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 agentmods add skills/emilyli2020/wave/demo-prepnpx skills add emilyLi2020/WAVE --skill demo-prepgit clone --depth 1 https://github.com/emilyLi2020/WAVEWrote 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/emilyli2020/wave/demo-prep)<a href="https://agentmods.dev/skills/emilyli2020/wave/demo-prep"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/demo-prep.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00531 |
| Opus 5 | $0.00023 | $0.00266 |
| Sonnet 5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
demo-prep 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 4d 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.
What it actually says
Demo Prep
The user is about to present their project at a hackathon or demo day. Help them create a polished, timed demo script that tells a compelling story.
Step 1: Gather Context
Ask the user:
- What does your app do? (one sentence)
- Who is it for?
- What is the single most impressive thing it does?
- How long is your presentation slot? (default: 3 minutes)
- Will you do a live demo, recorded video, or slides?
Step 2: Write the Demo Script
Structure the script in three acts:
Act 1: The Problem (30 seconds)
- One sentence describing the pain point
- One concrete example or statistic that makes it real
- "What if there was a better way?"
Act 2: The Solution (90 seconds)
- Show the app running (live or recorded)
- Walk through the core user flow step by step
- Highlight the "wow moment" (the single most impressive feature)
- Keep clicks to a minimum; narrate what is happening
Act 3: The Impact (30 seconds)
- What changes because this exists?
- One metric, testimonial, or future vision
- Clear closing statement
Step 3: Prepare the Backup Plan
- Record a screen capture of the full demo flow (in case live demo fails)
- Prepare 2-3 screenshots of key screens as fallback slides
- Test the app on the presentation machine/network before going on stage
- Have the live URL ready as a backup to localhost
Step 4: Rehearse Checklist
- Timed the full presentation (fits within the slot)
- Practiced at least 3 times out loud
- Tested the app on the demo machine
- Backup video/screenshots are ready
- Opening line is memorized (no fumbling the start)
- Closing line is memorized (end strong)
Output
Return:
- Script: The full narrated demo script with timestamps
- Click Path: Exact sequence of actions to perform during the demo
- Backup Plan: What to do if the live demo breaks
- Q&A Prep: 3-5 likely questions judges will ask, with suggested answers
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.
- 4d ago First seen · 62 lines · 45 tokens per session scan A 9aa4c220902e
demo-prep is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 531 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.