#281 by GitHub stars
openfilm/openfilm
The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
packages/openfilm/skills/collage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Local scripts
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/keynote/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/long-to-short/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/lyric-video/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/motion-graphics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/presenter-pip/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/replicate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/screen-demo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/vintage-film/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
packages/openfilm/skills/whiteboard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
skills/openfilm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b7673b585e3e → 623cec4297aa
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b7673b585e3e
No earlier version was observed for comparison.
Heat
8.6- Star growth, last 7 daysAhead of 100% of tracked repositories
- Star growth, last 24 hoursAhead of 100% of tracked repositories
- Rank movement, last 7 daysAhead of 98% of tracked repositories
- Commits, last 30 daysAhead of 97% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- collage
packages/openfilm/skills/collage - keynote
packages/openfilm/skills/keynote - long-to-short
packages/openfilm/skills/long-to-short - lyric-video
packages/openfilm/skills/lyric-video - motion-graphics
packages/openfilm/skills/motion-graphics - presenter-pip
packages/openfilm/skills/presenter-pip - replicate
packages/openfilm/skills/replicate - screen-demo
packages/openfilm/skills/screen-demo - vintage-film
packages/openfilm/skills/vintage-film - whiteboard
packages/openfilm/skills/whiteboard - openfilm
skills/openfilm
How it works
collage
When your agent uses it
Make motion graphics in a cut-paper collage style, with photos, paper and print cut out and put together by hand. Use for explainers, promos, stories, intros and social posts, or when the person asks for a collage, cut-paper, scrapbook, zine or mixed-media look (剪贴风, 拼贴, 手账风, 杂志拼贴).
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
515 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,207 bytesSKILL.mdcore2,207 bytescover.jpgasset306,307 bytesopenfilm.jsonasset2,285 bytes
Read SKILL.md
# Collage
Make a collage film an art director would sign: pictures cut from real material and put together by hand, so that what
they make together says what none of them says alone. Surprise us; the expected version is not the goal.
## What has to be true
- **Every piece says something.** Each picture, word and scrap is there for what it means in this film, not to fill
space. If the same pieces could tell another story, it is not done yet.
- **Every picture's source is clear**: the person's own, licensed, public domain, or made for this film. A made one is
never passed off as a real person, place or record.
- **People as they are**: their photos are cut, cropped, colored and printed, never their faces changed.
- **Words spelled right**, and readable, in the titles, labels and clippings.
- **It holds up next to the best collage work you know.** Watch the whole film as a viewer would, and keep refiningView the complete source on GitHubkeynote
When your agent uses it
Make a product film in the style of a big tech launch keynote: the real product on stage, one confident claim at a time. Use for app, website, software and gadget launches, feature announcements and product intros, or when the person asks for a keynote, launch event, premium or minimal tech style (发布会, 产品发布, 新品, 高级感).
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
538 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,330 bytescover.jpgasset48,056 bytesopenfilm.jsonasset2,668 bytes
Read SKILL.md
# Keynote
Make the launch film this product deserves: the real product on stage, each moment making one claim and showing the
proof, so the viewer leaves knowing what it is and wanting it. Surprise us; the expected version is not the goal.
## What has to be true
- **The real product.** Its own screens, words, name and logo, from the person or captured from the live product; never
a redrawn interface. Where a screen must be simpler, crop and zoom into the real one.
- **Every claim true.** What is shown has shipped, or is said to be coming; numbers, comparisons, customers, prices and
dates come from the person or the product's own pages, never made up. A demo sped up or put together says so.
- **One claim at a time**, with its proof on screen, readable at the size it will be watched.
- **It holds up next to the best launch films you know.** Watch the whole film as a viewer would, and keep refining
until it does. If it could launch another product, it is not done yet.View the complete source on GitHublong-to-short
When your agent uses it
Turn a long video (a talk, podcast, interview, lesson, livestream or vlog) into short vertical clips that each stand alone and hold attention from the first second. Use when the person gives a long recording and asks for clips, shorts, highlights or cut-downs for Douyin, Reels, Shorts or similar (长视频转短视频, 切片, 剪短视频, 高光, 拆条).
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
602 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,505 bytescover.jpgasset166,749 bytesopenfilm.jsonasset2,744 bytes
Read SKILL.md
# Long video to shorts
Find the moments in this recording that people would stop scrolling for, and make each one a short a channel would post
as it is: it opens on its strongest real line, ends on its point, and makes sense to someone who never saw the long
video. The speaker, watching it, would say: yes, that is what I meant.
