SkillAgentSearch skills...

frameflow

AI video editor for desktop. Edit by chat on a real timeline: cut filler, sync multicam, add motion graphics, captions and thumbnails. macOS, Windows, Linux.

Install / Use

claude mcp add navidshad -- npx -y github:navidshad/frameflow

If the server publishes to npm under a different name, use that package instead โ€” check the repo README.

About this skill
๐Ÿ”Œ

MCP Server

Model Context Protocol server

Quality Score

85/100

Supported Platforms

Claude Code
Claude Desktop
Gemini CLI

Our assessment of frameflow

frameflow scores 85/100 on our quality scale, 2520th of 4,720 Development & Engineering skills we index.

Its MCP Server is 15 KB long, well organised into 15 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.

It has 44 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
18/20
Description
15/15
Adoption
7/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 3 days ago, so frameflow is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 85/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit โ€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-16. Automated pattern scan on 2026-11-16. It catches known dangerous patterns, not every risk โ€” read a skill before letting an agent act on it.

frameflow compared with similar skills

All 4 of these similar skills score higher than frameflow; compare them before choosing.

SkillScoreStarsUpdatedFormat
frameflow (this skill)by navidshad85443d agoMCP Server
taste-skillby Leonxlnx100117.8k9d agoCLAUDE.md
Agent-Reachby Panniantong100112.8k10d agoCLAUDE.md
rufloby ruvnet10082.0ktodayCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md

Frequently asked questions

How do I install frameflow?
Run claude mcp add navidshad -- npx -y github:navidshad/frameflow. The install tabs above show the steps for each supported agent.
Which AI agents does frameflow work with?
It is written for Claude Code, Claude Desktop and Gemini CLI, as a MCP Server file. Other agents that read the same format can often use it too.
Is frameflow safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 85/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is frameflow still maintained?
The repository was last updated 3 days ago, so frameflow is actively maintained.
<div align="center">

FrameFlow

Talk to your video editor.

FrameFlow is an AI video editor for macOS, Windows and Linux.<br> Drop in your footage and say what you want. It builds the cut on a real timeline,<br> so you can still change anything by hand.

<br>

Download for macOS Download for Windows Download for Linux

<br> <img src="docs/readme/hero-dark.webp" width="100%" alt="The FrameFlow editor. On the left, the video's words as a list. In the middle, the picture with an animated week planner drawn over it. On the right, a chat where the user asked to cut the filler and the assistant answered. Along the bottom, the timeline with a motion track, a cutaway clip, the main video and sound effects.">

<sub>A desktop app for macOS, Windows and Linux ยท Free for personal and other noncommercial use</sub>

</div> <br>

What people make with it

1 ยท Clean up a talking video

For vloggers, teachers and anyone who records themselves.

Type one sentence:

Cut the filler words, the false start and the long pauses. Keep everything else in order.

FrameFlow listens to the recording, finds the slips and gives back a tighter cut. Here a 64-second take became 35 seconds.

<p align="center"> <img src="docs/readme/talk-chat.webp" width="49%" alt="The chat: the request to cut filler, false start and pauses, and the start of the assistant's answer listing what it removed."> <img src="docs/readme/talk-words.webp" width="49%" alt="The Words panel: the transcript of the video as a list, with a search box."> </p> <p align="center"><sub>The answer tells you what was cut, and why. The Words panel shows what is left, and lets you cut more by reading.</sub></p> <img src="docs/readme/talk-timeline.webp" width="100%" alt="The timeline after the edit: ten clips, each tagged AI, and a label showing 28.6 seconds were removed."> <p align="center"><sub>Every cut is marked on the timeline. Drag any edge to change it, or go back to the version before with one click.</sub></p> <br>

2 ยท Cut a two-camera podcast

For podcasts, interviews and panels.

Add the files from every camera. FrameFlow notices they are one recording and lines them up by their sound.

<p align="center"> <img src="docs/readme/podcast-suggestion.webp" width="40%" alt="A card in the media panel: 3 files look like one recording. They were recording at the same time. A button reads Sync as multicam."> </p>

Then every angle sits under the picture. Ask for the cut, or press 1, 2, 3 to switch cameras yourself while it plays.

Cut between the cameras so we always see whoever is speaking.

