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.
npx skills add Chris1Wang3/Idea-on-Trial --skill ide-briefing-pptgit clone --depth 1 https://github.com/Chris1Wang3/Idea-on-TrialWrote 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.
[](https://agentmods.dev/skills/chris1wang3/idea-on-trial/ide-briefing-ppt)<a href="https://agentmods.dev/skills/chris1wang3/idea-on-trial/ide-briefing-ppt"><img src="https://agentmods.dev/badge/skills/chris1wang3/idea-on-trial/ide-briefing-ppt/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.
<a href="https://agentmods.dev/skills/chris1wang3/idea-on-trial/ide-briefing-ppt"><img src="https://agentmods.dev/badge/skills/chris1wang3/idea-on-trial/ide-briefing-ppt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.01778 |
| Opus 5.5 | $0.00040 | $0.00711 |
| Sonnet 5.5 | $0.00020 | $0.00356 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
ide-briefing-ppt scanned grade A with 0 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 1mo ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Light IDE 简报 PPT
EN Single-file 1280×720 deck locked to the Light IDE UI.
中文 单文件 HTML PPT，界面必须和参考 PPT 长得一样。
When / 何时用： 用户明确点名本 skill、LLM Wiki 原稿，或明确要求整套 Light IDE UI
Not / 不用： 泛指 HTML PPT / 内部分享 · 杂志风 · 瑞士风 · 可编辑 slides · 大表格年报
按 Light IDE 风格做一份分享 PPT
做成和那份 LLM Wiki 分享一样的界面
沿用浅灰 + 琥珀 + 终端 + 文件树那套 UI 做新 PPT
可直接触发的说法
- 用 ide-briefing-ppt 做一份分享。
- 做一份 Light IDE / 终端风 HTML PPT。
- 界面必须和 LLM Wiki 分享那份一样。
- 帮我把大纲做成琥珀面板、浅灰底、等宽页脚的网页 PPT。
最小可用输入
最低可启动：主题 + 大纲（或可提炼大纲的原文）。
推荐输入：标题、场合/日期、页数、每页结论、要不要过程动画、讲稿备注。
可兼容输入：
- 只有主题：先给 6–10 页大纲，确认后再生成。
- 用户说「直接做」：按 8 页默认叙事弧生成，并声明假设。
- 用户点名「和那份 PPT 一样」：视为 UI 锁死，不得换肤。
UI 锁死（违反即失败）
生成结果必须和 LLM Wiki 分享.html / assets/template.html 同一套界面。换主题，不换皮肤。
- 必须整文件拷贝 assets/template.html。
- 禁止改
<style>。:root、字号、圆角、间距、组件 CSS 全部冻结。 - 默认只改两个插槽：
<title>，以及<!-- SLIDES_START -->到<!-- SLIDES_END -->之间的幻灯片。 - 动画是唯一例外：用户明确要求过程动画时，只能在
// ANIMATIONS_START到// ANIMATIONS_END之间新增anims.name函数；不得改其它 runtime。 - 禁止发明 class。只能用模板已有 class；inline
style只能使用版式示例已有的布局属性，正文额外字号只允许封面副标题的22px。 - 禁止换肤：不准换主色、不准加渐变英雄区、不准引入 WebGL / Google Fonts / 衬线标题 / 瑞士超细大字。
- 生成后必须跑：
python scripts/validate_deck.py path/to/deck.html
校验失败就改，不准交付。
详细版式、组件、动画和人工检查项见 references。
工作流
1) 对齐主题、页数、大纲、要不要过程动画
2) 拷贝 assets/template.html 到目标路径
3) 每页从 layouts.md 选版式，只替换文案
4) 需要演示过程时再读 animations.md
5) python scripts/validate_deck.py <输出.html>
6) 浏览器打开，和 template / 原 PPT 对界面
第一步：对齐内容，不讨论换肤
先确认：
| 项 | 默认 |
|---|---|
| 画布 | 1280×720，页内不滚动 |
| 页数 | 短 6–8 / 中 9–12；超出就拆页，不压缩字号 |
| 动画 | 默认关闭；用户明确要「演示过程」再加 |
| 语言 | 跟随用户；中文标题保持原 PPT 的字号阶梯 |
不要问「要不要换个配色」。配色已锁。
默认叙事弧：封面 → 问题/背景 → 2–4 页核心 → 步骤或对比 → 收束。
第二步：拷贝模板
cp "<SKILL_ROOT>/assets/template.html" "path/to/deck.html"
立刻替换 <title> 和封面占位文案。Grep [必填]，交付前必须清零。
第三步：按版式填内容
打开 references/layouts.md，每页选一个骨架粘贴。
What ships with it
8 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.
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.
- 1mo ago First seen · 161 lines · 99 tokens per session scan A a3bf97447c74
ide-briefing-ppt is a skill published in the GitHub repository Chris1Wang3/Idea-on-Trial (4 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,778 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.
Other skills, from other repositories
frontend-design
Design implementation-ready frontend solutions with UX intent, component structure, responsive behavior, accessibility, and handoff criteria.
roblox-gui
Use when building or fixing Roblox menus, HUDs, shops, dialogs, or UI that must work on phones, tablets, desktop and console.
ref-audit
Audits an artist's current reference board mid-modeling and identifies exactly what is missing and why the model might be going wrong. Use when something feels off but you can't identify what, your proportions look wrong, your model doesn't match the reference, or you suspect your reference board has gaps. Triggers on…
bitrix-ui
Bitrix UI kit (ui/main JS extensions, PHP facades): popups, side panels, dialogs, buttons, Toolbar, grid and filter, entity selector, forms, alerts, counters, uploader, viewer, timeline. Use when building admin, portal or component UI.
ref-style-decode
Deconstructs WHY a reference looks the way it does across 9 dimensions. Triggers on "analyze this reference", "why does this look good", "decode this style", "I want my work to look like X", "break down this artist's approach". DCC-agnostic. Works for any asset type.
form-cro
Form optimization for lead capture, contact, demo request, application, and checkout forms. Covers field-cost analysis, multi-step form design, validation UX, mobile optimization, and A/B testing frameworks.