Search \u201cfinest Claude Abilities for writing\u201d and also you get lists padded with expertise that write commit messages and inner standing reviews. Helpful issues. Not writing.<\/p>\n
This record solely contains repositories that exist for writing. Each entry is a repository whose total cause for being is writing or modifying, which suggests its star depend measures the factor you care about. Listed below are a few of the finest writing agent expertise (ranked by their reputation) that assist distinguish your writing from a mere: AI-slop!<\/span><\/p>\n Notice: All figures pulled from the GitHub on fifth August 2026.<\/p>\n blader\/humanizer \u00b7 1,005 forks<\/p>\n Thirty-three numbered patterns, every with a earlier than and after instance, all drawn from Wikipedia\u2019s 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 slightly than merely rationed.<\/p>\n Two issues it does that stop-slop doesn\u2019t:<\/p>\n Voice matching: Paste two or three paragraphs of your individual writing first. It reads your sentence rhythm, phrase decisions, and quirks, then rewrites towards these as a substitute of towards generic clear prose. Most anti-slop expertise flatten every little thing to the identical impartial register. This one goals at yours.<\/p>\n A second move: After rewriting, it runs an \u201cclearly AI generated\u201d audit over its personal output and rewrites once more, on the speculation that the primary move leaves tells.<\/p>\n 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. <\/p>\n hardikpandya\/stop-slop \u00b7 1,082 forks <\/p>\n Essentially the most-starred writing ability on GitHub, and it\u2019s one SKILL.md plus three reference recordsdata. It really works as a result of it refuses to inform the mannequin to \u201csound extra human.\u201d It ships lists as a substitute:<\/p>\n phrases.md bans throat-clearing openers, emphasis crutches, enterprise jargon, each adverb, obscure declaratives, meta-commentary<\/p>\n constructions.md bans binary contrasts, unfavorable listings, dramatic fragmentation, rhetorical setups, false company, passive voice<\/p>\n Sentence guidelines bans em dashes, staccato fragments, and lazy extremes like \u201ceach\u201d and \u201cby no means\u201d<\/p>\n Then it scores the end result 1 to 10 on directness, rhythm, belief, authenticity, and density. Under 35 out of fifty, revise. That\u2019s a verify the mannequin runs towards itself, which is what separates a ability from a suggestion.<\/p>\n Finest for: Last move on something drafted with AI assist.<\/p>\n Orchestra-Analysis\/AI-Analysis-SKILLs \u00b7 833 forks <\/p>\n 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.<\/p>\n However three of its classes are, and so they\u2019re stronger than most standalone writing repos:<\/p>\n Educational Plotting generates publication-quality figures with venue-specific styling, protecting each structure diagrams and matplotlib knowledge charts.<\/p>\n Ideation has two expertise for the blank-page downside. Analysis Brainstorming runs ten complementary lenses over a subject. Inventive Considering applies bisociation, structure-mapping and constraint manipulation.<\/p>\n 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.<\/p>\n worldwonderer\/oh-story-claudecode \u00b7 687 forks <\/p>\n 13 instances the celebs of my fiction entry, and a greater concept of what fiction writing with an agent seems like. Constructed for Chinese language net fiction, however the English README is full and the tactic transfers.<\/p>\n The pipeline is development scouting, deconstruction, writing, slop cleanup, cowl artwork. The center step is the one no person else does. Level it at a novel that labored and it produces a structured teardown:<\/p>\n Story Teardown Report\u00a0scores the story core throughout 5 dimensions, six payoff sides, cognitive reversal, and 9 layers of resonance.