data-story
Data Story video-editing style for Claude: Analyst look: every number becomes an animated counter or bar chart beside the speaker on a dark grid. Use for finance, business, market updates, research results, any talk with numbers. Turns a raw clip into a finished 16:9 edit with th
Install
npx skills add https://github.com/Viprasol-Tech/claude-video-editing-skills/tree/main/plugins/video-studio/skills/data-story
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install viprasol-tech-claude-video-editing-skills@llmmart
git clone https://github.com/Viprasol-Tech/claude-video-editing-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole viprasol-tech/claude-video-editing-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Data Story
Analyst look: every number becomes an animated counter or bar chart beside the speaker on a dark grid.
- Best for: finance, business, market updates, research results, any talk with numbers
- Category: Explainer
- Default format: 16:9 (change with
--format 9:16 | 1:1 | 4:5 | 16:9) - Needs camera footage: yes, a raw talking clip
- Text behind the speaker: no
Before you start
This style runs on the video-studio-core skill, which must be installed in the same skills folder.
CORE= thevideo-studio-corefolder next to this one (e.g.~/.claude/skills/video-studio-core).STYLE= this skill's folder (it holdstheme.jsonandtheme.css).- First time on a machine:
python CORE/scripts/check_env.py, and fix anything it reports. - If
COREis missing, tell the user to installvideo-studio-corefrom the same pack.
Make the edit
python CORE/scripts/run.py clip.mp4 --style STYLE --work edit-data-story --stop-after plan
# refine edit-*/plan.json (see below), then check stills:
python CORE/scripts/render.py edit-data-story/plan.json --frames 1,3,6,9
python CORE/scripts/render.py edit-data-story/plan.json
python CORE/scripts/finish.py edit-data-story/plan.json
Open contact_sheet.png and look at it before the full render. The final video is final.mp4 in the work folder.
Use --formats 1:1,16:9 on finish.py for extra sizes. Add music with "music": {"src": "track.mp3", "volume": 0.12} in the plan.
The look
- Speaker in a rounded panel on the right, data on the left on a dark grid.
- Every number the speaker says is on screen within 0.1 s, counting up. Comparisons become bar charts with the winner highlighted.
- Monospace numbers, green accent, nothing decorative.
Refine the plan
The draft from make_plan.py is automatic. Make it good:
- Read
words.jsonand rewrite the hook (first 2-3 s) into a short, specific promise. - Replace weak auto-picked key words with the words that carry the meaning (numbers, results, names, contrasts).
- Fix any mis-heard words in the
wordsarray (keep their times). - Go through the transcript and list every number. Group related ones into
bars(title + items with label, value, highlight). - Single figures stay as
counterwith a clear 2-4 word label. - Add a
cardsummary at the end with the 3 key takeaways. - For 9:16, change speaker rect to the bottom half (
rect: [0, 960, 1080, 960]) and move data to y=H*0.25. - Element types and fields:
CORE/references/plan-schema.md.
Check before delivering
- Contact sheet: text readable, nothing cut off, nothing covering the face unless intended, safe zones respected (9:16: keep text between 10% and 85% of the height).
- Watch for timing: overlays land with the spoken word, not after it.
ffprobethe final file: right size, duration and audio.- Tell the user what you cut (seconds removed), what the look adds, and where the file is.
Change the look
Colours and fonts live in theme.json (vars, fontsUrl) and theme.css. For a one-off change, edit plan.json (theme.vars, element style) instead of the skill files.
Example requests
- "Turn every number I say into a chart."
- "Data-story edit for my market update."
- "Make my revenue breakdown look like a Bloomberg segment."
Files (claude-video-editing-skills)
-
SKILL.md 3.6 KB
--- name: data-story description: "Data Story video-editing style for Claude: Analyst look: every number becomes an animated counter or bar chart beside the speaker on a dark grid. Use for finance, business, market updates, research results, any talk with numbers. Turns a raw clip into a finished 16:9 edit with the video-studio-core engine (transcribe, auto-cut, motion graphics, sound, grade)." license: MIT --- # Data Story Analyst look: every number becomes an animated counter or bar chart beside the speaker on a dark grid. - **Best for:** finance, business, market updates, research results, any talk with numbers - **Category:** Explainer - **Default format:** 16:9 (change with `--format 9:16 | 1:1 | 4:5 | 16:9`) - **Needs camera footage:** yes, a raw talking clip - **Text behind the speaker:** no ## Before you start This style runs on the **video-studio-core** skill, which must be installed in the same skills folder. - `CORE` = the `video-studio-core` folder next to this one (e.g. `~/.claude/skills/video-studio-core`). - `STYLE` = this skill's folder (it holds `theme.json` and `theme.css`). - First time on a machine: `python CORE/scripts/check_env.py`, and fix anything it reports. - If `CORE` is missing, tell the user to install `video-studio-core` from the same pack. ## Make the edit ```bash python CORE/scripts/run.py clip.mp4 --style STYLE --work edit-data-story --stop-after plan # refine edit-*/plan.json (see below), then check stills: python CORE/scripts/render.py edit-data-story/plan.json --frames 1,3,6,9 python CORE/scripts/render.py edit-data-story/plan.json python CORE/scripts/finish.py edit-data-story/plan.json ``` Open `contact_sheet.png` and look at it before the full render. The final video is `final.mp4` in the work folder. Use `--formats 1:1,16:9` on `finish.py` for extra sizes. Add music with `"music": {"src": "track.mp3", "volume": 0.12}` in the plan. ## The look - Speaker in a rounded panel on the right, data on the left on a dark grid. - Every number the speaker says is on screen within 0.1 s, counting up. Comparisons become bar charts with the winner highlighted. - Monospace numbers, green accent, nothing decorative. ## Refine the plan The draft from `make_plan.py` is automatic. Make it good: - Read `words.json` and rewrite the hook (first 2-3 s) into a short, specific promise. - Replace weak auto-picked key words with the words that carry the meaning (numbers, results, names, contrasts). - Fix any mis-heard words in the `words` array (keep their times). - Go through the transcript and list every number. Group related ones into `bars` (title + items with label, value, highlight). - Single figures stay as `counter` with a clear 2-4 word label. - Add a `card` summary at the end with the 3 key takeaways. - For 9:16, change speaker rect to the bottom half (`rect: [0, 960, 1080, 960]`) and move data to y=H*0.25. - Element types and fields: `CORE/references/plan-schema.md`. ## Check before delivering - Contact sheet: text readable, nothing cut off, nothing covering the face unless intended, safe zones respected (9:16: keep text between 10% and 85% of the height). - Watch for timing: overlays land with the spoken word, not after it. - `ffprobe` the final file: right size, duration and audio. - Tell the user what you cut (seconds removed), what the look adds, and where the file is. ## Change the look Colours and fonts live in `theme.json` (`vars`, `fontsUrl`) and `theme.css`. For a one-off change, edit `plan.json` (`theme.vars`, element `style`) instead of the skill files. ## Example requests - "Turn every number I say into a chart." - "Data-story edit for my market update." - "Make my revenue breakdown look like a Bloomberg segment." -
theme.css 688 B · in bundle
-
theme.json 2 KB
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.