eva: Skill for Claude Code

.claude/skills/eva-feature-screenshot/SKILL.md

eva-feature-screenshot is a skill for Claude Code from vvedantb/eva. It costs 144 tokens per session (3,149 once invoked), scanned A, original, MIT.

A workflow for capturing a clean, high-resolution screenshot of a new eva feature from the running app and preparing a framed version plus a post.

In plain words
What is it for?
Use it to capture a crisp 16:9 feature screenshot, create a branded version, and write an announcement for X.
Why use it?
It produces a readable product image without browser overlays or manually adding promotional text to the interface.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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 →

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-feature-screenshot/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-feature-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvedantb/eva/eva-feature-screenshot/github.svg)](https://agentmods.dev/skills/vvedantb/eva/eva-feature-screenshot)
Your own site
<a href="https://agentmods.dev/skills/vvedantb/eva/eva-feature-screenshot"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-feature-screenshot/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 eva-feature-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/vvedantb/eva/eva-feature-screenshot"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-feature-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,149 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 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 Memory Poisoning · line 61
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium MCP Rug Pull · line 76
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 80
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Prompt Injection · line 179
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 $0.00144 $0.03149
Opus 5 $0.00072 $0.01574
Sonnet 5 $0.00029 $0.00630
Haiku 4.5 $0.00014 $0.00315

Measured 5d ago against content hash b8606e1e541c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eva-feature-screenshot 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 5d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/frame.sh, scripts/hd-frame.mjs, scripts/hd-shot.mjs, …), 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.

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-feature-screenshot/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eva feature shot

One screenshot of a shipped feature + one tweet. No Remotion, no music, no editing, no captions burned into the image — the product UI is the asset.

Two files land in screenshots/ at the repo root (already gitignored):

File What it is
<YYYY-MM-DD>-<slug>.png raw 2560×1440 shot — keep it, it is the reshoot-free source
<YYYY-MM-DD>-<slug>-framed.png post this one — 3200×1800, branded frame

The framed version sits the raw shot on eva's brand gradient with rounded corners, an eva icon and the "Eva" wordmark above it. That is why the shot reads as a product announcement rather than a bug report screenshot.

Non-negotiable defaults

  1. 1280 layout, captured HD at 2560×1440 (16:9). The scripts drive a real Chrome at deviceScaleFactor 2 and capture scale:"device", so the app lays out at its native 1280 width (readable element sizes) but the PNG is twice the pixel density — crisp on a retina timeline. 16:9 is what X shows in-timeline without cropping. The framed output is 3200×1800 — also 16:9, so the frame costs nothing in the timeline. agent-browser cannot do this: its screenshot captures at CSS pixels and discards DPR, so it always outputs 1280×720. Use the HD scripts.

  2. Never full-page. A full-page shot of a dense app becomes a tall strip that renders thumbnail-sized in the timeline. One viewport, one idea.

  3. Hide the dev overlays before shooting. react-scan and agentation both render into the page. scripts/hd-shot.mjs handles it — use the scripts rather than a hand-rolled chain.

  4. Match the app's real theme. Whatever the user is running (set media dark for dark). Don't restyle the app for the photo.

  5. The feature must be the visual subject. A 200px panel in the corner of a busy page fails. Navigate to a view where it dominates, or open the surface that contains it (modal, sheet, detail pane) so it reads at timeline size.

Read the full file on GitHub · 208 lines

Files

What ships with it

5 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. 5d ago First seen · 208 lines · 144 tokens per session scan A b8606e1e541c

Subscribe to this mod's changes

eva-feature-screenshot is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 3,149 once invoked, about $0.0007 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

html-ppt-zhangzara-retro-zine

A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.

nexu-io/open-design · 49 tokens

html-ppt-zhangzara-studio

A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.

nexu-io/open-design · 47 tokens

motion-frames

A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…

nexu-io/open-design · 91 tokens

webgl-halftone-drift

A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.

nexu-io/open-design · 44 tokens

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

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens