Not in the top 1,000 by GitHub stars
artemnovitckii/content-skills
5 Claude Code skills that fix Claude's writing: dumbify, storytelling, viral-hooks, anti-ai-writing, and a voice-dna build guide. MIT.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
anti-ai-writing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1c6e909c975b
No earlier version was observed for comparison.
dumbify/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1c6e909c975b
No earlier version was observed for comparison.
storytelling/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1c6e909c975b
No earlier version was observed for comparison.
viral-hooks/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1c6e909c975b
No earlier version was observed for comparison.
Heat
5.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- anti-ai-writing
anti-ai-writing - dumbify
dumbify - storytelling
storytelling - viral-hooks
viral-hooks
How it works
anti-ai-writing
When your agent uses it
Use when writing or auditing any written content — captions, carousels, newsletters, threads, LinkedIn posts, long-form — and as the FINAL filter on every piece. Reach for it whenever text feels generic, fluent-but-hollow, over-formatted, or "sounds like AI." Strongest on written prose; lighter on spoken reels.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
2,839 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Where this runs
- The 5 diseases (diagnose before you fix)
- Rule priority (when rules collide)
- Specificity — the whole game
- The negative parallelism ban (the #1 tell)
- Analogy & metaphor control
- Blocklists (starting points — the principle outlives the list)
- AI tells (generic even when no single rule is broken)
- Writing mode
- Audit mode (the final pass)
- Anti-overfitting
Files
SKILL.mdcore12,301 bytes
Read SKILL.md
# Anti-AI Writing
**The goal is not "don't sound like AI."** That framing loses — blocklists rot, and chasing a negative gives you a beige voice. The goal is: **sound like a specific person who has thought about the thing and has something to say.** Specificity is the moat. Voice is the moat. Everything below serves those two.
Apply with judgment. **Spirit beats letter.** If a rule makes the sentence worse, break it.
## Where this runs
This skill matters most on **written content** — text a reader's eye scans. Run the **full pass** there: captions, carousels, newsletters, threads, LinkedIn, long-form, DMs, landing copy. It's the last filter on every written piece.
On **spoken content** (reel and video scripts — the words get said aloud), run the **spoken subset only**:
- **Apply:** specificity (Level 3+), kill hollow reframes that don't pay off, cut borrowed-authority / thinkfluencer filler, cut significance inflation. These hurt out loud too.
- **Skip:** the formatting tells (em dashes, bullets, hashtags don't exist in speech), and go light on the vocab blocklist — spoken cadence forgives, and your voice plus the **viral-hooks** and **storytelling** skills are already doing the heavy de-AI-ing. Over-applying prose rules to a script makes it sound stilted, not human.
View the complete source on GitHubdumbify
When your agent uses it
Use when writing or auditing content that has to be easy to follow — explainer reels, teaching carousels, how-to scripts, any piece that teaches or explains something — or when a draft feels dense, jargony, high-effort, or hard to follow. Lowers reading level and mental load so people keep watching and reading. Pairs with the other writing skills in this pack.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,132 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Simple language, not simple ideas
- Where it earns its keep
- The moves
- Don't let it fight the other skills
- How to gauge the level (no tool needed)
- Writing mode
- Audit mode
- Anti-overfitting
Files
SKILL.mdcore4,930 bytes
Read SKILL.md
# Dumbify
People don't churn because content is too simple. They churn because following it is **too much work.** Every bit of mental effort — a fancy word, a nested sentence, undefined jargon — is a reason to swipe away. This skill cuts that effort.
**Target: ~8th-grade reading level for the body, ~6th for hooks.** Easy to follow = low strain = high retention.
## Simple language, not simple ideas
You are lowering the **reading level**, not dumbing down the thinking. The idea can be sophisticated; the words shouldn't be. **Simple ≠ simplistic.** A sharp 13-year-old should be able to *follow* it — that doesn't mean the insight is for 13-year-olds.
## Where it earns its keep
- **High value:** explainers, educational/teaching content, how-to, anything on a technical, financial, or abstract topic. This is where dense writing kills retention.
- **Low value:** already-conversational captions, short hooks, casual personal stories — these come out simple naturally. Don't force this skill where there's nothing to simplify.View the complete source on GitHubstorytelling
When your agent uses it
Use when writing or auditing talking-head / narrative / "yap" content — reel scripts, video scripts, story-driven posts, any piece where someone talks to camera or tells a story. The hook stops the scroll; storytelling holds the watch after it. Not for pure tactical demos or bare listicles with no through-line.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
2,498 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When this fires
- Before you write: use real material, never invent
- 1. The Dance — context vs. conflict (the engine)
- 2. Direction — write the end first
- 3. Story Lens — your unique angle
- 4. Rhythm — write music, not monotony
- 5. Tone — talk to one person
- 6. The Hook — handoff to viral-hooks
- Writing mode (drafting a script)
- Audit mode (checking a draft)
- The checklist (every narrative piece)
- Common mistakes
Files
SKILL.mdcore10,609 bytes
Read SKILL.md
# Storytelling
The hook earns the first 2 seconds. **Storytelling earns every second after.** This skill is the craft of holding attention across the body of a spoken or narrative piece — so the viewer who stopped scrolling actually finishes, and wants to share.
Six techniques. The first four do most of the work; the last two are delivery and handoff.
## When this fires
- **Always**, on any talking-head / narrative / opinion / story-driven content (most reels, all long-form, founder stories, hot takes).
- **The Dance and Rhythm apply even to tutorials and listicles** — any content with a through-line benefits from open loops and varied cadence.
- **Direction and Story Lens shine most on story/opinion pieces** — where there's a narrative or a take to angle.
- **Skip** only for pure mechanical demos with zero narration ("watch me click this").
## Before you write: use real material, never inventView the complete source on GitHubviral-hooks
When your agent uses it
Use when writing or auditing the opening lines of any content — reel hooks, carousel slide 1, video intros, newsletter subject lines, tweet openers — or when a draft's opener feels flat, vague, or skippable.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
2,446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Four Hook Killers
- What "the hook" is on each platform
- Hook shape: 2-3 lines, not always one zinger
- Banned openers
- Writing mode
- Audit mode
- The checklist (every hook, before it ships)
- Common mistakes
Files
SKILL.mdcore10,366 bytes
Read SKILL.md
# Viral Hooks
A hook has exactly ONE job: help the right viewer decide to keep watching. To do that job it must deliver two things, and only two things:
1. **Topic clarity** — within 1-2 seconds, the viewer knows exactly what this is about.
2. **On-target curiosity** — the viewer believes this is for THEM, and an open question pulls them forward.
Everything in this skill exists to make a hook hit both. A hook that's clever but unclear fails. A hook that's clear but flat fails. Both, or it's not done.
**Always pair with your voice:** before writing hooks, read the hooks from your own top-performing posts. Match their cadence and energy — the patterns below are mechanics, your real posts are the sound. If you have a voice file (see the **voice-dna** skill in this pack), use it.
**If you have no sample of your voice** (auditing an outsider's script, a brand-new account, fewer than ~10 posts): proceed on the mechanics alone and say so in the output ("voice unverified — no sample to check against"). Never block, never silently pretend the voice check happened.
## The Four Hook KillersView the complete source on GitHubSkills included
- anti-ai-writing
- dumbify
- storytelling
- viral-hooks
Repository facts
- License
- MIT
- Created
- Jun 20, 2026
- Last pushed
- Jun 20, 2026
- Forks
- 26
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md anti-ai-writing/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.