agentleFS
shali10shali10/awesome-agent-skills/skills/human-voice-writing/SKILL.md

human-voice-writing

Skill1 starsChanged 3 months agoMITView on GitHub

Use when writing technical tutorials, engineering blogs, and articles that sound like a real person with technical depth rather than robotic AI prose.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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
  1. Distinctive:

    Over-polishing into corporate buzzwords: Keep the conversational, grounded tone of an experienced engineer explaining things over coffee.

    line 49
  2. Distinctive:

    Hiding critical config in prose: Always put paths, flags, and environment variables into distinct code blocks or Markdown tables.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Human Voice Technical Writing

Overview

A systematic writing methodology that eliminates synthetic "AI-isms" (filler phrases, robotic customer-service tone, repetitive conclusions) and produces technical content with authentic human voice, grounded engineering insights, and engaging rhythm.

When to Use & When NOT to Use

When to Use

  • Writing tech blog posts, tutorials, and architecture case studies.
  • Refining AI-generated drafts into natural, engaging prose.
  • Creating developer-focused changelogs, README showcases, and social posts.

When NOT to Use

  • Strict API documentation or JSON schema specs requiring purely mechanical descriptions.
  • Formal legal compliance disclosures or raw telemetry logging.

Core Writing Rules & Negative List

Category❌ Strict Negative List (Never Use)✅ Human Alternative (Use Instead)
AI Clichés"In today's fast-paced digital world...", "Delve into", "Tapestry"Start directly with the core problem or command
Robotic Openings"First and foremost...", "Let's embark on a journey...""Here is the exact setup that works in production:"
Empty Summaries"In conclusion...", "It is important to remember that..."End with a verification command, next step, or sharp tip
Fluff Transitions"Moreover, it is worth noting that...", "Furthermore..."Use clean bullet points or jump straight to the point

Structure of a Top-Tier Technical Post

  1. 🎯 The Hook & Core Goal (1-2 sentences: what we are building, without preamble).
  2. 💻 Production-Ready Code / Config Block (Full copy-pasteable configuration).
  3. 🔍 Step-by-Step Practical Walkthrough (Real commands with inline annotations).
  4. ⚠️ Pitfalls & Real Battle Scars (Actual bugs encountered and exact fixes).
  5. ✅ Grounded Verification (Exact command to confirm everything works).

Common Pitfalls

  1. Over-polishing into corporate buzzwords: Keep the conversational, grounded tone of an experienced engineer explaining things over coffee.
  2. Hiding critical config in prose: Always put paths, flags, and environment variables into distinct code blocks or Markdown tables.
  3. Omitting the verification step: A tutorial is incomplete without showing how to test and verify the final result.

Verification Checklist

  • Zero AI clichés (e.g. "delve", "testament", "tapestry", "furthermore") present.
  • No boilerplate introductory paragraph before the first heading.
  • All commands have been tested and include expected output.

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.