Skip to content
Skillpedia
Video editing280k · #291

taste-application

Helps your agent create videos in a specific style. It can copy the editing rhythm from a reference video, generate new scenes, adjust colors, and edit everything together with other footage.

What it does

This tool creates new videos based on a style you already have. It uses the editing rhythm of a reference video, generates new scenes, adjusts colors, and edits everything together with other videos you might have.

When to use it

  • ✓When you want to make a video in a specific style.
  • ✓To add new scenes to an existing video.
  • ✓To create 3D objects and insert them into your video.

Example of what to ask your AI

“Create a video in the style of this example, using my footage and adding some 3D objects.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/affaan-m/ECC/blob/main/skills/taste-application/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/affaan-m/ECC/blob/main/skills/taste-application/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

The tool analyzes an example video to understand its style and rhythm. Then, it generates new scenes, applies colors, and edits everything together, mixing it with your own videos and 3D objects.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add affaan-m/ECC --skill taste-application

Or download just the file:

curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/taste-application/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Taste Application

The second half of the pipeline. taste-distillation measures references into a style pack; this generates against that pack and cuts the result.

Execution and Delivery Contract

The original implementation ships here in scripts/; no separate ito-video checkout is required. Install scripts/requirements.txt for local processing. Install scripts/requirements-live.txt only for provider execution. Live uploads, submissions and downloads require explicit TASTE_FORGE_ALLOW_LIVE=1 in addition to credentials; set it only for the user's authorized run. --dry-run remains credential-free and produces labelled placeholders. An ambiguous provider timeout is not retried as a new paid job. Inspect the provider request before deciding whether another submission is warranted.

Use existing completed takes without any provider calls:

python scripts/pipeline.py --genre example --root stylepacks \
  --takes media/take-a.mp4 media/take-b.mp4 --duration 12 --fps 30 \
  --out out/review-v1.mp4

--duration is a best-effort cadence target, not an exact runtime. Complete shots may produce a shorter or longer edit; the assembler does not duplicate clips or add padding to meet the target. The output manifest retains actual duration and adds duration_contract with requested and actual seconds, shortfall, overrun, and the cadence_target policy. Differences of at least one output frame are warned explicitly. No exact-duration mode is provided; when an exact runtime is required, inspect the receipt and revise or reject the cut before delivery.

The pipeline keeps each run's graded shot files because the editable FCPXML and EDL reference them. It refuses output collisions and reports timeline export failures. A completed render is not a saved editor project or creative approval. Preserve source assets and versioned project checkpoints before and after live edits; record the saved path and digest separately from the in-memory timeline receipt.

Clone-ready Fal graphs and their offline input compiler are documented in workflows/README.md. Compile brief and style direction before submission; do not assume a disconnected schema field affects a model prompt. Validate current endpoint fields against the actual provider before a paid run.

For Blender, use the full textured source GLB; retopology is a separately named derivative and never replaces that source. blender_prop.py supports explicit --width 1920 --height 1080 --fps 30 --receipt receipt.json and preserves pack-derived rim lighting and material textures. Saving a scene is distinct from rendering it; inspect the receipt's state and packed images.

For Resolve overlays, use taste.resolve.apply_placements with injected objects from an explicitly selected, versioned target. Set source_end_mode to the convention verified on that host. Do not assume an inclusive source end across Resolve versions. The adapter allocates overlapping effects above preserved tracks and checks every placement immediately and again after all appends. Composite integers must match the installed API; for the verified Studio 21 host, Screen is 5, not the historical builder's incorrect 22. The receipt proves in-memory placement only. Save the project, verify its checkpoint, then inspect the exact rendered output before reporting delivery.

When to Activate

  • "make a video in this style" / "apply the pack" / "supplement this footage"
  • Assembling generated clips into something with real edit rhythm
  • Minting 3D props from a look and getting them back into the video
  • Verifying that a finished piece actually matches its reference

Division of Labour

The model supplies content, motion, framing and lighting structure. The pack supplies colour and rhythm. This is measured, not stylistic preference — see taste-distillation for the numbers. Practical consequences:

  • The generation prompt contains zero colour language. Add "Colour: none. Render neutral. Grading is applied afterwards."
  • Keep two separate flags: --brief (what HAPPENS: subject, action, place) and --style-steer (how it LOOKS). Merging them leaks style words into the scene ("teal" becomes a teal object) and subject words into the grade.
  • The model responds to local, checkable rules far better than global ones. "Backgrounds pure black and unlit; subjects blowing toward white" works; "extreme contrast" does not.

Generate TAKES, Not Shots

…

FAQ

What is a 'style pack'?

It's a set of information describing a specific visual style, like colors and editing rhythm, measured from a reference video.

Can I control the exact video duration?

The tool aims for a target duration, but the final result might be slightly shorter or longer. There's no option to guarantee the exact runtime.

What happens if I use existing footage?

The tool can use your existing footage and edit it alongside the generated material, respecting the original cuts of your videos.

Details

Original description by the author

Generate new video against a distilled style pack and cut it into a finished piece - plan takes from the reference's cut rhythm, generate on fal, grade with the pack's measured LUT, cut at the measured cadence, weave in existing footage, composite overlay plates, mint 3D props, and verify the result numerically. Use when the user wants to make a video in a captured style, supplement existing foota

repo: affaan-m/ECC

Popularity

GitHub stars
280k
Ranking position
#291
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills