sk-style — Claude Code skill: script editing and setup
The sk-style Claude Code skill polishes spoken scripts for short videos while keeping their meaning intact. It activates on requests to tighten wording, improve flow, or remove AI-sounding phrases.
MIT ★ 204 updated 2026-11-09
npx skills add howznguyen/shorts-kit --skill sk-style -a claude-codeWhat sk-style does
The skill edits the wording of a script without changing its claims. It breaks up long sentences, cuts filler and stacked intensifiers, names the subject at the start of a scene, and replaces phrases reused in earlier videos. It also checks closing turns and contrast pairs.
It starts with bun run lint <id> and handles each type of issue in a separate pass. After editing, it runs bun run tts <id>; the audio must be heard before lint runs again. §3b warnings should decrease, with no new warnings appearing. Numbers, caveats, and dates stay intact.
The skill does not reorder scenes or add or remove claims; sk-brief and sk-facts handle those changes. A real person’s verbatim quote stays as spoken, even when it exceeds the sentence limit.
What it helps with
- split long sentences without losing facts
- remove filler and stacked intensifiers
- replace a scene-opening pronoun with its subject
- rewrite phrases repeated in earlier videos
- reduce §3b warnings from
bun run lint <id>
Example prompts for the agent
- Tighten the spoken script for
video-idwithout changing its claims. - Remove AI-sounding phrasing and check sentence length in
video-id. - Fix the §3b warnings from
bun run lint video-id, keeping all numbers and dates.
How to install sk-style
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-style -a claude-code2Manually: put the files in place
~/.claude/skills/sk-style/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/sk-style/
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-style -a codex2Manually: put the files in place
.agents/skills/sk-style/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-style -a cursor2Manually: put the files in place
.cursor/skills/sk-style/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install howznguyen/shorts-kit .claude/skills/sk-style2Manually: put the files in place
.github/skills/sk-style/SKILL.md1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-style -a gemini-cli2Platform CLI
gemini skills install https://github.com/howznguyen/shorts-kit --path .claude/skills/sk-styleManually: put the files in place
.devin/skills/sk-style/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 sk-style
How do I install sk-style in Claude Code?
Run npx skills add howznguyen/shorts-kit --skill sk-style -a claude-code. The skill file is at ~/.claude/skills/sk-style/SKILL.md.
What does sk-style do?
It revises spoken wording for short-video scripts while preserving their facts and meaning. It shortens long sentences, removes filler, and replaces stale phrases.
Which commands does sk-style use?
It uses bun run lint <id> and bun run tts <id>. After editing, the script needs a fresh TTS run, an audio listen, and another lint check.
Source text
SKILL.md · MIT
---
name: sk-style
description: Polishes the wording of a short's spoken script without changing what it says, by splitting long sentences, cutting filler and AI-slop phrases, naming the subject at the start of each scene, and replacing worn phrases. Use when the user says "tighten the script", "this sounds like AI", "this sentence is clunky", "make it punchier", "rewrite for flow", "too many adjectives", or when bun run lint reports §3b sentence-style warnings.
---
# sk-style: fix the words, not the meaning
**Announce:** "Using sk-style for <id>."
Rules: §3b (`docs/soul/01-voice-and-structure.md`); numbers and phrase lists in
`docs/soul/thresholds.json` (`maxWordsPerSentence`, `medianWordsPerSentence`,
`shortSentenceMaxShare`, `bannedPhrases`, `intensifiersMax`, `strongWords`). To
measure top channels in your niche instead of guessing: `docs/lessons/style-measurement.md`.
## Boundary
| Fix here | Go elsewhere |
|---|---|
| split a long sentence, cut filler, swap a connective | change or drop a **number** → `sk-facts` |
| reorder clauses inside a sentence | reorder **scenes** or change flow → `sk-brief` |
| name the subject in a scene's first line | add or remove a **claim** → `sk-facts`, then `sk-narration` |
| replace a worn phrase | the phrase is prescribed by a § → `sk-improve` |
If a polish pass loses a number, a caveat or a date, it is no longer a polish.
Stop and go back to the brief and the ledger.
## Steps
1. **Snapshot.** `bun run lint <id>` and keep the output. It is the baseline for
step 6 and the to-do list for step 3.
2. **Read the whole script once without editing.** Editing on first read rewrites
things that were already right.
3. **One pass per fault**, across the whole script, before the next fault. Mixing
faults in one pass is how things get missed and meaning gets broken.
1. *Long sentences* over `maxWordsPerSentence`: split at a clause; keep every fact.
2. *Filler*: phrases in `bannedPhrases` and stacked intensifiers. Delete, or
replace with the number from the ledger that the adjective was standing in for.
3. *Scene openers*: a scene whose first word is a pronoun. Name the subject; the
viewer may have just arrived.
4. *Worn phrases*: a phrase used in earlier videos. Write a new one for this video.
5. *The closing turn*: negate what the viewer believes, then give the real reason.
Avoid parallel negation ("not X, not Y, not Z").
6. *Read aloud*: where you run out of breath mid-sentence, it is still too long,
even if lint passed.
7. *Contrast pairs* ("one does X, the other Y"): has the viewer heard both names,
and which ledger record states the contrast? The ledger holds single claims;
a relation between two numbers is the easiest thing to invent and no check
catches it.
4. **Re-run TTS:** `bun run tts <id>`. Mandatory, because `text` changed.
5. **Listen.** Does a split sentence sound clipped? Does a removed connective leave
a gap?
6. **Lint again and diff against step 1.** §3b warnings must go down and **nothing
else may appear**. A new fact or flow warning means you edited content, not words.
7. **A fault repeated across videos is a rule, not this video's bug.** Note it and
use `sk-improve`; do not quietly fix it by hand in every script.
## Do not
- Drop a number to make a sentence shorter.
- Invent a relation between two facts to make a sentence balance.
- Add phrases to `bannedPhrases` mid-video. Changing a rule is `sk-improve`,
and it edits the § too.
- Polish a video that is already posted. Posted videos are history.
## Exception
A verbatim quote from a real person keeps their words even if it breaks
`maxWordsPerSentence`. Say so in the brief so the next pass does not "fix" it.
Next: `sk-scene` if scene lengths changed, otherwise `sk-render`.
© howznguyen · MIT · howznguyen/shorts-kit