Agent skill

CLI Anything Openscreen

by HKUDS in HKUDS/CLI-Anything

Command-line interface for Openscreen — a screen recording editor.

Apache-2.0Auto-check passedMedia & Creative

Install CLI Anything Openscreen

skills CLI
$ npx skills add HKUDS/CLI-Anything --skill cli-anything-openscreen -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/CLI-Anything cli-anything-openscreen --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/HKUDS/CLI-Anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cli-anything-openscreen .claude/skills/cli-anything-openscreen && 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
cli-anything-openscreen
GitHub stars
52k
Token cost
~1.6k tokens
SKILL.md length
680 words
Files
1
Skills in repo
78
Repo updated
First seen
Licence
Apache-2.0

At a glance

Command-line interface for Openscreen — a screen recording editor.

  • Works in 10 steps: Always use --json for parseable output → Check return codes — 0 = success,… → Parse stderr for error messages in… → …
  • Tasks that involve Video production
  • SKILL.md covers Installation, Usage, Command Groups and State Management, plus 4 more sections
  • Calls pip

What it does

CLI Anything Openscreen is an agent skill from HKUDS/CLI-Anything. Command-line interface for Openscreen — a screen recording editor. A stateful CLI for editing screen recordings with zoom, speed ramps, trim, crop, annotations, and polished exports. Built on the Openscreen JSON project format with ffmpeg as the rendering backend. Designed for AI agents and power users who need programmatic video editing.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Video production. It works with FFmpeg. The repository describes itself as: "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Video production

Example prompts

  • “/cli-anything-openscreen”

Requirements

  • Python 3

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Always use --json for parseable output
  2. Check return codes — 0 = success, non-zero = error
  3. Parse stderr for error messages in non-JSON mode
  4. Use absolute file paths
  5. After export render, verify the output exists and probe it
  6. Times are in milliseconds for all region commands
  7. Coordinates (focus, crop, position) are normalized 0-1
  8. Use preview capture --json to validate zoom, trim, annotation, and timing visually
  9. Read returned bundle artifact paths from the JSON payload; images and clips live on disk
  10. Use cli-hub previews ... only to inspect/open existing bundles

What it can do on your machine

Read from SKILL.md and the folder at commit 34f5195. 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

    Shell commands in SKILL.md call:

    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

CLI Anything Openscreen loads about 1.6k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 680 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/CLI-Anything at commit 34f5195, republished under its Apache-2.0 licence (© HKUDS). 680 words, ~1,606 tokens.

Download SKILL.mdSave it as .claude/skills/cli-anything-openscreen/SKILL.md (or your agent's skills folder).
name
cli-anything-openscreen
description
Command-line interface for Openscreen — a screen recording editor. A stateful CLI for editing screen recordings with zoom, speed ramps, trim, crop, annotations, and polished exports. Built on the Openscreen JSON project format with ffmpeg as the rendering backend. Designed for AI agents and power users who need programmatic video editing.

cli-anything-openscreen

A stateful command-line interface for editing screen recordings. Transform raw captures into polished demo videos with zoom effects, speed adjustments, trimming, annotations, and beautiful backgrounds.

Installation

bash
pip install cli-anything-openscreen

Prerequisites:

  • Python 3.10+
  • ffmpeg must be installed on your system

Usage

Basic Commands
bash
cli-anything-openscreen --help
cli-anything-openscreen                     # REPL mode
cli-anything-openscreen project new -v recording.mp4 -o project.openscreen
cli-anything-openscreen --json project info
REPL Mode

Run cli-anything-openscreen without arguments to enter interactive mode. Type help for available commands, quit to exit.

Command Groups

project

Create, open, save, and configure projects.

CommandDescription
project new [-v VIDEO] [-o PATH]Create new project with optional video
project open <path>Open existing .openscreen project
project save [-o PATH]Save project to file
project infoShow project metadata and region counts
project set-video <path>Set source video file
project set <key> <value>Set editor setting (padding, wallpaper, etc.)
zoom

Manage zoom regions — smooth zoom effects on specific timeline areas.

CommandDescription
zoom listList all zoom regions
zoom add --start MS --end MS [--depth 1-6] [--focus-x 0-1] [--focus-y 0-1]Add zoom
zoom remove <id>Remove zoom region

Zoom depths: 1=1.25x, 2=1.5x, 3=1.8x, 4=2.2x, 5=3.5x, 6=5.0x

speed

Manage speed regions — speed up idle time, slow down important moments.

CommandDescription
speed listList all speed regions
speed add --start MS --end MS [--speed 0.25-2.0]Add speed change
speed remove <id>Remove speed region

Valid speeds: 0.25, 0.5, 0.75, 1.25, 1.5, 1.75, 2.0

trim

Manage trim regions — cut out sections of the recording.

CommandDescription
trim listList all trim regions
trim add --start MS --end MSCut out a section
trim remove <id>Remove trim region
crop

Set the visible area of the recording.

CommandDescription
crop getShow current crop region
crop set --x 0-1 --y 0-1 --width 0-1 --height 0-1Set crop (normalized)
annotation

Add text overlays to the recording.

CommandDescription
annotation listList all annotations
annotation add-text --start MS --end MS --text "..." [--x 0-1] [--y 0-1]Add text
annotation remove <id>Remove annotation
media

Inspect and validate media files.

CommandDescription
media probe <path>Show video metadata (resolution, duration, codec)
media check <path>Validate a video file
media thumbnail <input> <output> [-t TIME]Extract a frame
export

Render the final polished video.

CommandDescription
export presetsList available export presets
export render <output_path>Render project to video file
Show full SKILL.md (316 more words)Show less
preview

Capture truthful review bundles from the current Openscreen project.

CommandDescription
preview recipesList available preview recipes
preview capture --recipe quickRender a low-res preview bundle
preview latest [--recipe quick]Return the latest existing bundle

Current preview support is static rather than live. A quick bundle typically contains:

  • a low-res preview clip
  • sampled frames
  • a hero frame for quick inspection
  • summary.json with trim/zoom/speed facts

Bundle capture also writes or updates a stable recipe-level trajectory.json beside the preview root so agents can reconstruct preview history over time.

Viewer commands:

bash
cli-hub previews inspect /path/to/bundle
cli-hub previews html /path/to/bundle -o page.html
cli-hub previews open /path/to/bundle
session

Manage session state with undo/redo.

CommandDescription
session statusShow session info
session undoUndo last operation
session redoRedo last undone operation
session saveSave session state to disk
session listList all saved sessions

State Management

  • Undo/Redo: Up to 50 levels of undo history
  • Project persistence: JSON .openscreen files
  • Session tracking: auto-tracks modifications

Output Formats

  • Human-readable (default): Formatted key-value pairs
  • Machine-readable (--json): Structured JSON output

Editor Settings

SettingTypeDefaultDescription
aspectRatiostring"16:9"16:9, 9:16, 1:1, 4:3, 4:5
wallpaperstring"gradient_dark"Background preset
paddingint500-100, padding around video
borderRadiusint12Corner radius in pixels
shadowIntensityfloat00-1, drop shadow strength
motionBlurAmountfloat00-1, motion blur during zoom
exportQualitystring"good"medium, good, source
exportFormatstring"mp4"mp4, gif

For AI Agents

  1. Always use --json for parseable output
  2. Check return codes — 0 = success, non-zero = error
  3. Parse stderr for error messages in non-JSON mode
  4. Use absolute file paths
  5. After export render, verify the output exists and probe it
  6. Times are in milliseconds for all region commands
  7. Coordinates (focus, crop, position) are normalized 0-1
  8. Use preview capture --json to validate zoom, trim, annotation, and timing visually
  9. Read returned bundle artifact paths from the JSON payload; images and clips live on disk
  10. Use cli-hub previews ... only to inspect/open existing bundles

Version

1.0.0

© HKUDS, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/cli-anything-openscreen of HKUDS/CLI-Anything.

Open the folder on GitHubat commit 34f5195

Compare with similar skills

CLI Anything Openscreen 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.

