Borrowing it
Nothing to install: this file belongs to Kewton/CommandMate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kewton/CommandMate/main/.agents/skills/video-to-gif/SKILL.mdgit clone --depth 1 https://github.com/Kewton/CommandMateWrote 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/kewton/commandmate/video-to-gif)<a href="https://agentmods.dev/skills/kewton/commandmate/video-to-gif"><img src="https://agentmods.dev/badge/skills/kewton/commandmate/video-to-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.
<a href="https://agentmods.dev/skills/kewton/commandmate/video-to-gif"><img src="https://agentmods.dev/badge/skills/kewton/commandmate/video-to-gif.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.02694 |
| Opus 5 | $0.00056 | $0.01347 |
| Sonnet 5 | $0.00023 | $0.00539 |
| Haiku 4.5 | $0.00011 | $0.00269 |
Grade A, and why
video-to-gif 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 10d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-to-gif
録画済みの動画を GIF にする。to-gif.sh 一発で、バイト予算に収まる GIF が出る。
.claude/skills/video-to-gif/scripts/to-gif.sh demo.mp4 # demo.gif を隣に出す
.claude/skills/video-to-gif/scripts/to-gif.sh *.mp4 --out docs/images/features
.claude/skills/video-to-gif/scripts/to-gif.sh clip.mp4 --max-bytes 500k
.claude/skills/video-to-gif/scripts/to-gif.sh --ladder # 再試行の段取りだけ表示（ffmpeg 不要）
.claude/skills/video-to-gif/scripts/to-gif.sh --report docs/images/features/*.gif
.claude/skills/video-to-gif/scripts/to-gif.sh --check # 依存確認のみ
なぜ GIF なのか
GitHub の markdown ビューアは <video> を描画しない。HTML 許可リストに含まれておらず、
動画添付が再生されるのは issue / PR / discussion のコメントだけである。リポジトリ内の
.md に貼って動く動画は GIF しかない。
例外は GitHub Pages（website/）で、そちらは素の HTML がそのまま配信されるので
<video> が使える。LP に置くなら GIF ではなく mp4 の方が軽い（実測 GIF 1.02MB に対し
mp4 0.56MB）。GIF が要るのは docs 配下の markdown だけ。
なぜ demo-video の compose.sh --gif と別なのか
compose.sh --gif は合成パイプラインの途中でしか発火せず、720px / 12fps / sierra2_4a を
ハードコードしている。docs に載せるときに要るのは「完成済みの mp4 から、リポジトリが
背負えるサイズの GIF を作る」ことで、しかも収まったかどうかは測って判断する必要がある。
この 2 点は合成の関心事ではないので別スキルにした。
設計判断: dither は既定で切る
同一素材（20 秒 / 1280x800 の UI キャプチャ）を、無劣化リファレンスに対する SSIM で実測した。
| 設定 | バイト数 | SSIM (All) |
|---|---|---|
colors=256 dither=none ← 既定 |
1,073,725 | 0.99653 |
colors=128 dither=none |
883,912 | 0.99439 |
colors=128 dither=sierra2_4a |
1,271,671 | 0.99160 |
colors=128 dither=bayer |
998,339 | 0.99149 |
colors=64 dither=none |
736,163 | 0.99202 |
ディザは 2 軸とも悪化させる。 空間ノイズを撒くので GIF が圧縮に使う LZW の run が壊れ、
かつ画面録画の大半を占める平坦な UI パネルには均すべきグラデーションが無い。
colors=64 + sierra2_4a は 1,472,301 バイトで colors=128 の同ディザより大きい —
パレットが粗いほど誤差拡散が遠くまで広がるためである。
グラデーションが実在する素材（写真・動画コンテンツ）では --dither sierra2_4a を
意識して渡すこと。既定で有効にはしない。
--stats-mode diff も測ったが誤差の範囲で、むしろ僅かに大きくなった（full のまま）。
バイト予算とラダー
--max-bytes（既定 1.5M）に収まるまで、3 軸をラウンドロビンで一段ずつ落として再試行する。
fps を底まで落としてから解像度に手を付ける、という順序にはしない。4fps 等倍も 360px 30fps も
中間の妥協より見た目が悪く、画面の文字が読めることが UI デモの目的だからである。
What ships with it
1 file 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.
- 10d ago First seen · 142 lines · 113 tokens per session scan A c8dcc43c8743
video-to-gif is a skill published in the GitHub repository Kewton/CommandMate (40 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 2,694 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
crow-show-image
Surface an image you've generated (a diagram, chart, screenshot, or rendered figure) in Crow's Images panel so the user can see it inline. Use whenever you produce a visual artifact worth showing.
verify
Drive CrowTelemetry's OTLP ingest end-to-end — boot the real receiver, POST OTLP JSON with curl, inspect the SQLite db.
domux-communicate
Use when you (an agent in one domux worktree) need to hand work to, message, or read the output of the Claude agent running in ANOTHER worktree. Covers the canonical peer handoff — "I built X on branch Y, please pull it in" — plus discovering which agents are running. Wraps domux peek / domux send / domux read.
crow-review-pr
Perform a comprehensive code and security review on a GitHub pull request, then post the findings as a PR review. Use when the user invokes /crow-review-pr or asks to review a pull request through Crow.
crow-batch-workspace
Set up multiple Crow workspaces in parallel, delegating to crow-workspace's setup.sh for each and firing them simultaneously to cut total setup time. Use when the user invokes /crow-batch-workspace or asks to set up several Crow workspaces at once.
domux-start
Use when starting or kicking off a new task in a tmux+domux workbench — sets up the workspace before any code: resolves the git worktree root, branches off fresh origin/main, labels the domux session so the human can find it in the switcher, then begins the task. Invoke at the start of task-shaped requests in a…