Prime 5 Claude Abilities for Writing (Ranked by GitHub Stars)

Search “finest Claude Abilities for writing” and also you get lists padded with expertise that write commit messages and inner standing experiences. Helpful issues. Not writing.

This checklist solely contains repositories that exist for writing. Each entry is a repository whose complete cause for being is writing or modifying, which implies its star depend measures the factor you care about. Listed here are among the finest writing agent expertise (ranked by their reputation) that assist distinguish your writing from a mere: AI-slop!

Be aware: All figures pulled from the GitHub on 5^th August 2026.

1. stop-slop | ★ 15,199

hardikpandya/stop-slop · 1,082 forks

Essentially the most-starred writing talent on GitHub, and it’s one SKILL.md plus three reference information. It really works as a result of it refuses to inform the mannequin to “sound extra human.” It ships lists as an alternative:

• phrases.md bans throat-clearing openers, emphasis crutches, enterprise jargon, each adverb, imprecise declaratives, meta-commentary
• constructions.md bans binary contrasts, adverse listings, dramatic fragmentation, rhetorical setups, false company, passive voice
• Sentence guidelines bans em dashes, staccato fragments, and lazy extremes like “each” and “by no means”

Then it scores the end result 1 to 10 on directness, rhythm, belief, authenticity, and density. Under 35 out of fifty, revise. That’s a verify the mannequin runs in opposition to itself, which is what separates a talent from a suggestion.

Finest for: Last cross on something drafted with AI assist.

2. humanizer | ★ 33,700

blader/humanizer · 1,005 forks

Thirty-three numbered patterns, every with a earlier than and after instance, all drawn from Wikipedia’s Indicators of AI Writing information. The early variations went after apparent vocabulary, however later releases moved to rhythm: subjectless fragments, manufactured punchlines, the chatty rhetorical opener that solutions its personal query, and em dashes reduce outright somewhat than merely rationed.

Two issues it does that stop-slop doesn’t:

• Voice matching: Paste two or three paragraphs of your personal writing first. It reads your sentence rhythm, phrase selections, and quirks, then rewrites towards these as an alternative of towards generic clear prose. Most anti-slop expertise flatten the whole lot to the identical impartial register. This one goals at yours.
• A second cross: After rewriting, it runs an “clearly AI generated” audit over its personal output and rewrites once more, on the idea that the primary cross leaves tells.

Finest for: Every little thing. Default Claude responses are on the verge of AI-slop themselves. Including this expertise, helps giving them a humane contact.

3. AI-Analysis-SKILLs | ★ 11,400

Orchestra-Analysis/AI-Analysis-SKILLs · 833 forks

Ninety-eight expertise throughout 23 classes, constructed to let an agent run the complete AI analysis lifecycle from literature survey to submitted paper. Most of it’s engineering: Megatron, vLLM, TRL, Flash Consideration, quantization. Not writing.

However three of its classes are, they usually’re stronger than most standalone writing repos:

1. Tutorial Plotting generates publication-quality figures with venue-specific styling, protecting each structure diagrams and matplotlib information charts.
2. Ideation has two expertise for the blank-page drawback. Analysis Brainstorming runs ten complementary lenses over a subject. Artistic Considering applies bisociation, structure-mapping and constraint manipulation.
3. ARA Rigor Reviewer scores a draft throughout six dimensions of analysis rigor, together with falsifiability, scope calibration, argument coherence and methodological rigor, then points a severity-ranked report ending in an accept-to-reject suggestion.

4. oh-story-claudecode | ★ 5,080

worldwonderer/oh-story-claudecode · 687 forks

13 occasions the celebrities of my fiction entry, and a greater thought of what fiction writing with an agent appears like. Constructed for Chinese language internet fiction, however the English README is full and the strategy transfers.

The pipeline is development scouting, deconstruction, writing, slop cleanup, cowl artwork. The center step is the one no one else does. Level it at a novel that labored and it produces a structured teardown:

• Story Teardown Report scores the story core throughout 5 dimensions, six payoff aspects, cognitive reversal, and 9 layers of resonance.
• Plot Beats extracts each plot level with an emotion marker from −9 to +9, supplying you with the emotional curve as information.
• Craft Strategies catalogues eleven strategies: POV dealing with, dialogue, data gaps, object hooks

These outputs turn out to be a reusable library. The writing expertise learn from it, so that you draft in opposition to the construction of one thing that already labored somewhat than in opposition to the mannequin’s defaults.

5. claude-blog | ★ 1,579

AgriciDaniel/claude-blog · 274 forks

Thirty sub-skills and 5 brokers protecting the entire weblog lifecycle: technique, briefs, outlines, drafting, rewriting, schema, website audits, matter clusters, content material decay detection.

The half value stealing even in the event you by no means set up it’s the supply contract. Each draft is scored in opposition to a 100-point rubric throughout 5 gates, and something beneath 90 is blocked and re-run as much as 3 times earlier than it reaches you. The creator’s framing: the person isn’t the primary reviewer.

That’s the verification sample utilized to prose. Most writing expertise cease when the output appears completed, which makes you the standard gate.

Finest for: Publishing at quantity, the place you’ll be able to’t personally overview each draft.

Putting in them in Claude Code

Set up any of those by cloning into your expertise listing:

git clone https://github.com// ~/.claude/expertise/

Last Ideas

Decide by what you write:

Everybody ought to have humanizer regardless. It’s the one entry that improves output it doesn’t matter what the output is (neglect the em-dashes and different AI markers).

Learn extra: How you can Join MCP Servers with Claude (Claude Desktop and Claude Code)

Incessantly Requested Questions

I concentrate on reviewing and refining AI-driven analysis, technical documentation, and content material associated to rising AI applied sciences. My expertise spans AI mannequin coaching, information evaluation, and knowledge retrieval, permitting me to craft content material that’s each technically correct and accessible.