ops-humanizer

Featured

OPS on-demand: This skill should be used when the user asks to "humanize this", "this reads like…

AI & Automation 188 stars 22 forks Updated today MIT

Install

View on GitHub

Quality Score: 94/100

Stars 20%
76
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /ops:humanizer Load `ops-rules` before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If `AskUserQuestion` / `Workflow` are missing, follow Rule 10 in `ops-rules` (Hermes: numbered options / two-turn Telegram card; `delegate_task`). You are an editor. Your job is to take a draft that reads as machine-generated and make it read as if a person wrote it, without changing what it says. Two failure modes, equally bad. Leaving the tells in. And scrubbing so hard that the prose goes flat, or that a fact gets invented to fill the hole where a vague phrase used to be. ## The rules that outrank everything else 1. **Never invent.** No name, number, date, quote, source, or claim may appear in the rewrite that was not in the input or supplied by the owner. Trading a vague sentence for a specific one is only allowed when the specific came from somewhere real. If a sentence needs a fact you do not have, cut the sentence or write the plain version. A fabrication is a defect even when it reads better. (Fiction is the exception; there, invention is the assignment.) 2. **Keep the information, drop the shape.** Every claim survives. Paragraph structure, ordering, and length do not have to. Compress the padding, linger where a person would linger, merge or split freely. 3. **A supplied writing sample beats every rule below, including the em dash rule.** See Voice calibration. 4. **Rule 6 still applies.** If the text is an outboun...

Details

Author
Lifecycle-Innovations-Limited
Repository
Lifecycle-Innovations-Limited/claude-ops
Created
5 months ago
Last Updated
today
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

humanize-text-pro

Rewrite text so it reads as written by a person, with no AI tells, no invented facts, and no ambiguity. Use when the user asks to humanize, de-slop, naturalize, or clean up writing; asks whether a draft reads as AI; asks for a plain-language, disambiguating, or Simplified Technical English rewrite of a tool description, error message, system prompt, or agent instruction; or before drafting or sending any customer- or user-facing message (email, Slack or Teams message, support reply, release notes, public announcement, marketing copy). Also use when a draft needs to be sharper, more direct, or more opinionated while keeping the writer's own voice. Combines petergyang/no-ai-slop, blader/humanizer, and danyuchn/asd-ste100-skill into one non-conflicting ruleset.

0 Updated 4 days ago
sarrafgsarraf
AI & Automation Listed

humanizer

Rewrite or draft text so it reads like a human wrote it. Kills em dashes, robotic tone, AI-giveaway words, and formulaic structure. Use this skill whenever the user asks to humanize text, make writing sound natural or less like AI, remove the "ChatGPT voice", or complains that a draft sounds robotic, stiff, or generated. ALSO use it proactively whenever drafting content that will be read as the user's own words, including emails, LinkedIn posts, blog articles, essays, bios, cover letters, newsletters, website copy, and social posts. Do NOT use for code, legal contracts, academic citations, or technical reference docs where formality is required.

0 Updated 1 weeks ago
kshyam
AI & Automation Listed

humanize

Draft and rewrite prose in a human voice without machine-generated patterns.

26 Updated today
nikolanovoselec