take-one
take-one is a skill in talsiach/take-one, last changed 28 Oct 2026. It can change agent settings, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing.
Turn a short request into a finished short film rendered from code, working like a studio team of twelve jobs (strategist, creative director, writer, voice director, art director, storyboard artist, cinematographer, composer, sound designer, editor, reviewer, social copywriter). For launch and product videos, explainers, music videos, brand and story films. It learns the brand from its site, pitches the best route first (code, real-looking pictures, moving shots from a video model) with prices, asks whether to run to a finished first take or work in stages, always asks before spending money, credits or heavy usage, has a fresh reviewer score the cut against a bar, and takes notes on frames in a local review room.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
Nothing flagged
That isn't proof the skill is harmless.
Commit 43fd27b · 20 Nov 2026
How the check worksPattern check: nothing flagged
That isn't proof the skill is harmless.
QAI Index
We rate every listed skill the same way, from 0 to 100.
A guide to compare by, not a verdict on the skill.
How it's scoredGet an email when its check changes.
Keep it with the other skills you use, installed with one command.
Install
Sign in to see how to install it
Free with Google or an email link, no password needed. Then pick your agent and copy its steps.
What it can touch
Sign in to see the file and line behind each one
The summary at the top stays open to everyone. Signing in is free, with Google or an email link.
Pattern check
Pattern check: nothing flagged · commit 43fd27b · 20 Nov 2026
We checked every text file in this skill, at commit 43fd27b on 20 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Files we didn't read
- assets/previews/ascii-a.jpg · image, audio or video
- assets/previews/ascii-b.jpg · image, audio or video
- assets/previews/chrome-a.jpg · image, audio or video
- assets/previews/chrome-b.jpg · image, audio or video
- assets/previews/crayon-a.jpg · image, audio or video
- assets/previews/crayon-b.jpg · image, audio or video
- assets/previews/dark-a.jpg · image, audio or video
- assets/previews/dark-b.jpg · image, audio or video
- assets/previews/explainer-a.jpg · image, audio or video
- assets/previews/explainer-b.jpg · image, audio or video
Show 32 more
- assets/previews/game-a.jpg · image, audio or video
- assets/previews/game-b.jpg · image, audio or video
- assets/previews/glow-a.jpg · image, audio or video
- assets/previews/glow-b.jpg · image, audio or video
- assets/previews/hud-a.jpg · image, audio or video
- assets/previews/hud-b.jpg · image, audio or video
- assets/previews/ink-a.jpg · image, audio or video
- assets/previews/ink-b.jpg · image, audio or video
- assets/previews/lyric-a.jpg · image, audio or video
- assets/previews/lyric-b.jpg · image, audio or video
- assets/previews/manifesto-a.jpg · image, audio or video
- assets/previews/manifesto-b.jpg · image, audio or video
- assets/previews/mono-a.jpg · image, audio or video
- assets/previews/mono-b.jpg · image, audio or video
- assets/previews/papercut-a.jpg · image, audio or video
- assets/previews/papercut-b.jpg · image, audio or video
- assets/previews/penciltest-a.jpg · image, audio or video
- assets/previews/penciltest-b.jpg · image, audio or video
- assets/previews/pixel-a.jpg · image, audio or video
- assets/previews/pixel-b.jpg · image, audio or video
- assets/previews/riso-a.jpg · image, audio or video
- assets/previews/riso-b.jpg · image, audio or video
- assets/previews/short-a.jpg · image, audio or video
- assets/previews/short-b.jpg · image, audio or video
- assets/previews/sketch-a.jpg · image, audio or video
- assets/previews/sketch-b.jpg · image, audio or video
- assets/previews/teach-a.jpg · image, audio or video
- assets/previews/teach-b.jpg · image, audio or video
- assets/previews/title-a.jpg · image, audio or video
- assets/previews/title-b.jpg · image, audio or video
- assets/previews/watercolor-a.jpg · image, audio or video
- assets/previews/watercolor-b.jpg · image, audio or video
Outside links we did not follow
- http://www.apache.org/licenses/
- http://www.apache.org/licenses/LICENSE-2.0
- https://commons.wikimedia.org/wiki/File:Vincent_van_Gogh_-_Almond_blossom_-_Google_Art_Project.jpg
- https://github.com/user-attachments/assets/f2e005dc-b6b0-4023-b3d7-9bd958643022
- https://github.com/talsiach/take-one
- http://www.w3.org/2000/svg
- https://fonts.googleapis.com
- https://fonts.gstatic.com
- https://fonts.googleapis.com/css2?family=Inter+Tight:wght@700;800;900&family=Instrument+Serif:ital@1&family=JetBrains+Mono:wght@400;500&display=swap
- https://fonts.googleapis.com/css2?family=Archivo+Black&family=Space+Mono:wght@400;700&family=Playfair+Display:ital,wght@1,500;1,600&display=swap
Show 40 more
- https://cdn.jsdelivr.net/npm/three@0.170.0/build/three.module.js
- https://fonts.googleapis.com/css2?family=Archivo+Black&family=Playfair+Display:ital,wght@1,700&family=JetBrains+Mono:wght@400;700&display=swap
- https://x.com/MilitantAI/status/2104809953282465952
- https://notes.apoorv.xyz/launch-videos
- https://github.com/howseen-ai/claude-motion-design
