Search “finest Claude Abilities for writing” and also you get lists padded with expertise that write commit messages and inside standing stories. Helpful issues. Not writing.
This listing solely contains repositories that exist for writing. Each entry is a repository whose total motive for being is writing or enhancing, which implies its star rely measures the factor you care about. Listed below are a few of the finest writing agent expertise (ranked by their recognition) that assist distinguish your writing from a mere: AI-slop!
Word: All figures pulled from the GitHub on 5th August 2026.
1. stop-slop | ★ 15,199
hardikpandya/stop-slop · 1,082 forks
Probably the most-starred writing talent on GitHub, and it’s one SKILL.md plus three reference recordsdata. It really works as a result of it refuses to inform the mannequin to “sound extra human.” It ships lists as a substitute:
phrases.mdbans throat-clearing openers, emphasis crutches, enterprise jargon, each adverb, imprecise declaratives, meta-commentaryconstructions.mdbans binary contrasts, unfavourable 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 outcome 1 to 10 on directness, rhythm, belief, authenticity, and density. Beneath 35 out of fifty, revise. That’s a examine the mannequin runs in opposition to itself, which is what separates a talent from a suggestion.
Finest for: Remaining move 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 moderately than merely rationed.
Two issues it does that stop-slop doesn’t:
- Voice matching: Paste two or three paragraphs of your individual writing first. It reads your sentence rhythm, phrase selections, and quirks, then rewrites towards these as a substitute of towards generic clear prose. Most anti-slop expertise flatten every part to the identical impartial register. This one goals at yours.
- A second move: After rewriting, it runs an “clearly AI generated” audit over its personal output and rewrites once more, on the idea that the primary move leaves tells.
Finest for: The whole lot. 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 total 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, and so they’re stronger than most standalone writing repos:
- Educational Plotting generates publication-quality figures with venue-specific styling, protecting each structure diagrams and matplotlib information charts.
- Ideation has two expertise for the blank-page drawback. Analysis Brainstorming runs ten complementary lenses over a subject. Artistic Pondering applies bisociation, structure-mapping and constraint manipulation.
- 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 advice.
4. oh-story-claudecode | ★ 5,080
worldwonderer/oh-story-claudecode · 687 forks
13 instances the celebrities of my fiction entry, and a greater concept of what fiction writing with an agent appears like. Constructed for Chinese language net fiction, however the English README is full and the strategy transfers.
The pipeline is pattern 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 sides, 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, info gaps, object hooks
These outputs turn into a reusable library. The writing expertise learn from it, so that you draft in opposition to the construction of one thing that already labored moderately 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, web site audits, subject clusters, content material decay detection.
The half value stealing even should 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 under 90 is blocked and re-run as much as 3 times earlier than it reaches you. The writer’s framing: the consumer 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 may’t personally evaluation 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/ Remaining 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 one can Join MCP Servers with Claude (Claude Desktop and Claude Code)
Steadily Requested Questions
A. As a result of stars on a devoted repo attribute to the talent itself. stop-slop has 15,199 stars for one SKILL.md, which is 15,199 folks endorsing that particular file. A talent inside a 200,000-star bundle of 41 instruments tells you nothing about that talent.
A. Two or three. One anti-slop move, one in your format, optionally one for analysis. Past that their set off descriptions overlap and also you lose the flexibility to foretell which fires.
A. Most do. Abilities are markdown, so that they port to Codex, Cursor, and Gemini CLI. stop-slop paperwork 4 set up surfaces together with uncooked API system prompts. skill-deslop ships a packaged .talent file for Claude Desktop.
A. As a result of the patterns are documentable. Wikipedia’s WikiProject AI Cleanup maintains an inventory drawn from hundreds of AI-generated texts, which supplies these expertise a shared factual base that common writing recommendation lacks. It’s the one writing drawback with an agreed reply key.
A. After getting a home model, sure. Learn stop-slop for the way to write guidelines a mannequin can truly examine, and writing-shape for the way to construction a multi-turn writing session. Between them you’ll have the sample. All star and fork counts retrieved from the GitHub API on 5 August 2026. These transfer quick. Confirm earlier than publishing.
I specialise in 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.
Login to proceed studying and luxuriate in expert-curated content material.