agentleFS
EmzyjepppEmzyjeppp/devflow-rules/skills/humanize-writing/SKILL.md

humanize-writing

Skill0 starsChanged 43 days agoMITView on GitHub

Natural, direct, and non-artificial writing guidelines (Humanize Pro) for technical documentation, UI copy, and engineering communication.

18 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Fact-Driven Content: Never invent fake metrics, names, or testimonials to sound relatable.

    line 13
  2. Distinctive:

    Natural and Direct Voice: Use active voice and common professional vocabulary.

    line 14
  3. Very specific:

    Avoid Em Dashes: Do not use em dashes (—). Use commas, periods, colons, or parentheses.

    line 15
  4. Distinctive:

    UI Copy & Labels: Use concise, action-driven verbs ("Save changes", "Delete account", "Invalid password").

    line 31
  5. Distinctive:

    Technical Guides: Use direct step-by-step instructions with clear expected outcomes.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 11 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Humanize Writing

This skill guides the composition of natural, concise, and substance-focused writing, eliminating AI clichés and synthetic phrasing while preserving strict technical accuracy.

Core Principles

  1. Lead with Value: Begin with the primary message immediately. Remove greeting pleasantries ("Sure, I would be happy to help...") and formulaic concluding summaries.
  2. Fact-Driven Content: Never invent fake metrics, names, or testimonials to sound relatable.
  3. Natural and Direct Voice: Use active voice and common professional vocabulary.
  4. Avoid Em Dashes: Do not use em dashes (—). Use commas, periods, colons, or parentheses.
  5. Contextual Alignment: Adapt voice and density to the medium (UI copy, technical documentation, or architectural records).

Patterns to Avoid

For a full list of artificial writing patterns and clichés, see references/ai-tells.md.

Key patterns to eliminate:

  • Cliché phrases such as "solid foundation", "paving the way", "revolutionize", "in this fast-paced digital era", "in conclusion".
  • Monotonous paragraph structures and forced three-item lists.
  • Automatic praise and unsupported superlatives.

Channel-Specific Guidance

For in-depth channel guidelines, consult references/channels.md.

  • UI Copy & Labels: Use concise, action-driven verbs ("Save changes", "Delete account", "Invalid password").
  • Technical Guides: Use direct step-by-step instructions with clear expected outcomes.
  • Release Notes / Changelogs: State factual changes and operational impacts directly.

Copy Editing Examples

Artificial / Stiff CopyNatural and Direct Copy
Through this feature, users are empowered to comprehensively manage and configure profile details.Update your profile settings in account preferences.
An unexpected issue has occurred during the transaction processing sequence. Please consider retrying later.Transaction failed. Please try again.
This critical step is paramount to ensure the system operates at peak performance without potential pitfalls.Run database migrations before starting the server.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.