- https://x.com/kevin_t_ngo/status/2104638743634391408
- https://github.com/Tejashmakwana/motionmaxxing
- https://github.com/alexgreensh/anidoodle
- https://x.com/goatfishxyz/status/2104163769224204376
- https://x.com/elliotarledge/status/2104096029847277687
- https://x.com/Thom_Wolf/status/2103545533474206118
- https://x.com/eudaemonea/status/2102610626321490404
- https://x.com/mattshumer_/status/2103928105320763818
- https://x.com/_mexicat/status/2103108369569726802
- https://x.com/vikktorrrre/status/2103829638799618407
- https://x.com/anabology/status/2103534482930491441
- https://x.com/donaldjewkes/status/2102801274173587569
- https://github.com/JohnHeibel/PDoomVideo
- https://x.com/achxvi/status/2103918792845963545
- https://x.com/flxrnc/status/2105311836190978392
- https://x.com/flxrnc/status/2109629188525420930
- https://x.com/chetaslua/status/2109375245320847702
- https://x.com/blueemi99/status/2109633997638938935
- https://x.com/mr_salio/status/2109414908014018906
- https://whatships.com/
- https://x.com/cognition/status/2107165034463867001
- https://x.com/stevelauda_/status/2101855047412031533
- https://x.com/claudeai/status/2031088171262554195
- https://x.com/benjitaylor/status/2082515001949221152
- https://x.com/joshpuckett/status/2107175379903594714
- https://x.com/tomiwebstr/status/2092175528396493189
- https://x.com/OpenAI/status/2107894997538525580
- https://x.com/getondesign/status/2107333887026491811
- https://x.com/jans/status/2107476474399985729
- https://x.com/evilrabbit_/status/2105062376575992090
- https://x.com/Varcyyyy/status/2090184114083447165
- https://x.com/BhaskarVisuals/status/2092251902385807543
- https://x.com/tomkrcha/status/2026329359838318906
- https://x.com/vladmoroz/status/2107865714812162228
- https://x.com/agusegui/status/2108251509830140401
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The format our Agent Skills docs set out, held to the strictest version of each rule among the agents we check.
- Warning
The body is about 11,438 tokens (approx.); the spec suggests under 5,000. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
The first sentence of the description is 279 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
There is no license field, so readers can't tell whether they may reuse the skill. O2
Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Note
Reference files that SKILL.md doesn't link: THIRD_PARTY.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/audio.md (158 lines), references/directed-look.md (141 lines), references/music-engine.md (103 lines), references/pipeline.md (181 lines), references/toolbox.md (105 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Warning
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
The first sentence of the description is 279 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
The body is about 11,438 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Reference files that SKILL.md doesn't link: THIRD_PARTY.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/audio.md (158 lines), references/directed-look.md (141 lines), references/music-engine.md (103 lines), references/pipeline.md (181 lines), references/toolbox.md (105 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Note
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
The description is 722 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
The body is about 11,438 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Reference files that SKILL.md doesn't link: THIRD_PARTY.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/audio.md (158 lines), references/directed-look.md (141 lines), references/music-engine.md (103 lines), references/pipeline.md (181 lines), references/toolbox.md (105 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Note
OpenAI (Codex & API)Passes
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Note
The first sentence of the description is 279 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
- VS Code & CopilotPasses
SKILL.md
Files
182 files
Show 162 more
Changelog
Newest first: each commit that changed its folder on GitHub, and each change to its listing here.
- Listed on QAI
- Updated: Picture and video routes: check what the person has, Codex setup, Hig… (8e0fd8d (opens in a new tab))
- Updated: Character life: blinks, eyes that lead, limbs that settle (ce2d522 (opens in a new tab))
- Updated: Picture audit and a broken-value check (b81bdaf (opens in a new tab))
- Updated: Edge check: pictures, cards and labels cut by an edge (8196357 (opens in a new tab))
- Updated: Text check: two texts printed on top of each other (55dab94 (opens in a new tab))
- Updated: Runs without Python or bc, the Mac graphics setting only on a Mac, do… (4627d59 (opens in a new tab))
- Updated: The review room is named in the first reply and is a required part of… (865556d (opens in a new tab))
- Updated: Safer review pack, a rule for outside content, and a yes before a thi… (ab8ec52 (opens in a new tab))
- Updated: Take One: a Claude Code skill that makes a short film from one line (68c60d5 (opens in a new tab))
QAI Index badge
Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.
[](https://qai.io/skills/talsiach/take-one/take-one)Other Frontend & design skills
Same category, most repo stars first.