## What has to be true
- **The speaker's meaning, intact.** Nothing said in different places is joined into a claim they did not make; an
"if", a "not" or an "in some cases" is never cut away; an answer keeps its question. A title or any other text on
screen says only what the recording says, or is plainly yours.
- **It stands alone**: a viewer knows who is speaking and what they are answering.
- **Every word exact.** The transcript says exactly what was said; names, numbers and terms you cannot confirm are named
in your reply. Each cut falls in a pause: no clip starts on a clipped word or stops mid-thought.View the complete source on GitHublyric-video
When your agent uses it
Make a lyric video for a song that the artist would release as the official one — a piece made for this one song, every word landing exactly on the voice. Use when the person gives a song (with its lyrics or an .lrc file) and asks for a lyric video, a music video with words, karaoke-style lyrics or a song post (歌词视频, 动态歌词, 歌词 MV, 卡拉OK).
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
591 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,523 bytescover.jpgasset177,234 bytesopenfilm.jsonasset2,264 bytes
Read SKILL.md
# Lyric video
You are the director this song has been waiting for. Make its lyric video: the one the artist releases as the official
video, that people play again and send to friends because of how it makes the song feel. It belongs to this song and
no other. Surprise us; the expected version is not the goal.
In a lyric video the sung words are the heart of the picture: they live in the image and move with the voice. Lyrics
shown as subtitles are not a lyric video.
## What has to be true
- **The words live on the voice.** Each word arrives the moment it is sung, within two frames. Measure it against the
audio, check it independently of whatever made the times, and report honestly, in numbers, how close it is.
- **The lyrics are the person's**, word for word and line for line, in their language.View the complete source on GitHubmotion-graphics
When your agent uses it
Make premium motion graphics (an explainer, a promo, a title sequence or a data story) designed and animated at the level of a top studio, for this subject alone. Use when the person asks for motion graphics, an MG animation, an animated explainer, a promo or an intro that should look high end (高级 MG, 动效, 动画视频, 片头, 宣传动画).
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
537 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,290 bytescover.jpgasset84,950 bytesopenfilm.jsonasset2,565 bytes
Read SKILL.md
# Motion graphics
Make the piece a top motion studio would put in its reel: an idea for this subject, designed and moved with intent,
that makes people understand it or want it. Surprise us; the expected version is not the goal.
## What has to be true
- **It belongs to this subject.** The idea, the pictures and the motion come from what it is about; nothing in it could
be moved into another company's film.
- **The person's facts and brand.** Every number, name, quote and claim as they gave it, none made up; a chart's shapes
match its values, with units and where the data comes from; when there is a voice, the picture shows what it says as
it says it. Their logo, colors and type are used as given, never redrawn.
- **It holds up next to the best motion work you know.** Watch the whole film as a viewer would, and keep refining until
it does.View the complete source on GitHubpresenter-pip
When your agent uses it
Make a talking-head video where the content fills the screen and the presenter speaks from a small window: slides, screens, charts and pictures that follow what they say, their face always there. Use when the person gives a recording of themselves talking (with slides, a screen, data or notes) and asks for a lesson, a knowledge video, a business review, a commentary or a presentation with them in a corner (小窗人物口播, 画中画, 口播, 讲解视频).
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
554 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,408 bytescover.jpgasset89,897 bytesopenfilm.jsonasset2,582 bytes
Read SKILL.md
# Presenter in a window
Make the video that keeps the person present and puts what they talk about in charge: each thing they mention fills
the screen the moment they say it, and they speak from a window that never gets in its way.
## What has to be true
- **The picture follows their words.** Each slide, screen, chart, number or picture arrives as they say it and leaves
when they move on. Check it in the frames against the transcript's word times, and say how close it is.
- **The window never covers what matters**: the content, the subtitles, or a phone app's buttons; their face is never
cut badly.
- **Their words and meaning.** Cuts fall in pauses; ums and false starts go only when they ask; nothing appears that they
did not say or give. A number on screen is the one they say, from their data or its source.
