Agent skill

Finger Frame AI

by SylphAI-Inc in SylphAI-Inc/skills

Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing.

No licenceAuto-check passedMedia & Creative

Install Finger Frame AI

skills CLI
$ npx skills add SylphAI-Inc/skills --skill finger-frame-ai -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install SylphAI-Inc/skills finger-frame-ai --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/SylphAI-Inc/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/finger-frame-ai .claude/skills/finger-frame-ai && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
finger-frame-ai
GitHub stars
112
Token cost
~1.2k tokens
SKILL.md length
565 words
Files
9 (incl. scripts, assets)
Skills in repo
8
Repo updated
First seen
Licence
None found

At a glance

Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing.

  • Works in 4 steps: Check readiness → Validate the source → Generate → …
  • Someone asks to make
  • SKILL.md covers When to Use, Required Input and Consent, Instructions and Error Handling
  • Runs Python scripts from its folder; calls python3; needs GOOGLE_API_KEY and GEMINI_API_KEY

What it does

Finger Frame AI is an agent skill from SylphAI-Inc/skills. Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing. Use when someone asks to make, create, restyle, or process a video where a two-hand finger-frame becomes a window into an AI-stylized (default: neon cyberpunk CGI) world.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and assets (for example `README.md`, `scripts/composite.py` and `scripts/process.py`).

It sits in Media & Creative, covering Video production. It works with FFmpeg. The repository describes itself as: Community-shareable skills for AdaL — the automation-first agent harness.

When your agent uses it

  • Someone asks to make
  • Process a video where a two-hand finger-frame becomes a window into an AI-stylized (default: neon cyberpunk CGI) world

Example prompts

  • “/finger-frame-ai”

Requirements

  • Python 3
  • A credential in GEMINI_API_KEY
  • A credential in GOOGLE_API_KEY

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Check readiness
  2. Validate the source
  3. Generate
  4. Verify and report

What it can do on your machine

Read from SKILL.md and the folder at commit 51a5abd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 5 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GOOGLE_API_KEY
    • GEMINI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Finger Frame AI loads about 1.2k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 565 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 565 words (~1,192 tokens).

“Turn a local video of the two-hand finger-frame gesture into an H.264 MP4 where the area inside the fingers reveals an AI-restyled version of the scene.”

— opening of SKILL.md by SylphAI-Inc
name
finger-frame-ai
author
shangliy
version
1.0.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 8 other files (scripts, assets) in skills/finger-frame-ai of SylphAI-Inc/skills.

  • SKILL.md
  • .gitignore
  • README.md
  • assets/finger-frame-skill.mov
  • scripts/composite.py
  • scripts/process.py
  • scripts/requirements.txt
  • scripts/stylize.py
  • scripts/test_process.py

Open the folder on GitHubat commit 51a5abd

Compare with similar skills

Finger Frame AI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Finger Frame AI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Finger Frame AI this skillSylphAI-Inc/skills112—~1.2kAutomated safety check: PassNone
Video Understandcalesthio/OpenMontage66k—~841Automated safety check: PassAGPL-3.0
HyperFrames Video Entry Pointheygen-com/hyperframes60k3 repos~5.2kAutomated safety check: PassApache-2.0
Video Shotseternityspring/reelbench-skills8781 repos~1.8kAutomated safety check: NotesApache-2.0
Mobile Demo Film Editorsuperset-sh/superset15k—~1.8kAutomated safety check: PassCustom licence
Video Editcalesthio/OpenMontage66k—~855Automated safety check: NotesAGPL-3.0

Similar skills

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    60k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Video Shots

    eternityspring/reelbench-skills

    拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.

    878 GitHub starsUsed in 1 repo~1.8k tokens
    Media & CreativeAuto-check: notes
  • Mobile Demo Film Editor

    superset-sh/superset

    Edits real mobile screen recordings into a configurable demo video with phone framing, title cards, cutaways and an end card, using a bundled renderer.

