Mintlify 一类前端渲染的站点，导航栏 logo 常常这样），如果 WebFetch 说"没找到 logo 图片"不要就此放弃，改用 `browser navigate` 打开页面，再用 `
skills/gbro-collage-broll/SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gbro Collage B-roll

把口播文稿压成一组 sharp visual idea，再做成高级编辑风纸拼贴组装动画——可以是一条 5-10 秒短片，也可以是多段拼接成一条完整广告。

默认链路：

  1. 按文案自动分段，算出每段预估时长，等待用户确认段数/时长/背景色方案
  2. 对每段只设计视觉隐喻，等待用户确认
  3. 只生成最终静帧，等待用户确认
  4. 自动调用 Gemini Omni Flash 生成视频（每段时长按台词长度动态计算）并完成 QA

这几个确认闸门是工作流的一部分。它们让用户把注意力放在审美、方向和节奏上，同时避免错误分段、错误隐喻或错误静帧直接消耗视频生成成本。

沟通语言

跟用户沟通（Gate 0-3 的每一次输出、确认提示、QA 结论、交付说明）都用用户当前对话使用的语言，不要固定用中文。本文档里的字段名（"核心意思""情绪""一句话视觉命题"等）是给你看的语义占位，实际向用户展示时翻译成对方的语言——用户说英文就整套用英文回，用户说中文才用中文。

唯一固定用英文的地方是发给图片/视频模型的 prompt 本身（imagegen prompt、omni prompt），不管用户用什么语言沟通，这两类 prompt 都保持英文——模型对英文 prompt 的理解和风格控制明显更稳定。台词/字幕/配音文本则跟用户语言或用户指定的语言走，不要自作主张替用户翻译成中文再拿去配音。

首次使用：环境自检

每次触发本 skill 时，进入 Gate 1 之前先运行自检脚本：

bash <本skill目录>/scripts/check_setup.sh

全部通过则直接开始 Gate 1，不要向用户重复配置信息。任何一项失败时，视为首次使用：不进入 Gate 1，先向用户输出下面的配置指南（只列出缺失项），等用户确认配置完成后重新自检。

配置指南（按缺失项输出）

  1. AI_GATEWAY_API_KEY 未设置 这是本环境的内置凭证，Gate 2（静帧）和 Gate 3（视频）都靠它经 AI Gateway 调用模型。正常情况下平台已自动注入；如果自检显示缺失，提示用户联系平台方，不要让用户去 Google AI Studio 申请 key（那是旧链路的做法，本变体不需要）。

  2. ffmpeg / ffprobe 缺失 sudo apt-get install -y ffmpeg（Debian/Ubuntu）。征得用户同意后可直接安装。

  3. Python 环境缺失或版本过旧（需要 >= 3.10） 用于 scripts/generate_still_gateway.py。

  4. node 缺失 用于调用 generate-video 兄弟 skill 的 generate_video_sdk.js。

  5. generate-image / generate-video 兄弟 skill 缺失 本变体依赖它们，可能装在 ~/.claude/skills/generate-image / ~/.claude/skills/generate-video（按 Happycapy-skills 目录标准装法），也可能在 /opt/claude-skills/generate-image / /opt/claude-skills/generate-video（部分 Happycapy 沙箱预装位置）。check_setup.sh 会自动探测这两个位置，取实际存在的那个；后文所有命令里的 <generate-video 目录> / <generate-image 目录> 都指 check_setup.sh 探测到的那个真实路径。两个位置都没找到时，向用户说明需要等效的图片/视频生成工具，或退回原版 Codex 链路。

强制审批协议

Gate 0：分段与时长规划

在设计任何隐喻之前，先确定"要做几段、每段多长、背景色怎么处理"。这一步只做文本分析和算术，不生成图片、不生成视频。

  1. 自动分段：按句号/破折号/语义转折把用户给的完整文案切成候选段落。每段应该对应一个独立、能一眼看懂的视觉隐喻——不要把两个不同的意思塞进一段，也不要把一个意思拆得过碎。如果用户已经给了明确分好的几句话，直接按用户的分句来，不用再自动切。

  2. 估算每段时长：对每个候选段落调用

    python3 <本skill目录>/scripts/estimate_duration.py "<该段台词>" --lang auto

Read the full file on GitHub · 440 lines

Files

What ships with it

14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 440 lines · 264 tokens per session scan B 353c51dce733

Subscribe to this mod's changes

gbro-collage-broll is a skill published in the GitHub repository happycapy-ai/Happycapy-skills (139 stars, last pushed 9d ago), licensed MIT. It adds 264 tokens to every session and 8,735 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens