eva: Skill for Claude Code

.claude/skills/eva-launch-video/SKILL.md

eva-launch-video is a skill for Claude Code from vvedantb/eva. It costs 152 tokens per session (2,804 once invoked), scanned A, original, MIT.

A workflow for producing polished product-demo videos from real recordings of the eva app, with edited scenes, music, and captions.

In plain words
What is it for?
Use it to recapture screens, adjust scenes and timings, generate matching music, render the video, and check the result.
Why use it?
It turns a raw app recording into a finished video suitable for showing a feature.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vvedantb/eva's own configuration. It tells Claude Code how to work on eva itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eva configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/gen-lofi-variants.mjs --duration=20.5 --cuts=2.5,5.5,8.5,11.5,14.5,17.5 \.

Reuse

Borrowing it

Nothing to install: this file belongs to vvedantb/eva. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vvedantb/eva/main/.claude/skills/eva-launch-video/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vvedantb/eva

Made for: Claude Code.

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 eva-launch-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvedantb/eva/eva-launch-video.svg)](https://agentmods.dev/skills/vvedantb/eva/eva-launch-video)
Your own site
<a href="https://agentmods.dev/skills/vvedantb/eva/eva-launch-video"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-launch-video.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00152 $0.02804
Opus 5 $0.00076 $0.01402
Sonnet 5 $0.00030 $0.00561
Haiku 4.5 $0.00015 $0.00280

Measured 3d ago against content hash 38c296105e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eva-launch-video 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 3d 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.

.claude/skills/eva-launch-video/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eva product video

Make a high-end product video of the eva app (Linear/Notion quality) using the existing Remotion project at video/. Footage comes from the real app, captured with agent-browser.

Wrong skill? This one is the polished multi-scene edit (Remotion, music, captions). For a single feature, prefer the lighter siblings: eva-feature-screenshot (one screenshot + tweet) or eva-feature-demo (one raw agent-browser recording + tweet). Tweet copy for any of the three comes from eva-tweet.

The canonical project already exists — reuse it, don't start over.

  • Project: video/ · primary composition: EvaHero (video/src/EvaHero.tsx)
  • Render output: video/out/eva-demo.mp4
  • Reusable components in video/src/components/: Backdrop, AppWindow, EvaMark, HeroCaption (+ Accent), Cursor, Spotlight, StatCounter, SnapIn, tokens.
  • Helper scripts in video/scripts/: stills.mjs, gen-music.mjs, check-audio.mjs.

To make a NEW video: re-capture screens for the new story, edit the scene list / captions / durations in EvaHero.tsx, regenerate the music to match the cut times, render, QA.

Non-negotiable defaults (learned the hard way — change only with a reason)

Each of these was a mistake first. Keep them unless the user overrides.

  1. 1280×720, 30fps. Not 1080p. The eva UI is a dense desktop app; at 1080p it reads "too zoomed / too big" on a phone. 720p is the mobile-friendly sweet spot for Twitter/X.

  2. Capture at the frame's native layout, show full-bleed. Set the browser viewport to 1280×720 when capturing, then display the screenshot full-bleed at 1:1 (filling the whole frame). The single biggest quality lever:

    • Capturing at 2560×1440 and downscaling to 720p halves UI text size → "zoomed out" and unreadable on mobile.
    • Cropping/zooming the camera into a region shows awkward fragments of the UI.
    • A 1280-wide layout shown 1:1 = native element sizes = readable + "zoomed in" + crisp.

Read the full file on GitHub · 167 lines

Files

What ships with it

2 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. 3d ago First seen · 167 lines · 152 tokens per session scan A 38c296105e72

Subscribe to this mod's changes

eva-launch-video is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 2,804 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

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…

heygen-com/hyperframes · 92 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens