New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Strips AI writing patterns from text

Notes humanizer

by mohitagw15856 · MIT license · ★ 1,395 on GitHub · updated Sep 23

Notes humanizer cover

Strips AI writing patterns from text and rewrites it to sound genuinely human — removing the statistical defaults, then adding earned voice calibrated to genre (opinion pieces get a person's voice; docs and summaries stay neutral)…

---
name: notes-humanizer
description: "Strips AI writing patterns from text and rewrites it to sound genuinely human — removing the statistical defaults, then adding earned voice calibrated to genre (opinion pieces get a person's voice; docs and summaries stay neutral) without ever faking humanity. Use when a draft reads as AI-generated, over-polished, or rhythmically uniform — including blog posts, emails, LinkedIn posts, or any prose that needs to sound like a real person wrote it. Produces a pattern audit, side-by-side comparison, itemised change log, and clean rewritten output ready to paste."
---

# Notes Humanizer

"Humanize this" prompts don't work because they don't know what to remove. AI text has specific, identifiable defaults — em dashes used as parenthetical substitutes, rule-of-three lists where all items have identical rhythm, sentences that hover between 15 and 20 words. Fix those defaults, add the signals human writers actually produce, and the text stops reading as synthetic. This skill does that systematically, in two phases, and shows you exactly what changed and why.

> Credit: Originally created by Orel (TheIndiepreneur) — adapted and extended for this library.

---

## Required Inputs

| Input | Format | Notes |
|---|---|---|
| Text to humanize | Paste directly into the chat | Any length. Works on paragraphs, full articles, social posts, emails. |

Overview

"Humanize this" prompts don't work because they don't know what to remove. AI text has specific, identifiable defaults — em dashes used as parenthetical substitutes, rule-of-three lists where all items have identical rhythm, sentences that hover between 15 and 20 words. Fix those defaults, add the signals human writers actually produce, and the text stops reading as synthetic. This skill does that systematically, in two phases, and shows you exactly what changed and why.

Manual install (npx, ZIP)
Claude Codenpx skills add mohitagw15856/pm-claude-skills --skill notes-humanizer -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/mohitagw15856/pm-claude-skills/tar.gz/f6ca79348c55 \ | tar -xz -C ~/.claude/skills --strip-components=2 pm-claude-skills-f6ca79348c55/skills/notes-humanizer
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/cf549218be0d4215a5b4/notes-humanizer.zip" -OutFile "$env:TEMP\notes-humanizer.zip"; Expand-Archive "$env:TEMP\notes-humanizer.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md11.4 KB
Read the files here
mohitagw15856/f6ca7931 file
SKILL.md
Show the full text190 lines

Notes Humanizer

"Humanize this" prompts don't work because they don't know what to remove. AI text has specific, identifiable defaults — em dashes used as parenthetical substitutes, rule-of-three lists where all items have identical rhythm, sentences that hover between 15 and 20 words. Fix those defaults, add the signals human writers actually produce, and the text stops reading as synthetic. This skill does that systematically, in two phases, and shows you exactly what changed and why.

Credit: Originally created by Orel (TheIndiepreneur) — adapted and extended for this library.


Required Inputs

Input Format Notes
Text to humanize Paste directly into the chat Any length. Works on paragraphs, full articles, social posts, emails.

No other inputs required. Claude will not ask clarifying questions before starting — it works with what's given.


Output Structure

Section 1: What Was Found

A plain-language audit of the AI patterns detected in the original text, before any rewriting:

PATTERNS DETECTED
─────────────────
Em dashes used as parenthetical substitutes: 3
Filler openers ("Let's dive in", "It's worth noting", etc.): 2
Rule-of-three lists with identical rhythm: 1
Sentence length variance: low (avg 17 words, range 14–21)
Hedging qualifiers: 4
Passive constructions where active is cleaner: 2
Section 2: Side-by-Side Comparison
Original Rewritten
[original paragraph] [rewritten paragraph]

(One row per paragraph or logical block. Short texts get the full comparison in one table. Long texts get the table collapsed to changed sections only, with unchanged sections noted.)

Section 3: Change Log

Every specific change made, with the reason:

CHANGES MADE
────────────────────────────────────────────────
1. Removed em dash in "success — and it shows"
   → Rewritten as "success (and it shows)"
   Why: em dash here is a parenthetical substitute, not a genuine pause

2. Deleted "It's worth noting that"
   Why: pure filler — the sentence is stronger without it

3. Broke rule-of-three list "X, Y, and Z"
   → "X and Y. Z is different — [expanded thought]"
   Why: all three items had identical rhythm; broke the pattern

4. Split a 30-word sentence where the point turned: "…and it failed. That's the problem."
   Why: the meaning lands on a short beat here — the brevity is earned, not inserted for variance

5. Added sentence starting with "But"
   Why: human writers do this; AI avoids it as a statistical default

6. Added specific example: [detail added]
   Why: the original made an abstract claim with no grounding detail

7. Added aside: "(I've watched this fail three times in a row)"
   Why: breaks fourth wall slightly; signals genuine perspective
Section 4: Clean Output

The full rewritten text, ready to copy and paste — no annotations, no formatting artifacts.

[Full rewritten text here]

Instructions for Claude

Phase 0: Calibrate to genre (do this first)

Before touching anything, decide what kind of text this is — the genre sets how far Phase 2 goes:

  • Neutral / informational (documentation, reference, summaries, status reports, official notices, most business comms): run Phase 1 only. Strip the tells and stop. Do not inject opinion, asides, or personality — a clean doc is the goal, not a voice. Injected "humanity" here reads as unprofessional.
  • Personal / persuasive / social (opinion pieces, blog posts, founder notes, LinkedIn, marketing, personal emails): run Phase 1 + Phase 2. Here earned voice is the point.
  • Unsure or mixed: default to the lighter touch (Phase 1, plus only the Phase 2 moves the content genuinely earns), and say which genre you assumed.

The single rule underneath: calibrate voice to the job of the text. Never dismantle useful structure (a scannable doc, a real list) just to look less templated.

Phase 1: Audit

Read the full text before making any changes. Identify and count every instance of these patterns:

Patterns to remove or rewrite:

Pattern Action
Em dash used as parenthetical substitute (word — word where a comma or parenthesis would work) Replace with parentheses or rewrite the clause
"Let's dive in" Delete or replace with a direct first sentence
"In conclusion" Delete or rewrite as a genuine closing thought
"It's worth noting that" Delete — the sentence stands without it
"At its core" Delete or rewrite
"Game-changer" Replace with what the thing actually changes
"Delve" Replace with look, dig, explore — or rewrite the sentence
"Navigate" used metaphorically for non-navigation tasks Replace with a direct verb
Rule-of-three lists where all three items have identical grammatical structure and similar word count Break the third item out as its own sentence or expand it
Sentences where every sentence in a paragraph falls in the 14–22 word range Deliberately add one very short sentence and one longer one
"Needless to say" Delete
"It's important to note that" Delete
Passive constructions where the active form is more direct Flip to active

Do not remove every em dash — only the ones used as parenthetical substitutes. Do not remove all hedging — only empty hedging that adds no information.

Phase 2: Inject (personal / persuasive genres only — see Phase 0)

Only for text where earned voice is the point. These are options the content earns, not a checklist to complete — apply the ones the material genuinely supports and skip any that would be forced. A move inserted to hit a quota is itself an AI tell. Never fake humanity: no invented typos, no forced slang, no staged messiness, and no chopping or padding sentences just to manufacture rhythm variance.

  1. A genuine opinion or take (if the author clearly holds one). State the belief the text already implies, without hedging. Don't manufacture an opinion the author never expressed.

  2. A specific detail or example (only if a real one exists). Ground the most abstract claim in something concrete the author actually knows. Never invent a number, quote, date, name, or fact to sound specific — that's fake specificity, a worse tell than vagueness. If no real detail is available, ask the author for one or keep the honest abstraction; do not fabricate.

  3. An aside that steps out of the formal argument (where it fits the register). The signal most synthetic text lacks — but only in genres that welcome it, and only when it connects to a real point. Forced or cutesy asides are worse than none.

  4. Let a sentence be short where the point lands on a short beat. Follow the meaning, not a word count. Never shorten a sentence just to add "variance."

  5. Start a sentence with "And" or "But" only where the rhythm truly earns it. If no place does, don't add one — a random "But" is a tell, not a fix.

Phase 3: Report

Present the output in the four-section structure defined above. The change log must list every individual change — not categories of change, but specific instances. If you changed three em dashes, list all three separately.