<\/p>\n Plot Beats\u00a0extracts each plot level with an emotion marker from \u22129 to +9<\/span>, supplying you with the emotional curve as knowledge.<\/p>\n Craft Methods\u00a0catalogues eleven strategies: POV dealing with, dialogue, data gaps, object hooks<\/p>\n These outputs change into a reusable library. The writing expertise learn from it, so that you draft towards the construction of one thing that already labored slightly than towards the mannequin\u2019s defaults.<\/p>\n AgriciDaniel\/claude-blog \u00b7 274 forks <\/p>\n 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.<\/p>\n The half price stealing even for those who by no means set up it’s the supply contract. Each draft is scored towards 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 creator\u2019s framing: the person is rarely the primary reviewer.<\/span><\/p>\n That\u2019s the verification sample utilized to prose. Most writing expertise cease when the output seems completed, which makes you the standard gate.<\/p>\n Finest for: Publishing at quantity, the place you possibly can\u2019t personally evaluate each draft.<\/p>\n Set up any of those by cloning into your expertise listing:<\/p>\n git clone https:\/\/github.com\/\/ ~\/.claude\/expertise\/<\/p>\n Talent humanizer<\/p>\n $ git clone https:\/\/github.com\/blader\/humanizer ~\/.claude\/expertise\/humanizer<\/p>\n stop-slop<\/p>\n $ git clone https:\/\/github.com\/hardikpandya\/stop-slop ~\/.claude\/expertise\/stop-slop<\/p>\n AI-Analysis-SKILLs<\/p>\n $ git clone https:\/\/github.com\/Orchestra-Analysis\/AI-Analysis-SKILLs ~\/.claude\/expertise\/ai-research<\/p>\n oh-story-claudecode<\/p>\n $ git clone https:\/\/github.com\/worldwonderer\/oh-story-claudecode ~\/.claude\/expertise\/oh-story<\/p>\n claude-blog<\/p>\n $ git clone https:\/\/github.com\/AgriciDaniel\/claude-blog ~\/.claude\/expertise\/claude-blog<\/p>\n<\/div>\n Choose by what you write:<\/p>\n You write Something drafted with AI Weblog posts and essays<\/p>\n humanizer Fiction or serial tales ML or AI analysis papers Excessive-volume content material you possibly can\u2019t evaluate Chinese language-language prose Everybody ought to have humanizer regardless. It\u2019s the one entry that improves output it doesn’t matter what the output is (overlook the em-dashes and different AI markers). <\/p>\n Learn extra: The way to Join MCP Servers with Claude (Claude Desktop and Claude Code)<\/p>\n A. As a result of stars on a devoted repo attribute to the ability itself. stop-slop has 15,199 stars for one SKILL.md, which is 15,199 folks endorsing that particular file. A ability inside a 200,000-star bundle of 41 instruments tells you nothing about that ability.<\/p>\n<\/p><\/div>\n1. humanizer | \u2605 33,700<\/h2>\n
![\"Humanizer](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/image-2-z0i00s.webp\")
<\/figure>\n<\/div>\n2. stop-slop | \u2605 15,199<\/h2>\n
![\"Claude](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/image-1-z0i00s.webp\")
<\/figure>\n<\/div>\n3. AI-Analysis-SKILLs | \u2605 11,400<\/h2>\n
![\"Orchestra](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/image-3-z0i00s.webp\")
<\/figure>\n<\/div>\n4. oh-story-claudecode | \u2605 5,080<\/h2>\n
5. claude-blog | \u2605 1,579<\/h2>\n
![\"Claude](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/image-4-z0i00s.webp\")
<\/figure>\n<\/div>\nPutting in them in Claude Code<\/h2>\n
\n Set up command<\/p>\nLast Ideas<\/h2>\n
\n Set up<\/p>\n
\n humanizer<\/p>\n
\n +<\/span>
\n claude-blog<\/p>\n
\n oh-story-claudecode<\/p>\n
\n AI-Analysis-SKILLs (ml-paper-writing)<\/span><\/p>\n
\n claude-blog<\/p>\n
\n Humanizer-zh<\/p>\n<\/div>\nIncessantly Requested Questions<\/h2>\n
![\"Vasu](\"https:\/\/av-eks-lekhak.s3.amazonaws.com\/media\/lekhak-profile-images\/converted_image_KFNyH8C.webp\")
<\/p><\/div><\/div>\n