humanizer
Skill623 starsChanged 10 months agoMITView on GitHub
Detect and remove AI writing patterns to produce natural, human-sounding prose
188 other projects use a version of this.
Adopted by
Most recently taken up by
- aditya-vermax/skillstheir own version, first seen Nov 8, 2026
- chrisleekr/skillstheir own version, first seen Nov 8, 2026
- xhqing/CommunityManagerAgenttheir own version, first seen Nov 8, 2026
- CloudChef/atlasclaw-providerstheir own version, first seen Nov 8, 2026
- Fractera/Agent-Engineering-Infrastructuretheir own version, first seen Nov 8, 2026
- Fractera/Agentic-Engineering-Infrastructuretheir own version, first seen Nov 8, 2026
Used with
Projects with it also use economy-mode, personal-voice and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkilleconomy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
Also in 4 projects that use this
petermuirurithuoSkillpersonal-voice
Captures the user's personality, communication style, and values. Use this skill whenever responding to the user, drafting anything on their behalf (emails, CVs, messages, opinions, explanations), or whenever tone, word choice, or how an opinion is delivered matters. Apply it by default for any prompt, not only when the user explicitly asks for "my style" or "my voice.
Also in 3 projects that use this
Microsoft AzureSkillarchitectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
Also in 3 projects that use this
- +9 more from Azure
Other versions188 projects use a version of this.
Word for word · 1
- QuixiAI/agi-memory★ 623100% same
Edited · 0
None found.
Wrote their own version · 187
- NousResearch/hermes-agent★ 262ksame name
- blader/humanizer★ 63ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- rommapp/romm★ 14ksame name
- github/gh-aw★ 5.6ksame name
- latitude-dev/latitude-llm★ 4.7ksame name
- github/squad★ 3.4ksame name
- compozy/compozy★ 2.9ksame name
- SRombauts/SQLiteCpp★ 2.8ksame name
177 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audio-analysisSkill
- calendarSkill
- code-executionSkill
- connector-action-authorizationSkill
- core-memorySkill
- cost-reportSkill
- councilSkill
- crm-lookupSkill
- daily-briefingSkill
- delegationSkill
- email-digestSkill
- expense-captureSkill
- github-issuesSkill
- gmail-actionsSkill
- gmail-connector-setupSkill
- home-assistantSkill
- host-nodeSkill
- image-genSkill
- inbox-triageSkill
- integration-connector-setupSkill
- knowledge-ingestSkill
- meeting-follow-upSkill
- meeting-prepSkill
- memory-exchangeSkill
- notionSkill
- operationsSkill
- outreachSkill
- personal-notesSkill
- researchSkill
- self-inspectionSkill
- self-reflectionSkill
- skill-authoringSkill
- speechSkill
- spotifySkill
- travel-prepSkill
- trelloSkill
- twitter-x-actionsSkill
- twitter-x-connector-setupSkill
- weatherSkill
- weekly-reviewSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 14 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 174 edited versions we read keep these.
14
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When the user asks to "humanize" or "make this sound more natural" or "remove the AI voice"
- Distinctive: line 17
When drafting outgoing communications (emails, posts, messages) that should not read as AI-generated
- Distinctive: line 18
When editing content that will be published under the user's name
- Distinctive: line 19
When the user flags specific text as "sounding too AI"
- Distinctive: line 23
Analyze the input: Before rewriting, identify the specific AI patterns present.
- Distinctive: line 26
Exhaustive listing: Every possible angle covered with equal weight, nothing omitted or prioritized
- Distinctive: line 33
Determine the target voice: Ask or infer the desired tone.
- Distinctive: line 42
Cut the throat-clearing: Start sentences with the point, not a preamble.
- Distinctive: line 45
Use specific details: instead of generic descriptors.
- Distinctive: line 49
Review the output: Check that the rewrite preserved the original meaning and key information.
- Distinctive: line 54
Never add falsehoods or change factual claims during humanization.
- Distinctive: line 55
When the user's own writing samples exist in memory, use them as the gold standard for voice matching.
- Distinctive: line 56
If the input text is already natural-sounding, say so rather than rewriting for the sake of it.
- Distinctive: line 57
Do not over-correct. Some AI patterns (clear structure, logical flow) are also features of good writing.
“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Writing Pattern Detection and Removal
Analyze text for telltale AI-generated writing patterns and rewrite it to sound natural, varied, and human-authored.
When to Use
- When the user asks to "humanize" or "make this sound more natural" or "remove the AI voice"
- When drafting outgoing communications (emails, posts, messages) that should not read as AI-generated
- When editing content that will be published under the user's name
- When the user flags specific text as "sounding too AI"
Step-by-Step Methodology
- Analyze the input: Before rewriting, identify the specific AI patterns present. Common tells include:
- Hedging openers: "It's important to note that", "It's worth mentioning", "Interestingly"
- Formulaic structure: Intro paragraph, three body paragraphs, conclusion that restates the intro
- Exhaustive listing: Every possible angle covered with equal weight, nothing omitted or prioritized
- Sycophantic tone: "Great question!", "Absolutely!", "That's a fantastic point"
- Hollow intensifiers: "Incredibly", "Remarkably", "Fundamentally", "Essentially"
- Emoji and exclamation overuse: Forced enthusiasm that reads as performative
- Symmetrical phrasing: "Not only X, but also Y", parallel constructions repeated throughout
- Meta-commentary: "Let me break this down", "Here's the thing", "To put it simply"
- Determine the target voice: Ask or infer the desired tone. Options include:
- Casual conversational (texting a friend)
- Professional but warm (work email)
- Authoritative and concise (executive brief)
- The user's own voice (if prior writing samples exist in memory, match them)
- Rewrite with human patterns: Apply transformations that mimic natural writing:
- Vary sentence length dramatically. Mix 4-word fragments with 30-word run-ons. Real people do not write in uniform 15-word sentences.
- Use contractions and colloquialisms appropriate to the register.
- Cut the throat-clearing. Start sentences with the point, not a preamble.
- Allow imperfection. Occasional sentence fragments, starting with "And" or "But", ending with prepositions -- these are features of natural prose, not bugs.
- Prioritize ruthlessly. Real writers omit what does not matter. Drop the "comprehensive" instinct.
- Use specific details instead of generic descriptors. "The 3pm demo" not "the upcoming presentation."
- Call the tool: Pass the original text and target voice to
humanize_text, which applies rule-based pattern removal and optionally an LLM rewrite pass. - Review the output: Check that the rewrite preserved the original meaning and key information. Humanizing should change the voice, not the substance.
Quality Guidelines
- The goal is natural prose, not dumbed-down prose. Sophisticated vocabulary and complex ideas are fine; robotic cadence and formulaic structure are not.
- Never add falsehoods or change factual claims during humanization. This is a voice transformation, not a content edit.
- When the user's own writing samples exist in memory, use them as the gold standard for voice matching.
- If the input text is already natural-sounding, say so rather than rewriting for the sake of it.
- Do not over-correct. Some AI patterns (clear structure, logical flow) are also features of good writing. Remove the tells, keep the clarity.
- Respect the register. A legal brief should not sound like a blog post, and a casual message should not sound like a press release.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

