Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

AI writing detox · jamditis | DecimalAI

documentationby jamditis

AI writing detox

jamditis/ai-writing-detox

Source jamditis/claude-skills-journalism ↗License MIT

Eliminate AI-generated writing patterns that erode reader trust.

SkillScore96Maintained

Automatic

Writing & Editing pack

Last verified 8/27/2026

What it changes

Passed 24 of 25 test cases with the skill, and 21 of 25 without it.

Without skill84%

With skill96%

Checks it passed that the model alone missed

The response removes the word "comprehensive".
The response replaces "has the ability to" with "can".
The response starts the sentence directly with the subject.

3 fixed21 passed either way1 still failing0 broke

Pass-rate lift: +12 pp
Tokens: +213%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 8/27/2026v224 of 25 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jamditis-ai-writing-detox/SKILL.md https://app.decimal.ai/s/jamditis-ai-writing-detox/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jamditis-ai-writing-detox, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jamditis-ai-writing-detox/ and pins it in .decimal/skills.lock

decimalai skills add jamditis-ai-writing-detox

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jamditis-ai-writing-detox/SKILL.md https://app.decimal.ai/s/jamditis-ai-writing-detox/SKILL.md

Raw file: /s/jamditis-ai-writing-detox/SKILL.md ↗ · machine-readable summary at /s/jamditis-ai-writing-detox.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Edit this promotional summary line for a media outlet: 'Our team delivers accurate, comprehensive, and engaging coverage every day.' Remove reflexive three-item list rhythms.

What was checked, without and with the skill
Checked	Without skill	With skill
The response avoids using a three-item parallel list structure.	Passed	Passed
The response removes the word "comprehensive".	Missed	Passed

case-20 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md260 linessingle file

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)

Word	Why it's bad	Alternative
delve	AI signature word	explore, examine, look at
realm	Pretentious	area, field
tapestry	Purple prose	(delete entirely)
landscape	Corporate speak	situation, environment
leverage	Jargon	use
utilize	Jargon	use
robust	Meaningless	strong, reliable
seamless	Almost always false	smooth, easy
comprehensive	Rarely necessary	full, complete
cutting-edge	Cliché	modern, new
holistic	Corporate	complete, full
synergy	Corporate	(delete, rewrite)
paradigm	Overused	model, approach
empower	Vague	(be specific about what capability)
innovative	Empty praise	(describe what's new)
transformative	Hyperbolic	changed, improved
sophisticated	Vague filler	advanced, or describe what's complex
leveraging	Corporate jargon	using
ecosystem	Overused metaphor	system, environment
rich	(as modifier)	(delete or be specific)
over (for quantity)	AP rule	more than

Banned phrases

Track record

Benchmark

24 / 25

test cases passed, vs 21 / 25 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/26/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jamditis / claude-skills-journalism

journalism-core/skills/ai-writing-detox/SKILL.md

View on GitHub ↗

License MITImported 8/26/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

AI writing detox

When to use

Banned words (delete or replace)

Banned phrases

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills