
Ai Writing Detox
If you write anything public-facing with AI help, you need this. It's a systematic detox for the telltale patterns that make readers wince: "delve into the landscape," throat-clearing intros, reflexive three-item lists, the dreaded "it's not X, it's Y" construction. Comes with ban lists for words (robust, leverage, comprehensive), phrases ("in today's landscape"), and structural tics like starting every sentence with "So" or ending with em-dashes. The before/after examples are brutal but accurate. Particularly sharp on 2025-era Claude/GPT signatures like tricolon abuse and empty hedges. Includes AP style rules like sentence case for headings and "more than" instead of "over." Read your draft aloud after running this and it'll sound like you actually wrote it.
- skills.sh installs
- 333
- GitHub stars
- 451
- last updated
- Aug 21, 2026
Install
$ npx -y skills add jamditis/claude-skills-journalism --skill ai-writing-detox --agent claude-codeInstalls into .claude/skills of the current project.
Files
AI writing detox
Good writing is invisible. If readers notice the writing style, it's distracting from the content. AI patterns are noticeable, they break trust.
When to use
- Writing or editing any journalism content
- Creating press releases or media advisories
- Drafting documentation or reports
- Writing social media posts
- Reviewing any AI-assisted text before publication
Banned words (delete or replace)
Sponsors
Details
- Repository
- github.com/jamditis/claude-skills-journalism
- Categories
- Documentation, AI & Agent Building
- First seen
- Jun 3, 2026