    15k GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Edit

    calesthio/OpenMontage

    Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.

    66k GitHub stars~855 tokensUpdated 7 days ago
    Media & CreativeAuto-check: notes
  • Lemo-Opuscar Short Film Director

    lemomo-ai/lemo-opuscar

    Directs a short film made entirely in code in one of the Lemo-Opuscar library's named visual styles, from fetching the library through production and delivery.

    1.8k GitHub stars~596 tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from SylphAI-Inc/skills

All 8 skills in this repo
  • Glowmotion

    SylphAI-Inc/skills

    Create premium animated technical diagrams as single self-contained HTML+SVG files — flowcharts whose connectors visibly flow and architecture diagrams where requests travel as glowing comet dots…

    112 GitHub stars~1.7k tokensUpdated 18 days ago
    Auto-check passed
  • Codegraph

    SylphAI-Inc/skills

    Turn any codebase into an explorable interactive graph so a developer can understand it fast.

    112 GitHub stars~3.5k tokensUpdated 18 days ago
    Auto-check passed
  • Model Office

    SylphAI-Inc/skills

    Launches "Model Office" — a live browser dashboard that visualizes multi-model job routing as a blocky Lego/Minecraft-style pixel office.

    112 GitHub stars~1.5k tokensUpdated 18 days ago
    Auto-check passed
  • Posthog Analytics

    SylphAI-Inc/skills

    Automate PostHog dashboard creation, sync, update, and export via API

    112 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Create Skill

    SylphAI-Inc/skills

    Guide users through creating AdaL skills by clarifying the skill type (personal, project, or public plugin) and scaffolding the appropriate structure.

    112 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Clone Anywebsite

    SylphAI-Inc/skills

    Clone any website's landing page with pixel-perfect fidelity.

    112 GitHub stars~10k tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Finger Frame AI

What does Finger Frame AI do?

Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing. Finger Frame AI is an agent skill from SylphAI-Inc/skills. Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing.

When should I use Finger Frame AI?

Finger Frame AI fits situations like: someone asks to make; process a video where a two-hand finger-frame becomes a window into an AI-stylized (default: neon cyberpunk CGI) world.

How do I install Finger Frame AI in Claude Code?

Run `npx skills add SylphAI-Inc/skills --skill finger-frame-ai -a claude-code`. Or copy the skill folder (skills/finger-frame-ai in SylphAI-Inc/skills) into .claude/skills/finger-frame-ai in your project. Claude Code loads it when a task matches its description.

How do I install Finger Frame AI in Codex?

Run `npx skills add SylphAI-Inc/skills --skill finger-frame-ai -a codex`. Or copy the skill folder (skills/finger-frame-ai in SylphAI-Inc/skills) into .agents/skills/finger-frame-ai in your project. Codex loads it when a task matches its description.

Can I use Finger Frame AI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SylphAI-Inc/skills --skill finger-frame-ai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/finger-frame-ai, .gemini/skills/finger-frame-ai, .github/skills/finger-frame-ai and .opencode/skills/finger-frame-ai in your project.

What does Finger Frame AI need to run?

Going by SKILL.md and its folder, Finger Frame AI needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named GOOGLE_API_KEY and GEMINI_API_KEY. Our summary lists: Python 3; A credential in GEMINI_API_KEY; A credential in GOOGLE_API_KEY.

Does Finger Frame AI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Finger Frame AI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Finger Frame AI use?

No licence was found for Finger Frame AI or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Finger Frame AI use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Finger Frame AI?

Skills that share tags, products or a category with Finger Frame AI: Video Understand (calesthio/OpenMontage, 66k stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Video Shots (eternityspring/reelbench-skills, 878 stars) and Mobile Demo Film Editor (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Finger Frame AI?

SylphAI-Inc (a GitHub organization) maintains it in SylphAI-Inc/skills, which has 112 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 22, 2026.

Source: SylphAI-Inc/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.