Handling edge cases
  • If the text is already mostly clean: Report what you found (or didn't find), make the few remaining changes, and note explicitly that the original was close. Don't invent problems.
  • If the text is very short (under 100 words): Skip the comparison table. Show original, then rewritten, then change log.
  • If the text is over 1,500 words: Process the full text but collapse the comparison table to changed sections only.

Quality Checks

  • Genre was assessed first (Phase 0); neutral/informational text got Phase 1 only, with no injected opinion, aside, or personality
  • Audit was completed before rewriting (patterns counted, not just detected)
  • Every removed pattern is listed in the change log with a specific reason
  • Em dashes were assessed individually — only parenthetical-substitute uses were removed
  • Rule-of-three lists: the rhythm was actually checked, not just the fact that there were three items
  • No fact, number, quote, date, or name was invented to add specificity
  • Any Phase 2 moves applied were earned by the content — none inserted to hit a quota (short sentence / "And"/"But" opener / aside added only where the material genuinely called for it, or not at all)
  • The specific detail or example added connects to an actual claim in the text, not floated in generically
  • The aside (if any) breaks the fourth wall slightly without being forced or cutesy
  • The change log lists specific instances, not categories
  • The clean output section has no annotations or formatting artifacts — ready to paste
  • If the original was already clean, that was stated explicitly rather than changes invented

Anti-Patterns

  • Do not fake humanity: no invented typos, no forced slang, no staged messiness, and no programmatic sentence-length variation added to hit a target — faked signals are themselves AI tells
  • Do not inject voice into neutral genres — documentation, summaries, reports, and official comms get the tells stripped and nothing added; personality there reads as unprofessional
  • Do not invent specificity — never add a number, quote, date, name, or fact that isn't real to make prose sound concrete; ask for the detail or keep the honest abstraction
  • Do not dismantle useful structure (a scannable layout, a genuine list) just to look less templated
  • Do not remove all em dashes — only the ones functioning as parenthetical substitutes should be removed; genuine dramatic pauses are valid
  • Do not invent problems to justify changes when the original is already clean — report what was found honestly, even if the answer is "this text is mostly fine"
  • Do not add the aside or opinion generically — the injected human signals must connect to an actual claim or argument in the text, not float in as decoration
  • Do not list changes by category in the change log — every individual change must be listed separately with the specific reason for that specific instance
  • Do not apply humanisation changes that alter the factual claims or intended meaning of the original text — the skill rewrites style, not substance

Example Trigger Phrases

  • "Humanize this text: [paste]"
  • "Use the notes-humanizer skill on this draft"
  • "This reads like ChatGPT wrote it — fix it: [paste]"
  • "Strip the AI out of this and make it sound like a real person wrote it"
  • "Run the humanizer on this LinkedIn post: [paste]"
  • "This has too many em dashes and rule-of-three lists — clean it up: [paste]"
  • "Make this email sound less robotic: [paste]"
1---
2name: notes-humanizer
3description: "Strips AI writing patterns from text and rewrites it to sound genuinely human — removing the statistical defaults, then adding earned voice calibrated to genre (opinion pieces get a person's voice; docs and summaries stay neutral) without ever faking humanity. Use when a draft reads as AI-generated, over-polished, or rhythmically uniform — including blog posts, emails, LinkedIn posts, or any prose that needs to sound like a real person wrote it. Produces a pattern audit, side-by-side comparison, itemised change log, and clean rewritten output ready to paste."
4---
5 
6# Notes Humanizer
7 
8"Humanize this" prompts don't work because they don't know what to remove. AI text has specific, identifiable defaults — em dashes used as parenthetical substitutes, rule-of-three lists where all items have identical rhythm, sentences that hover between 15 and 20 words. Fix those defaults, add the signals human writers actually produce, and the text stops reading as synthetic. This skill does that systematically, in two phases, and shows you exactly what changed and why.
9 
10> Credit: Originally created by Orel (TheIndiepreneur) — adapted and extended for this library.
11 
12---
13 
14## Required Inputs
15 
16| Input | Format | Notes |
17|---|---|---|
18| Text to humanize | Paste directly into the chat | Any length. Works on paragraphs, full articles, social posts, emails. |
19 
20No other inputs required. Claude will not ask clarifying questions before starting — it works with what's given.
21 
22---
23 
24## Output Structure
25 
26### Section 1: What Was Found
27 
28A plain-language audit of the AI patterns detected in the original text, before any rewriting:
29 
30```
31PATTERNS DETECTED
32─────────────────
33Em dashes used as parenthetical substitutes: 3
34Filler openers ("Let's dive in", "It's worth noting", etc.): 2
35Rule-of-three lists with identical rhythm: 1
36Sentence length variance: low (avg 17 words, range 14–21)
37Hedging qualifiers: 4
38Passive constructions where active is cleaner: 2
39```
40 
41### Section 2: Side-by-Side Comparison
42 
43| Original | Rewritten |
44|---|---|
45| [original paragraph] | [rewritten paragraph] |
46 
47(One row per paragraph or logical block. Short texts get the full comparison in one table. Long texts get the table collapsed to changed sections only, with unchanged sections noted.)
48 
49### Section 3: Change Log
50 
51Every specific change made, with the reason:
52 
53```
54CHANGES MADE
55────────────────────────────────────────────────
561. Removed em dash in "success — and it shows"
57 → Rewritten as "success (and it shows)"
58 Why: em dash here is a parenthetical substitute, not a genuine pause
59 
602. Deleted "It's worth noting that"
61 Why: pure filler — the sentence is stronger without it
62 
633. Broke rule-of-three list "X, Y, and Z"
64 → "X and Y. Z is different — [expanded thought]"
65 Why: all three items had identical rhythm; broke the pattern
66 
674. Split a 30-word sentence where the point turned: "…and it failed. That's the problem."
68 Why: the meaning lands on a short beat here — the brevity is earned, not inserted for variance
69 
705. Added sentence starting with "But"
71 Why: human writers do this; AI avoids it as a statistical default
72 
736. Added specific example: [detail added]
74 Why: the original made an abstract claim with no grounding detail
75 
767. Added aside: "(I've watched this fail three times in a row)"
77 Why: breaks fourth wall slightly; signals genuine perspective
78```
79 
80### Section 4: Clean Output
81 
82The full rewritten text, ready to copy and paste — no annotations, no formatting artifacts.
83 
84```
85[Full rewritten text here]
86```
87 
88---
89 
90## Instructions for Claude
91 
92### Phase 0: Calibrate to genre (do this first)
93 
94Before touching anything, decide what kind of text this is — the genre sets how far Phase 2 goes:
95 
96- **Neutral / informational** (documentation, reference, summaries, status reports, official notices, most business comms): run **Phase 1 only**. Strip the tells and stop. Do **not** inject opinion, asides, or personality — a clean doc is the goal, not a voice. Injected "humanity" here reads as unprofessional.
97- **Personal / persuasive / social** (opinion pieces, blog posts, founder notes, LinkedIn, marketing, personal emails): run **Phase 1 + Phase 2**. Here earned voice is the point.
98- **Unsure or mixed:** default to the lighter touch (Phase 1, plus only the Phase 2 moves the content genuinely earns), and say which genre you assumed.
99 
100The single rule underneath: **calibrate voice to the job of the text.** Never dismantle useful structure (a scannable doc, a real list) just to look less templated.
101 
102### Phase 1: Audit
103 
104Read the full text before making any changes. Identify and count every instance of these patterns:
105 
106**Patterns to remove or rewrite:**
107 
108| Pattern | Action |
109|---|---|
110| Em dash used as parenthetical substitute (`word — word` where a comma or parenthesis would work) | Replace with parentheses or rewrite the clause |
111| "Let's dive in" | Delete or replace with a direct first sentence |
112| "In conclusion" | Delete or rewrite as a genuine closing thought |
113| "It's worth noting that" | Delete — the sentence stands without it |
114| "At its core" | Delete or rewrite |
115| "Game-changer" | Replace with what the thing actually changes |
116| "Delve" | Replace with look, dig, explore — or rewrite the sentence |
117| "Navigate" used metaphorically for non-navigation tasks | Replace with a direct verb |
118| Rule-of-three lists where all three items have identical grammatical structure and similar word count | Break the third item out as its own sentence or expand it |
119| Sentences where every sentence in a paragraph falls in the 14–22 word range | Deliberately add one very short sentence and one longer one |
120| "Needless to say" | Delete |
121| "It's important to note that" | Delete |
122| Passive constructions where the active form is more direct | Flip to active |
123 
124Do not remove every em dash — only the ones used as parenthetical substitutes. Do not remove all hedging — only empty hedging that adds no information.
125 
126### Phase 2: Inject (personal / persuasive genres only — see Phase 0)
127 
128Only for text where earned voice is the point. These are **options the content earns, not a checklist to complete** — apply the ones the material genuinely supports and **skip any that would be forced**. A move inserted to hit a quota is itself an AI tell. Never fake humanity: no invented typos, no forced slang, no staged messiness, and no chopping or padding sentences just to manufacture rhythm variance.
129 
1301. **A genuine opinion or take** *(if the author clearly holds one).* State the belief the text already implies, without hedging. Don't manufacture an opinion the author never expressed.
131 
1322. **A specific detail or example** *(only if a real one exists).* Ground the most abstract claim in something concrete the author actually knows. **Never invent a number, quote, date, name, or fact to sound specific** — that's fake specificity, a worse tell than vagueness. If no real detail is available, ask the author for one or keep the honest abstraction; do not fabricate.
133 
1343. **An aside that steps out of the formal argument** *(where it fits the register).* The signal most synthetic text lacks — but only in genres that welcome it, and only when it connects to a real point. Forced or cutesy asides are worse than none.
135 
1364. **Let a sentence be short where the point lands on a short beat.** Follow the meaning, not a word count. Never shorten a sentence just to add "variance."
137 
1385. **Start a sentence with "And" or "But" only where the rhythm truly earns it.** If no place does, don't add one — a random "But" is a tell, not a fix.
139 
140### Phase 3: Report
141 
142Present the output in the four-section structure defined above. The change log must list every individual change — not categories of change, but specific instances. If you changed three em dashes, list all three separately.
143 
144### Handling edge cases
145 
146- **If the text is already mostly clean:** Report what you found (or didn't find), make the few remaining changes, and note explicitly that the original was close. Don't invent problems.
147- **If the text is very short (under 100 words):** Skip the comparison table. Show original, then rewritten, then change log.
148- **If the text is over 1,500 words:** Process the full text but collapse the comparison table to changed sections only.
149 
150---
151 
152## Quality Checks
153 
154- [ ] Genre was assessed first (Phase 0); neutral/informational text got Phase 1 only, with no injected opinion, aside, or personality
155- [ ] Audit was completed before rewriting (patterns counted, not just detected)
156- [ ] Every removed pattern is listed in the change log with a specific reason
157- [ ] Em dashes were assessed individually — only parenthetical-substitute uses were removed
158- [ ] Rule-of-three lists: the rhythm was actually checked, not just the fact that there were three items
159- [ ] No fact, number, quote, date, or name was invented to add specificity
160- [ ] Any Phase 2 moves applied were earned by the content — none inserted to hit a quota (short sentence / "And"/"But" opener / aside added only where the material genuinely called for it, or not at all)
161- [ ] The specific detail or example added connects to an actual claim in the text, not floated in generically
162- [ ] The aside (if any) breaks the fourth wall slightly without being forced or cutesy
163- [ ] The change log lists specific instances, not categories
164- [ ] The clean output section has no annotations or formatting artifacts — ready to paste
165- [ ] If the original was already clean, that was stated explicitly rather than changes invented
166 
167## Anti-Patterns
168 
169- [ ] Do not fake humanity: no invented typos, no forced slang, no staged messiness, and no programmatic sentence-length variation added to hit a target — faked signals are themselves AI tells
170- [ ] Do not inject voice into neutral genres — documentation, summaries, reports, and official comms get the tells stripped and nothing added; personality there reads as unprofessional
171- [ ] Do not invent specificity — never add a number, quote, date, name, or fact that isn't real to make prose sound concrete; ask for the detail or keep the honest abstraction
172- [ ] Do not dismantle useful structure (a scannable layout, a genuine list) just to look less templated
173- [ ] Do not remove all em dashes — only the ones functioning as parenthetical substitutes should be removed; genuine dramatic pauses are valid
174- [ ] Do not invent problems to justify changes when the original is already clean — report what was found honestly, even if the answer is "this text is mostly fine"
175- [ ] Do not add the aside or opinion generically — the injected human signals must connect to an actual claim or argument in the text, not float in as decoration
176- [ ] Do not list changes by category in the change log — every individual change must be listed separately with the specific reason for that specific instance
177- [ ] Do not apply humanisation changes that alter the factual claims or intended meaning of the original text — the skill rewrites style, not substance
178 
179---
180 
181## Example Trigger Phrases
182 
183- "Humanize this text: [paste]"
184- "Use the notes-humanizer skill on this draft"
185- "This reads like ChatGPT wrote it — fix it: [paste]"
186- "Strip the AI out of this and make it sound like a real person wrote it"
187- "Run the humanizer on this LinkedIn post: [paste]"
188- "This has too many em dashes and rule-of-three lists — clean it up: [paste]"
189- "Make this email sound less robotic: [paste]"
190 
View all files on GitHub →

