explorer: Skill for Claude Code

.claude/skills/record-demo-gif/SKILL.md

record-demo-gif is a skill for Claude Code from anantadwi13/explorer. It costs 50 tokens per session (2,875 once invoked), scanned D, original, MIT.

A recorder for producing desktop and mobile animated GIF demonstrations of a web project for its README. A README is the project’s introductory documentation file.

In plain words
What is it for?
Use it to regenerate the two specified GIFs, adjust their interaction timelines, or add another recorded scene.
Why use it?
It keeps the documented demos aligned with the current interface and can repeat the same interactions in automated tests or CI.

Skill for Claude Code

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

This is anantadwi13/explorer's own configuration. It tells Claude Code how to work on explorer 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 explorer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anantadwi13/explorer. 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/anantadwi13/explorer/main/.claude/skills/record-demo-gif/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/anantadwi13/explorer

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 record-demo-gif

README.md
[![agentmods](https://agentmods.dev/badge/skills/anantadwi13/explorer/record-demo-gif/github.svg)](https://agentmods.dev/skills/anantadwi13/explorer/record-demo-gif)
Your own site
<a href="https://agentmods.dev/skills/anantadwi13/explorer/record-demo-gif"><img src="https://agentmods.dev/badge/skills/anantadwi13/explorer/record-demo-gif/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 record-demo-gif

Your own site · 80×15
<a href="https://agentmods.dev/skills/anantadwi13/explorer/record-demo-gif"><img src="https://agentmods.dev/badge/skills/anantadwi13/explorer/record-demo-gif.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,875 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00050 $0.02875
Opus 5 $0.00025 $0.01437
Sonnet 5 $0.00010 $0.00575
Haiku 4.5 $0.00005 $0.00287

Measured 10d ago against content hash 21d81c5eedb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

record-demo-gif scanned grade D with 3 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (record.mjs, record.sh), 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.

If `ffmpeg` is missing the script prints how to install it (`sudo apt-get install -y ffmpeg`). The first run installs the `ws` npm package into the skill folder; later runs reuse it.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

CDP=$(curl -s http://127.0.0.1:9222/json | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{const t=JSON.parse(d);console.log(t.find(x=>x.type==='page').webSocketDebuggerUrl)})")

Makes network callslowCapability

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

CDP=$(curl -s http://127.0.0.1:9222/json | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{const t=JSON.parse(d);console.log(t.find(x=>x.type==='page').webSocketDebuggerUrl)})")
.claude/skills/record-demo-gif/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Regenerate the README demos. Two GIFs are produced:

  • docs/desktop.gif — 1280×720 capture, scaled to 900px wide
  • docs/mobile.gif — 390×720 capture, scaled to 320px wide

Both run at 12 fps and are encoded with an ffmpeg palettegen/paletteuse filter chain so the small file size doesn't smear text.

Quick start (no timeline changes)

From the repo root:

./.claude/skills/record-demo-gif/record.sh

That single command rebuilds the SPA, regenerates the deterministic testdata/sample-repo (a git repository — required so the git surface is active in the demo), starts a sandboxed explorer instance against it, drives a headless Chromium through the Chrome DevTools Protocol, captures PNG frames, and stitches them into the two GIFs. It cleans up its own background processes on exit.

If ffmpeg is missing the script prints how to install it (sudo apt-get install -y ffmpeg). The first run installs the ws npm package into the skill folder; later runs reuse it.

What's in each timeline

The recorded interactions live in record.mjs under two clearly-marked blocks:

  • // === DESKTOP TIMELINE === — what desktop.gif shows
  • // === MOBILE TIMELINE === — what mobile.gif shows

Edit those blocks to change scenes, then re-run record.sh.

Both demos run against testdata/sample-repo (regenerated on every run by scripts/sample-repo.sh) so the new git surface — branch picker, commits list, commit detail diffs, "N changes" badge — is active.

Current desktop sequence:

  1. Click README.md from the main folder listing → markdown renders.
  2. Smooth-scroll the markdown, then snap back to top.
  3. Open the Settings popover → click Dark → click breadcrumb to dismiss.
  4. Click logo.png in the sidebar tree → binary image preview opens.
  5. Click the branch picker (main ▾) in the toolbar → click View commits → click the first commit → commit detail with file diff renders.

Current mobile sequence:

  1. Tap README.md from the listing → markdown renders.
  2. Scroll, then snap back to top.
  3. Tap the hamburger (Open folders) → drawer slides in.
  4. Tap logo.png in the drawer tree → drawer auto-closes, image preview renders.
  5. Re-open the drawer → tap the branch picker (now in the drawer header) → tap View commits → commits list renders.

Read the full file on GitHub · 160 lines

Files

What ships with it

3 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. 10d ago First seen · 160 lines · 50 tokens per session scan D 21d81c5eedb1

Subscribe to this mod's changes

record-demo-gif is a skill published in the GitHub repository anantadwi13/explorer (2 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 2,875 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ppt-design

A workflow for designing presentation slides as editable HTML pages, with an optional conversion to editable PowerPoint files. It defines slide layouts, an outline, visual rules, and how images are embedded.

GCWing/BitFun · 139 tokens

create-openbitfun-cinematic-wallpaper-skin

Apply the cinematic animated-wallpaper style recipe to a OpenBitFun Appearance skin. Use after loading the parent create-openbitfun-skin Skill when the user provides animated character artwork and wants a host-managed video background, source-derived glass materials, image-led cards, illustrated dialogs, reproducible…

GCWing/BitFun · 75 tokens

pptgen-drawio

A tool for generating multi-page Draw.io presentations and exporting them as PowerPoint files. It supports thesis-defence slides and general presentation decks, with optional PowerPoint templates.

xstongxue/best-skills · 80 tokens

wechat-article-writer

A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.

xstongxue/best-skills · 105 tokens

drawio-diagram

A tool for creating editable Draw.io diagrams, a file format used for flowcharts, system diagrams, and model illustrations.

xstongxue/best-skills · 104 tokens

iib

Interact with IIB (Infinite Image Browsing) service for searching, browsing, tagging, and organizing AI-generated images. Use when the user needs to search images by prompt/keyword, manage image tags, organize files into folders, get image generation parameters, or work with an image library.

zanllp/infinite-image-browsing · 61 tokens