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.
Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow.
Install Color Grading
$ npx skills add notivn/AIEV --skill color-grading -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install notivn/AIEV color-grading --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/color-grading .claude/skills/color-grading && rm -rf skills-srcUse ~/.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/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .claude/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/notivn/AIEV/tree/main/.claude/skills/color-gradingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add notivn/AIEV --skill color-grading -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install notivn/AIEV color-grading --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/color-grading .agents/skills/color-grading && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .agents/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add notivn/AIEV --skill color-grading -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install notivn/AIEV color-grading --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/color-grading .cursor/skills/color-grading && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .cursor/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/notivn/AIEV.git --path .claude/skills/color-grading--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add notivn/AIEV --skill color-grading -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install notivn/AIEV color-grading --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/color-grading .gemini/skills/color-grading && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .gemini/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install notivn/AIEV color-gradingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add notivn/AIEV --skill color-grading -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/color-grading .github/skills/color-grading && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .github/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add notivn/AIEV --skill color-grading -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install notivn/AIEV color-grading --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/color-grading .opencode/skills/color-grading && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "color-grading" agent skill from https://github.com/notivn/AIEV/tree/main/.claude/skills/color-grading into .opencode/skills/color-grading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "color-grading", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
color-grading- GitHub stars
- 126
- Token cost
- ~932 tokens
- SKILL.md length
- 431 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow.
- Works in 5 steps: Probe the color (command above) ->… → Produce the graded version (high quality… → Visual verification (mandatory): extract… → …
- Asks for grading/delog
- SKILL.md covers Rule #1: the preview IS the…, Source of truth for presets +…, Delog / HDR tonemap (insert… and Workflow for grading one video, plus 1 more section
- Calls ffprobe and ffmpeg
What it does
Color Grading is an agent skill from notivn/AIEV. Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow. Read when the edit prompt has a "Chỉnh màu" (color grading) section, when the source footage is HDR/log, or when the user asks for grading/delog.
Its SKILL.md is about 930 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 and Motion graphics. It works with FFmpeg. The repository describes itself as: Automatic AI video editing. Claude directs HyperFrames (HTML + GSAP motion graphics) and Remotion (timeline assembly) to turn raw footage into a finished MP4 - transcript… The licence is MIT.
When your agent uses it
- Asks for grading/delog
- Tasks that involve Video production
- Tasks that involve Motion graphics
Example prompts
- “Chỉnh màu”
- “/color-grading”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Probe the color (command above) -> decide whether a tonemap is needed.
- Produce the graded version (high quality encode, audio untouched)
- Visual verification (mandatory): extract 3 frames (start / middle / end) of the graded version and LOOK at each one
- Use the .graded.mp4 version throughout the ENTIRE pipeline instead of the original (meta.json srcVideo; transcription
- Record in the asset description (assets.json) which preset was used to grade it, so it does not get graded twice later.
What it can do on your machine
Read from SKILL.md and the folder at commit 1a4c2b0. 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:
ffprobeffmpeg
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Color Grading loads about 932 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 431 words of instructions outside code blocks.
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 notivn/AIEV at commit 1a4c2b0, republished under its MIT licence (© notivn). 431 words, ~932 tokens.
Download SKILL.mdSave it as
.claude/skills/color-grading/SKILL.md (or your agent's skills folder).- name
- color-grading
- description
- Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow. Read when the edit prompt has a "Chỉnh màu" (color grading) section, when the source footage is HDR/log, or when the user asks for grading/delog.
Color Grading - grading video footage
Rule #1: the preview IS the final result
The user already APPROVED the color in the web UI based on a preview generated from the canonical filter chains in
apps/server/src/color.ts (GRADE_PRESETS). When applying it to the real video you MUST use that exact filter chain
- do not invent your own, do not "improve it further". A different chain = a color that no longer matches what the user picked.
