ranking-list — Claude Code skill: video editing and install
The ranking-list Claude Code skill turns a vertical talking-head clip into a tier-ranking reel. Items appear as they are named, then move into their tier when the speaker gives a verdict.
MIT ★ 94 updated 2026-10-30
/plugin marketplace add artemnovitckii/claude-editing-skills
/plugin install editing-skills@claude-editing-skillsWhat ranking-list does
The skill builds a reel with an S-to-F table, a title and captions positioned below the speaker’s chin. It activates with /ranking-list or a request to make a ranking reel from a 9:16 clip where the speaker names and judges items.
The reel.py script marks spoken words and extracts a frame for positioning the table and captions; build.py then renders an MP4 from a JSON spec. The .sheet.jpg file shows a frame for review. Transcription needs a GROQ_API_KEY; ffmpeg, Node and Python 3 are also required. If the virtual environment is missing, the setup script runs setup.sh.
What it helps with
- edit a vertical clip into a tier-ranking reel
- sync item cards with spoken names and verdicts
- position the table and captions around the speaker’s face
Example prompts for the agent
- Turn this 9:16 clip into a ranking reel with
/ranking-list. - Make an S-to-F tier list from this video; show each card when the item is named and drop it into place on the verdict.
- Build a tier-ranking reel from this clip and check the table placement in the frame.
How to install ranking-list
1Plugin marketplace
/plugin marketplace add artemnovitckii/claude-editing-skills/plugin install editing-skills@claude-editing-skillsThis installs the whole editing-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill ranking-list -a claude-code3Manually: put the files in place
~/.claude/skills/ranking-list/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ranking-list/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill ranking-list -a codex2Manually: put the files in place
.agents/skills/ranking-list/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill ranking-list -a cursor2Manually: put the files in place
.cursor/skills/ranking-list/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install artemnovitckii/claude-editing-skills skills/ranking-list2Manually: put the files in place
.github/skills/ranking-list/SKILL.md1Skills CLI (Vercel)
npx skills add artemnovitckii/claude-editing-skills --skill ranking-list -a gemini-cli2Platform CLI
gemini skills install https://github.com/artemnovitckii/claude-editing-skills --path skills/ranking-listManually: put the files in place
.devin/skills/ranking-list/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ranking-list
How do I install ranking-list in Claude Code?
Add the marketplace with /plugin marketplace add artemnovitckii/claude-editing-skills, then install the plugin with /plugin install editing-skills@claude-editing-skills.
What does ranking-list do?
It edits a 9:16 talking-head video into a ranking reel. Cards appear when items are named and move into their assigned tiers when the speaker gives a verdict.
What does ranking-list need to run?
Transcription requires a GROQ_API_KEY. The skill also needs ffmpeg, Node and Python 3.
Source text
SKILL.md · MIT
---
name: ranking-list
description: Edits a talking-head clip into a tier-list ranking reel. An S-to-F tier table sits on the speaker's chest, each item pops up as it is named and drops into its tier when the verdict lands, with an orange title on top and spoken captions just under the chin. Use when the user runs /ranking-list or asks for a tier list, a ranking reel or "rank these" on a 9:16 clip.
---
# /ranking-list
```
┌──────────────────────┐
│ BEST CONTENT FORMATS│ orange skewed title
│ (face) │
│ at c tier │ caption just under the chin
│ S ▓▓ ┌──────────┐ │
│ A │ FACEBOOK │ │ item pops on the chest, then drops into its row
│ B └──────────┘ │
│ … F │
└──────────────────────┘
```
## First use
This skill's folder is the "Base directory" Claude Code shows when it loads it.
```bash
SKILL_DIR="<base directory of this skill>" # the path Claude Code printed as "Base directory for this skill"
KIT=$(python3 -c 'import os,sys;print(os.path.realpath(os.path.join(sys.argv[1],"..","..","kit")))' "$SKILL_DIR")
PY="$KIT/.venv/bin/python"; [ -x "$PY" ] || bash "$KIT/setup.sh"
```
`GROQ_API_KEY` must be set to transcribe. Needs ffmpeg and Node.
## Steps
1. **Clip.** A 9:16 talking head where the speaker names things and judges them ("carousels are S tier… reels, B").
2. **Words.** Run `"$PY" "$KIT/reel.py" words <video>`. It prints one sentence per line with `[ends …]` (when its last word ends). Find each item's name and its verdict. The item pops on its name and drops on its verdict. Pick a stretch that holds 1 to 5 items, and keep `end` at least 0.4 s after the last drop.
3. **Chin.** Run `"$PY" "$KIT/reel.py" frame <video> <t> frame.jpg` and read the y of the chin.
- Set `caption_top` about 40 px under the chin.
- Set `table_top` 80 px under that.
- On a close-up (chin below about y 1150), use 3 or 4 `tiers` so the table stays above y 1500. The item card shrinks itself to fit.
- Captions must never sit on the face.
4. **Spec.** Write `<clip>.ranking-list.json` (below). Paths in a spec are relative to the spec file. Times are seconds from `start`, or spoken words.
5. **Build.** Run `"$PY" "$SKILL_DIR/build.py" <spec.json>`.
6. **Check.** Look at `<out>.sheet.jpg`:
- The caption is under the chin.
- The table and items sit on the chest, above the red bottom zone.
- Each drop lands on its verdict word.
7. **Hand over** the mp4 path.
## Spec
```json
{
"video": "my-clip.mp4", "start": 0, "end": 7.1,
"title": "BEST CONTENT\nFORMATS",
"table_top": 1100, "caption_top": 1022,
"items": [
{"name": "CAROUSELS", "tier": "S", "pop": 0.06, "drop": "cheat", "images": ["c1.jpg", "c2.jpg", "c3.jpg"]},
{"name": "REELS", "tier": "B", "pop": "twice", "drop": "reels", "icon": "play", "color": "#7a2fb0"}
]
}
```
- **`items`**: each item gets a `name` (keep it short and uppercase), a `tier` (S, A, B, C, D, E or F), and `pop` and `drop` times. Its picture is one of:
- `images`: 2 or 3 images fan out, or 1 image fills the card.
- `icon: "play"`: a reel icon.
- nothing: just the name on a coloured card (`color`).
- Items in the same tier line up left to right in the order they drop.
- **`tiers`** (optional) replaces S to F: `[["GOAT", "#FF7F7F"], ["MID", "#FFDF7F"], ["NO", "#7FBFFF"]]`.
## Taste
- Pop on the name, drop on the verdict. If they are said together, drop 1 s after the pop.
- Title in 2 short lines, 2 to 3 words each.
- Logos and images must be ones the user is allowed to show. A plain name card is always fine.
© Artem Novitckii · MIT · artemnovitckii/claude-editing-skills