CLI Anything Openscreen compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CLI Anything Openscreen this skillHKUDS/CLI-Anything52k—~1.6kAutomated safety check: PassApache-2.0
Video Understandcalesthio/OpenMontage65k—~841Automated safety check: PassAGPL-3.0
HyperFrames Video Entry Pointheygen-com/hyperframes58k3 repos~5.2kAutomated safety check: PassApache-2.0
Video Shotseternityspring/reelbench-skills8671 repos~1.8kAutomated safety check: NotesApache-2.0
Mobile Demo Film Editorsuperset-sh/superset15k—~1.8kAutomated safety check: PassCustom licence
Video Editcalesthio/OpenMontage65k—~855Automated safety check: NotesAGPL-3.0

Similar skills

  • Video Understand

    calesthio/OpenMontage

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

    65k GitHub stars~841 tokensUpdated 4 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.

    58k 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.

    867 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.

    65k GitHub stars~855 tokensUpdated 4 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.

    1.3k GitHub stars~596 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed

More from HKUDS/CLI-Anything

All 78 skills in this repo
  • CLI-Anything for Codex

    HKUDS/CLI-Anything

    Lets Codex build, refine, test, validate and list CLI-Anything harnesses for GUI applications or source repositories, following the project's full methodology.

    52k GitHub stars~1.5k tokensUpdated 15 days ago
    Auto-check passed
  • CLI-Anything for Reasonix

    HKUDS/CLI-Anything

    Adapts the CLI-Anything methodology so Reasonix can build, refine, test and validate a command-line harness for an existing GUI application or source repository.

    52k GitHub stars~1.8k tokensUpdated 15 days ago
    Auto-check passed
  • Guides Hermes Agent through building, refining and testing a CLI-Anything harness that wraps a GUI application or source repository in a scriptable command line.

    52k GitHub stars~1.1k tokensUpdated 15 days ago
    Auto-check passed
  • Builds, refines, tests or validates a CLI-Anything harness that wraps a GUI application or source repository as a stateful Click CLI with JSON output and a REPL mode.

    52k GitHub stars~839 tokensUpdated 15 days ago
    Auto-check passed
  • Krita CLI Harness

    HKUDS/CLI-Anything

    Drives Krita from the command line to create projects, add layers, apply filters, resize the canvas and export images, with JSON output for agents.

    52k GitHub stars~931 tokensUpdated 15 days ago
    Auto-check passed
  • MacroCLI GUI Macros

    HKUDS/CLI-Anything

    Defines, lists, inspects and runs parameterized GUI macros from the command line, with the runtime choosing the execution backend.

    52k GitHub stars~1.4k tokensUpdated 15 days ago
    Auto-check passed

Works with

Questions about CLI Anything Openscreen

What does CLI Anything Openscreen do?

Command-line interface for Openscreen — a screen recording editor. CLI Anything Openscreen is an agent skill from HKUDS/CLI-Anything. Command-line interface for Openscreen — a screen recording editor.

When should I use CLI Anything Openscreen?

CLI Anything Openscreen fits situations like: tasks that involve Video production.

How do I install CLI Anything Openscreen in Claude Code?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything-openscreen -a claude-code`. Or copy the skill folder (skills/cli-anything-openscreen in HKUDS/CLI-Anything) into .claude/skills/cli-anything-openscreen in your project. Claude Code loads it when a task matches its description.

How do I install CLI Anything Openscreen in Codex?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything-openscreen -a codex`. Or copy the skill folder (skills/cli-anything-openscreen in HKUDS/CLI-Anything) into .agents/skills/cli-anything-openscreen in your project. Codex loads it when a task matches its description.

Can I use CLI Anything Openscreen 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 HKUDS/CLI-Anything --skill cli-anything-openscreen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cli-anything-openscreen, .gemini/skills/cli-anything-openscreen, .github/skills/cli-anything-openscreen and .opencode/skills/cli-anything-openscreen in your project.

What does CLI Anything Openscreen need to run?

Going by SKILL.md and its folder, CLI Anything Openscreen needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does CLI Anything Openscreen access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is CLI Anything Openscreen 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. Review the folder before installing.

What licence does CLI Anything Openscreen use?

CLI Anything Openscreen is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CLI Anything Openscreen use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 CLI Anything Openscreen?

Skills that share tags, products or a category with CLI Anything Openscreen: Video Understand (calesthio/OpenMontage, 65k stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 58k stars), Video Shots (eternityspring/reelbench-skills, 867 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 CLI Anything Openscreen?

HKUDS (a GitHub organization) maintains it in HKUDS/CLI-Anything, which has 51,644 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on September 22, 2026.

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