Details

Updated
Sep 23, 2026
License
MIT
Stars on the repo
★ 1,395
Checked
Source
mohitagw15856/pm-claude-skills ↗
Creator
mohitagw15856 · 193 listings
View creator

Made with notes-humanizer

Notes humanizer — Galaxy 3D — fly through all 1170 skills as a glowing constellation you orbit and click into (from the mohitagw15856/pm-claude-skills README)
Notes humanizer — Galaxy 3D — fly through all 1170 skills as a glowing constellation you orbit and click into (from the mohitagw15856/pm-claude-skills README)

by mohitagw15856

Notes humanizer — PM Skills Wrapped — your practice turned into a shareable, Spotify-Wrapped-style story (from the mohitagw15856/pm-claude-skills README)
Notes humanizer — PM Skills Wrapped — your practice turned into a shareable, Spotify-Wrapped-style story (from the mohitagw15856/pm-claude-skills README)

by mohitagw15856

Similar skills

See all →
SkillRewrite AI-sounding text so it reads like the writerhumanizerblader/humanizer · by bladerRewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing.★ 53.6k GitHub starsSkillRemove AI writing patterns from proseStop slophardikpandya/stop-slop · by hardikpandyaRemove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.★ 17.8k GitHub starsSkillEdit drafts into sharperNo AI sloppetergyang/no-ai-slop · by petergyangEdit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.★ 12k GitHub starsSkillDetect, scan, audit, scoreAI writing detectorconorbronsdon/avoid-ai-writing · by conorbronsdonUse when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.★ 4.7k GitHub starsSkillAudit and rewrite content to remove AI writing patternsAvoid AI Writing — Audit & Rewriteconorbronsdon/avoid-ai-writing · by conorbronsdonAudit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.★ 4.7k GitHub starsSkillMake AI-generated writing read as human-writtenSepia — de-AI writingNanako0129/sepia · by Nanako0129Make AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-review comments, incident postmortems, tickets, work orders, technical articles, blog posts, and long-form journalism. Four operations - write, review (diagnose AI tells without editing), refactor (minimal in-place edits), recreate (full rewrite). Use when asked to humanize, de-AI, unslop, or strip AI flavor from any text; when writing or revising any of these document types; or whenever output must not read as machine-written.★ 3.1k GitHub stars

More from mohitagw15856

SkillDesign a 360-degree feedback survey or write a structured360-Degree Feedback Template Skillmohitagw15856/pm-claude-skills · by mohitagw15856Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.★ 1.4k GitHub starsSkillDesign statistically rigorous A/B tests for product featuresA/B Test Planner Skillmohitagw15856/pm-claude-skills · by mohitagw15856Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.★ 1.4k GitHub starsSkillGenerate a WCAG 2.2 accessibility audit checklistAccessibility Audit Skillmohitagw15856/pm-claude-skills · by mohitagw15856Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.★ 1.4k GitHub starsSkillBuild a structured account plan for any key customerAccount Plan Skillmohitagw15856/pm-claude-skills · by mohitagw15856Build a structured account plan for any key customer or target account. Use when asked to create an account plan, key account strategy, strategic account review, or territory plan. Produces a complete account plan with relationship map, growth opportunities, risks, and 90-day action plan.★ 1.4k GitHub starsSkillOptimize an article for Answer Engine Optimization so AIAEO Optimizer Skillmohitagw15856/pm-claude-skills · by mohitagw15856Optimize an article for Answer Engine Optimization (AEO) so AI engines like ChatGPT, Perplexity, and Claude can extract, quote, and cite it. Use when asked to AEO-optimize, make content AI-readable, improve AI citation chances, or adapt an article for answer engines. Produces an AEO-optimised rewrite with question headings, 50–80 word answer capsules, a paragraph-length audit, and flagged trust signals.★ 1.4k GitHub starsSkillConduct a structured ethical review of an AI or ML featureAI Ethics Review Skillmohitagw15856/pm-claude-skills · by mohitagw15856Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.★ 1.4k GitHub stars