- **It holds up next to the best explainers you know.** Watch the whole film as a viewer would, and keep refining untilView the complete source on GitHubreplicate
When your agent uses it
Remake a reference video in OpenFilm, as close as the person wants it, from frame for frame to its structure, rhythm, look and motion carrying their own content. Use when the person gives a video, as a file or a link, and asks for an exact copy of it, one like it, its style or pacing, or a remake for their product or topic (复刻, 照着做, 做个同款, 一模一样, 仿这个视频).
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
710 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,920 bytescover.jpgasset96,264 bytesopenfilm.jsonasset2,387 bytes
Read SKILL.md
# Replicate a video
Remake a video the person admires, as close as they want it: the same film frame for frame, or its form (the parts,
the rhythm, the look, the way things move) carrying their own content. When their words do not say which, ask. Either
way it is made again in OpenFilm, so every part of it can be changed.
## What has to be true
- **The same moments.** Where the reference cuts, a word appears, something moves or a sound hits, the film does too,
scaled when the lengths differ; for an exact copy, each frame matches the reference's frame at the same time. Compare
the two at the same times with `npx openfilm look`, and report honestly, in numbers, how close it is.
- **Made again.** The reference stays in `references/` and is never a clip of the film: what the film shows is made
anew, and the reference's own music, footage or voice go in only when the person asks for them.
- **Their version is theirs**: when they want their own content, every part carries their topic, product, words andView the complete source on GitHubscreen-demo
When your agent uses it
Turn a screen recording into a polished product demo or tutorial: the view follows the action, dead time is gone, every step is easy to see, and the product looks as good as it is. Use when the person gives a screen recording (or a product to capture) and asks for a demo, walkthrough, tutorial, feature video or how-to (录屏演示, 产品演示, 教程, 操作视频, 功能介绍).
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
528 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,206 bytescover.jpgasset93,261 bytesopenfilm.jsonasset2,800 bytes
Read SKILL.md
# Screen demo
Make the demo that shows this product at its best and is effortless to follow: the viewer always knows where to look,
sees each step land, never waits, and could do the same in the product today.
## What has to be true
- **The real product.** Its own screens, actions and results, from the person's recording or captured from the live
product; never a redrawn interface or a result that did not happen. Where it must be simpler, crop and zoom into the
real thing.
- **Clear where to look**, at the size it will be watched: the action, its text and its result readable on that
screen, a phone too when the demo is vertical.
- **Nothing private in any frame**: keys, tokens, passwords, emails, names, customer data, notifications, other tabs
and bookmarks are hidden, or that part is recorded again.View the complete source on GitHubvintage-film
When your agent uses it
Make the person's photos and clips into a memory film that looks shot on old film or kept as instant photos and prints. Use for memories and recaps (a trip, a birthday, a graduation, a wedding, a year, a child growing up) or when the person asks for a retro, film, analog, Polaroid or instant-photo look (复古, 胶片, 拍立得, 回忆, 相册, 年度回顾).
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
614 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,592 bytescover.jpgasset121,102 bytesopenfilm.jsonasset2,351 bytes
Read SKILL.md
# Vintage film
Make the memory film the people in these pictures will watch again and send to each other: their own photos and clips,
as if found on an old reel or in a box of prints. Surprise us; the expected version is not the goal.
The pictures are the film. The film look is how they were taken and printed, part of each picture rather than a filter
laid over it, and it never changes who or what is in them.
## What has to be true
- **The people and moments untouched.** Faces, bodies, who was there and what was behind them stay as they were: what a
darkroom could do (crop, scale, color, grain, light) and nothing more. No face restored, no picture extended, no
person made to move or smile, unless the person asks; then say it is generated.
- **Only true words.** Dates, places and names come from the person or the pictures' own metadata, never guessed; theView the complete source on GitHubwhiteboard
When your agent uses it
Make an explainer drawn on a board while a voice explains, every drawing and word drawn out as it is spoken. Use for lessons, micro-lectures, training, how-it-works and concept explainers, when the person turns a document, slides or notes into an explainer, or asks for a whiteboard, hand-drawn, sketch or doodle style (白板, 手绘, 讲解, 微课, 课件).
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
610 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What has to be true
- What you have
- With the person
Files
SKILL.mdcore2,562 bytescover.jpgasset83,611 bytesopenfilm.jsonasset2,499 bytes
Read SKILL.md
# Whiteboard explainer
Make the explainer a great teacher would draw: a voice explains and the board grows with it, so the viewer watches the
idea being built and remembers it.