Source of truth for presets + manual adjustments
Read apps/server/src/color.ts:
GRADE_PRESETS- 14 color templates (tu-nhien, tuoi-sang, vivid, cinematic, teal-orange, film-vintage, mau-phim, golden-hour, am, lanh, dem-xanh, moody, pastel, den-trang) with their -vf chains.GradeAdjust- the user's manual tweaks stacked ON TOP of the preset (brightness/contrast/ saturation/gamma viaeq,colortemperature,vibrance); thebuildFilterChain(preset, tonemap, adjust)function assembles them in the correct order: tonemap -> preset -> manual adjustments.- The edit prompt already prints the complete -vf chain for each asset - JUST USE IT VERBATIM.
Delog / HDR tonemap (insert BEFORE the preset)
Inspect the footage with ffprobe:
ffprobe -v error -select_streams v:0 -show_entries stream=color_transfer,color_primaries -of csv=p=0 input.mp4If color_transfer is arib-std-b67 (HLG - iPhone/Android HDR capture) or smpte2084 (HDR10),
or color_primaries is bt2020 -> insert the tonemap BEFORE the preset:
zscale=t=linear:npl=100,tonemap=hable:desat=0,zscale=p=bt709:t=bt709:m=bt709:r=tv,format=yuv420pProfessional camera log (S-Log3, D-Log, V-Log...) whose metadata does not declare HDR needs the vendor's .cube LUT -
if that LUT is not in the system, tell the user instead of guessing.
Show full SKILL.md (215 more words)Show less
Workflow for grading one video
- Probe the color (command above) -> decide whether a tonemap is needed.
- Produce the graded version (high quality encode, audio untouched):
ffmpeg -y -i assets/source.mp4 -vf "<tonemap-if-needed>,<preset-chain>" -c:v libx264 -crf 16 -preset medium -c:a copy assets/source.graded.mp4- Visual verification (mandatory): extract 3 frames (start / middle / end) of the graded version and LOOK at each one: are skin tones natural and not blown out orange? are highlights not clipped? are blacks not crushed? If something is wrong -> report back, do NOT silently change the filter (the user locked in the preset).
- Use the
.graded.mp4version throughout the ENTIRE pipeline instead of the original (meta.json srcVideo; transcription can use either file since the audio is copied unchanged). - Record in the asset description (assets.json) which preset was used to grade it, so it does not get graded twice later.
Known issues
- Grading twice: the
.graded.mp4gets the preset applied again in a later session -> harsh color. ALWAYS check the filename and assets.json before grading. - Grading only the main video and forgetting b-roll/inserted images: inserted images usually do not need grading (they are graphics), but b-roll shot on the same camera needs the same preset - check the asset descriptions to know which files came from the camera.
- Missing
format=yuv420pat the end of the tonemap chain -> the output is 10-bit and HyperFrames/browsers may not play it.
© notivn, MIT. 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 .claude/skills/color-grading of notivn/AIEV.
Open the folder on GitHubat commit 1a4c2b0
Compare with similar skills
Color Grading 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Color Grading this skillnotivn/AIEV | 126 | — | ~932 | Automated safety check: Pass | MIT | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 59k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Cut Silencesnateherkai/hyperframes-student-kit | 1.2k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Anime Cel Video Makeredenfunf/reelmimic | 1.8k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Paper Cut-out Animationedenfunf/reelmimic | 1.8k | — | ~1.5k | Automated safety check: Pass | MIT | |
| p5 Paint Animationheygen-com/hyperframes-community-skills | 183 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Cut Silences
nateherkai/hyperframes-student-kit
Agent 1 of the video editing pipeline. An agent skill from nateherkai/hyperframes-student-kit.
Anime Cel Video Maker
edenfunf/reelmimic
Builds Japanese TV-anime style MP4 videos in code, with cel-shaded characters, painted backgrounds and staging effects, rendered in headless Chrome and encoded with ffmpeg.