<img src="docs/readme/podcast-editor.webp" width="100%" alt="The editor with a podcast open. Three camera angles sit under the main picture. The timeline shows twelve shots switching between the cameras above one unbroken sound track."> <br>

3 ยท Add motion graphics

For explainers, tutorials and channel branding.

Not just a name tag over a video. A motion layer in FrameFlow is a small page drawn frame by frame, so it can be a whole animated scene: a board that fills up, a chart that grows, a map, a character.

<img src="docs/readme/week-board.webp" width="100%" alt="An animation over a shot of a creator at his desk. Twelve idea labels pop in and connect, three turn amber and fly along curved trails to Monday, Wednesday and Friday on a week rail, where they become video cards, while a ring counts up to sixty minutes."> <p align="center"><sub>One motion layer, exported from FrameFlow. Twelve ideas pop in, three are picked and fly to their days, and a ring counts the hour.</sub></p>

Start from a template (name tags, chapter cards, quotes, counters, callouts), write your own scene, or ask the assistant to make one. Then change it without touching code: every scene shows its own words, colours and timing.

<img src="docs/readme/motion-scene.webp" width="100%" alt="The editor in Pro mode with the animated scene selected. On the left, its settings: the list of ideas, which ones are picked, an accent colour, and a bar of named moments with their lengths. On the right, the finished week board on the picture."> <p align="center"><sub>These tools live in <b>Pro</b> mode. FrameFlow checks every scene before it draws it, so the export matches the preview frame for frame.</sub></p> <br>

4 ยท Make the thumbnail

For anyone who posts the video afterwards.

Press Thumbnail. FrameFlow picks frames from your video, writes a first request from its title and what is said in it, and makes a cover image. Every version stays on a board, so you can compare them and continue from the one that worked.

<img src="docs/readme/thumbnail-graph.webp" width="100%" alt="A board with three connected boxes: three frames taken from the video, the request for a YouTube thumbnail, and the result, a thumbnail with the headline A week of videos in 1 hour."> <br>

How it works

  1. Add your footage. Files from your computer, or a link from YouTube or Google Drive.
  2. Say what you want. Or cut by hand. The assistant and your mouse work on the same timeline.
  3. Export. MP4 for posting, or ProRes to hand to another editor.
<img src="docs/readme/home.webp" width="100%" alt="The FrameFlow home screen asks What are you making? Two choices: Images, which opens the image board, and Video, which opens the timeline editor. Recent projects are listed under each."> <br>

All features

FrameFlow has two workspaces. Video opens the timeline editor; Images opens the image board.

Video

<table> <tr><th width="24%" align="left">Area</th><th width="76%" align="left">What you can do</th></tr> <tr><td valign="top"><b>Assistant</b></td><td>Ask for an edit in plain words. Choose Claude Code or Gemini to do it. Point it at a selection or the whole timeline, and attach a frame from the video to show what you mean.</td></tr> <tr><td valign="top"><b>Import</b></td><td>Files, whole folders, or a link from YouTube or Google Drive. Footage is split into scenes and transcribed for you.</td></tr> <tr><td valign="top"><b>Timeline</b></td><td>Several video and audio tracks. Split, trim, ripple delete, close gaps, duplicate, copy and paste, snapping, markers and chapters, undo and redo. A silence finder for long pauses.</td></tr> <tr><td valign="top"><b>Words</b></td><td>The transcript as a list. Search what was said, cut a word, or cut every match at once.</td></tr> <tr><td valign="top"><b>Captions</b></td><td>Made from the transcript and burned into the export.</td></tr> <tr><td valign="top"><b>Multicam</b></td><td>Sync cameras by sound. See every angle live and cut with the number keys. Pick the best microphone. Find who speaks when.</td></tr> <tr><td valign="top"><b>Motion graphics</b> <sub>Pro</sub></td><td>Eight templates and your own HTML scenes, checked before they are drawn. Named moments you drag to retime. Keyframes and motion paths.</td></tr> <tr><td valign="top"><b>Titles and backgrounds</b></td><td>Plain titles in both modes. Generated backgrounds (solid, gradient, noise, bars) in Pro.</td></tr> <tr><td valign="top"><b>Transitions</b> <sub>Pro</sub></td><td>58 transitions, dropped on a cut.</td></tr> <tr><td valign="top"><b>Effects</b> <sub>Pro</sub></td><td>Exposure, contrast, saturation, gamma, warmth and hue. Eight looks, plus packs of your own. Sharpen, vibrance and blur.</td></tr> <tr><td valign="top"><b>Picture</b></td><td>Move, scale and rotate on the picture itself. Picture-in-picture on a second track. Green-screen keying. Landscape, vertical or square frames, up to 4K. Change speed and keep the pitch.</td></tr> <tr><td valign="top"><b>Sound</b></td><td>Waveforms, clip level and fades. Tracks know if they are voice, music or effects, and music ducks under speech. Loudness is set on export. Repair: denoise, remove rumble, even out level, compress.</td></tr> <tr><td valign="top"><b>Sound design</b> <sub>Pro</sub></td><td>17 built-in sounds, and one button that adds a sound to each title. With an ElevenLabs key: generated voice, music and effects.</td></tr> <tr><td valign="top"><b>Tracking</b></td><td>Ask the assistant to follow a face or an object, and keep an emoji, a blob or a box on it.</td></tr> <tr><td valign="top"><b>Versions</b></td><td>Every AI turn is saved as a version. See them as a list or a graph, go back, branch, or save a checkpoint of your own.</td></tr> <tr><td valign="top"><b>Monitor</b></td><td>Safe-area guides, an exact-frame view that matches the export, fullscreen, and the cost of the project's AI use.</td></tr> <tr><td valign="top"><b>Export</b></td><td>MP4 (H.264 or H.265) or ProRes 422 HQ, at the project's size or as a fast preview. Every export is listed in the project.</td></tr> <tr><td valign="top"><b>Light and Pro</b></td><td>Light keeps the essentials. Pro adds the rows marked <sub>Pro</sub>. Switch in the top bar.</td></tr> </table>