The drawing is the explanation: each mark is drawn as the words that name it are spoken. A finished picture that fades
or slides in is not a whiteboard explainer.
## What has to be true
- **Drawn as it is said.** Each mark starts when the voice reaches it and is done before the next idea. Check it in the
frames against the voice's word times, and report how close it is.
- **True to the source.** Every fact, number, term and example as the person's document has it. What you add is your own
sentence, never a new fact; what you correct, you say.View the complete source on GitHubopenfilm
When your agent uses it
Make videos as web pages with OpenFilm. Use when the user asks for a video, motion graphics, an animation, a launch film, an explainer, a music video, to edit, cut, check or render a film (film.html and pages with window.film), or to open OpenFilm or its Studio.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
118 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore462 bytes
Read SKILL.md
# OpenFilm
Run `npx -y openfilm@latest` and follow the manual it prints: it is the whole of OpenFilm, about a thousand words. Run it
again whenever you need it.View the complete source on GitHubSkills included
- collage
- keynote
- long-to-short
- lyric-video
- motion-graphics
- presenter-pip
- replicate
- screen-demo
- vintage-film
- whiteboard
- openfilm
Repository facts
- License
- MIT
- Created
- Oct 4, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 472
- Open issues
- 13
- Project activity
- Active
Rank over the last 12 weeks
Now #281 · best #281 · up 639 in 30 days
- #304 on Nov 1
- #298 on Nov 2
- #293 on Nov 3
- #288 on Nov 4
- #283 on Nov 5
- #281 since Nov 6
21 earlier periods
- #920 on Oct 4
- #934 on Oct 10
- #939 on Oct 11
- #962 on Oct 12
- #965 on Oct 13
- #981 on Oct 14
- #965 on Oct 15
- #941 on Oct 16
- #772 on Oct 17
- #686 on Oct 18
- #590 on Oct 19
- #548 on Oct 20
- #509 on Oct 21
- #465 on Oct 22
- #446 on Oct 23
- #403 on Oct 24
- #415 on Oct 25
- #351 on Oct 28
- #335 on Oct 29
- #325 on Oct 30
- #314 on Oct 31
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
packages/openfilm/skills/collage/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 30 network referencesin 10 files: collage/openfilm.json:1 keynote/openfilm.json:1 long-to-short/openfilm.json:1 and 7 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 30 signals by file
packages/openfilm/skills/collage/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/collage", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/collage", "kind": "style", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/collage",
packages/openfilm/skills/keynote/openfilm.json
- Network accessline 1
{ "version": "0.1.1", "repository": "https://github.com/openfilm/skills/tree/main/skills/keynote", - Network accessline 2
"version": "0.1.1", "repository": "https://github.com/openfilm/skills/tree/main/skills/keynote", "kind": "style", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/keynote",
packages/openfilm/skills/long-to-short/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/long-to-short", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/long-to-short", "kind": "workflow", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/long-to-short",
packages/openfilm/skills/lyric-video/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/lyric-video", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/lyric-video", "kind": "style", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/lyric-video",
packages/openfilm/skills/motion-graphics/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/motion-graphics", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/motion-graphics", "kind": "workflow", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/motion-graphics",
packages/openfilm/skills/presenter-pip/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/presenter-pip", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/presenter-pip", "kind": "workflow", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/presenter-pip",
packages/openfilm/skills/replicate/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/replicate", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/replicate", "kind": "workflow", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/replicate",
packages/openfilm/skills/screen-demo/openfilm.json
- Network accessline 1
{ "version": "0.1.1", "repository": "https://github.com/openfilm/skills/tree/main/skills/screen-demo", - Network accessline 2
"version": "0.1.1", "repository": "https://github.com/openfilm/skills/tree/main/skills/screen-demo", "kind": "workflow", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/screen-demo",
packages/openfilm/skills/vintage-film/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/vintage-film", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/vintage-film", "kind": "style", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/vintage-film",
packages/openfilm/skills/whiteboard/openfilm.json
- Network accessline 1
{ "version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/whiteboard", - Network accessline 2
"version": "0.1.0", "repository": "https://github.com/openfilm/skills/tree/main/skills/whiteboard", "kind": "style", - Network accessline 3
"repository": "https://github.com/openfilm/skills/tree/main/skills/whiteboard",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md packages/openfilm/skills/collage/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/openfilm-openfilm/)