Paper Cut-out Animation
edenfunf/reelmimic
Builds paper cut-out, stop-motion style MP4 videos in code, with jointed paper puppets, torn or scissor-cut edges and soft shadows, rendered frame by frame in headless Chrome.
p5 Paint Animation
heygen-com/hyperframes-community-skills
Turns a text prompt, photo or short video into hand-made looking p5.js animation: self-writing handwriting, brushstroke repaints and living paintings rendered offline.
Pixel Art Video Engine
edenfunf/reelmimic
Makes animated pixel-art videos in an indie-game style: a 480×270 canvas upscaled four times, limited palettes with dithering, procedural characters and dialogue captions, encoded as MP4.
More from notivn/AIEV
All 14 skills in this repoBackground Music
notivn/AIEV
Pick background music from the assets/music/ library and configure auto-ducking (music dips automatically under speech) via meta.json audio.music for the Remotion assembly layer.
Noti Tiktok Full Text
notivn/AIEV
Build a Vietnamese vertical TikTok explainer in the "MỔ XẺ PAPER AI" (AI paper dissection) format with HyperFrames (HTML/CSS/GSAP → MP4), Noti.vn style.
Skill Authoring
notivn/AIEV
The standard for writing new skills for the AI Edit Video system - file structure, frontmatter, tone of voice, and how to accumulate production lessons into skills.
Noti Tiktok Vn
notivn/AIEV
Edit a Vietnamese vertical TikTok video (9:16) with HyperFrames following the Noti.vn/GĐT standard - talking-head + kinetic typography + karaoke captions + zoom/punch-in camera + timestamp-synced…
Noti Youtube Edit
notivn/AIEV
Build a Vietnamese landscape 16:9 YouTube video (1920×1080) with HyperFrames (HTML/CSS/GSAP → MP4), keeping the Noti.vn/GĐT branding inherited from noti-tiktok-vn.
Short Form Video
notivn/AIEV
Build and iterate short-form vertical (9:16) videos in Hyperframes - TikTok/Reels/Shorts style.
Related
Works with
Categories
Questions about Color Grading
What does Color Grading do?
Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow. Color Grading is an agent skill from notivn/AIEV. Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow.
When should I use Color Grading?
Color Grading fits situations like: asks for grading/delog; tasks that involve Video production; tasks that involve Motion graphics.
How do I install Color Grading in Claude Code?
Run `npx skills add notivn/AIEV --skill color-grading -a claude-code`. Or copy the skill folder (.claude/skills/color-grading in notivn/AIEV) into .claude/skills/color-grading in your project. Claude Code loads it when a task matches its description.
How do I install Color Grading in Codex?
Run `npx skills add notivn/AIEV --skill color-grading -a codex`. Or copy the skill folder (.claude/skills/color-grading in notivn/AIEV) into .agents/skills/color-grading in your project. Codex loads it when a task matches its description.
Can I use Color Grading 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 notivn/AIEV --skill color-grading -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/color-grading, .gemini/skills/color-grading, .github/skills/color-grading and .opencode/skills/color-grading in your project.
What does Color Grading need to run?
Going by SKILL.md and its folder, Color Grading needs the command-line tools its instructions call (ffprobe and ffmpeg).
Does Color Grading 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 Color Grading 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 Color Grading use?
Color Grading is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Color Grading use?
About 932 tokens (SKILL.md is roughly 3.7k 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 Color Grading?
Skills that share tags, products or a category with Color Grading: HyperFrames Video Entry Point (heygen-com/hyperframes, 59k stars), Cut Silences (nateherkai/hyperframes-student-kit, 1.2k stars), Anime Cel Video Maker (edenfunf/reelmimic, 1.8k stars) and Paper Cut-out Animation (edenfunf/reelmimic, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Color Grading?
notivn (a GitHub organization) maintains it in notivn/AIEV, which has 126 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.
Source: notivn/AIEV on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.