Images

<table> <tr><th width="24%" align="left">Area</th><th width="76%" align="left">What you can do</th></tr> <tr><td valign="top"><b>Start</b></td><td>A request in plain words, your own images, or a reference video.</td></tr> <tr><td valign="top"><b>Board</b></td><td>Every request and every result is a box on a board. Branch from any box, delete a branch, and group boxes into named frames.</td></tr> <tr><td valign="top"><b>Variations</b></td><td>Ask for several samples at once and compare them side by side.</td></tr> <tr><td valign="top"><b>References</b></td><td>A result keeps the frames it was built from. Reuse them, or refine a result using all of them.</td></tr> <tr><td valign="top"><b>Improvise</b></td><td>Let the AI rewrite your request into a fuller, more detailed one.</td></tr> <tr><td valign="top"><b>Upscale</b></td><td>Enlarge a result ร—2 or ร—4.</td></tr> <tr><td valign="top"><b>Thumbnail from a video</b></td><td>One button in the editor picks frames from your video, drafts the request and opens the board.</td></tr> <tr><td valign="top"><b>Models</b></td><td>Choose the model for each job: understanding, generating, upscaling.</td></tr> <tr><td valign="top"><b>Save</b></td><td>View a result full screen and save it as a file. The cost of the project's AI use is shown.</td></tr> </table> <br>

Bring your own AI agent

Already use Claude Code or Codex? Turn on Agent access and it can work on the project you have open, with the same tools as the built-in assistant. Each change it makes is saved as a version you can undo.

<p align="center"> <img src="docs/readme/more-agent.webp" width="80%" alt="The Agent access settings: a switch to let an agent in your terminal read and edit the open project, an address on this computer, an access token, and the command that connects Claude Code."> </p> <p align="center"><sub>Off until you switch it on. It listens on this computer only and needs the token shown here.</sub></p> <br>

Get FrameFlow

Installers are on the Releases page.

| Platform | File | | :--- | :--- | | macOS (Apple Silicon) | .dmg, signed and notarised | | Windows (x64) | .exe, not signed yet, so SmartScreen will warn | | Linux (x64) | .AppImage or .deb |

What you need

  • A Google Gemini API key. FrameFlow asks for it on first launch and uses it for transcripts, scene descriptions and images. You get one at Google AI Studio.
  • Optional: Claude Code, if you want it to do the editing. It runs on your own Claude plan.
  • Optional: an ElevenLabs

Truncated for display โ€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars44
CategoryDevelopment
Updated3d ago
Forks5

Languages

TypeScript

Trust signals

85/100

From repository metadata: license, adoption, age and documentation. Not a code audit โ€” see the Safety scan above for what the skill file itself contains.

1 medium1 info
frameflow โ€” MCP Server: Install & Safety Check | SkillAgent