Plain Technical Writing Skill — AI skill for Claude Code
Claude Skill: plain technical writing an expert reader can find, understand, and use — ISO 24495-1 reader model, Diataxis genre separation, answer-first structure, ASD-STE100 strict mode for procedure.
How to install Plain Technical Writing Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open leegonzales/plain-technical-writing-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Plain Technical Writing Skill does
Claude Skill: plain technical writing an expert reader can find, understand, and use — ISO 24495-1 reader model, Diataxis genre separation, answer-first structure, ASD-STE100 strict mode for procedures and agent-facing text
Alternatives in AI
- Anthropic Quickstarts — by Anthropic - Offers comprehensive development guides for three distinct AI-powered demo projects with standa 15.4k ★
- Wiki Query — Query the LLM Wiki and synthesize an answer 2.3k ★
- Claude Hub — by Claude Did This - A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered c 393 ★
README
Plain Technical Writing
**Version 1.0.2** | [Changelog](CHANGELOG.md)
Write reports, docs, specs, runbooks, and error text that an expert reader can find, understand, and use. Applies ISO 24495-1 plain-language principles with an explicit reader model, Diataxis genre separation, answer-first structure, and ASD-STE100 Simplified Technical English for procedures and agent-facing text.
What it fixes
Dense technical writing usually fails for one of three reasons, and each needs a different repair: the wrong genre (explanation smuggled into a reference), the wrong reader model (terms the reader doesn't hold, or over-gloss on terms they own), or the wrong mechanics (long sentences, dead verbs, one thing under three names). Most rewrites reach straight for mechanics — the least common cause. This skill diagnoses before rewriting.
Use cases
- Technical reports, README files, design docs, architecture write-ups
- PR descriptions, release notes, decision memos, status updates
- Runbooks, SOPs, error messages, tool descriptions, agent-to-agent instructions
- TRDs and other requirement specs — the answer-first + reader-model steps make requirements testable, not just shorter
- Rewriting existing text a reader called confusing, jargon-heavy, or dense
Not a fit: essays, marketing copy, or creative work where voice is the point.
How it works
- Name the reader — one line: who, what they hold, what they want, what they'll do after reading
- Declare the information type — Reference / How-to / Tutorial / Explanation / Decision memo / Troubleshooting — and write only that type
- Put the answer first — conclusion or recommendation opens the document and every section in it
- Choose the mode — Strict STE (
references/ste-strict.md) for procedures and agent-facing text; Plain-SME (references/mechanics.md) for reports, design docs, and explanations - Audit before shipping — a 10-item checklist (sentence length, passive voice, nominalizations,
Related Skills
Quantum Reading Skill
Read Less, Understand More - Lightweight intelligent text reader for AI agents with 30%+ token optimization
Sourcelens
Harness-based Agentic RAG: search, understand, and answer questions over documents and code using an AI coding
Analyze Footage
Analyze existing video files using TwelveLabs AI. Understand what's in your footage — find specific scenes, de
Vibe Explain
Cognitive debt map for AI-generated code. Surfaces opaque blocks you don't fully own or understand, generates
AI Translate
Markdown file translation. Technical/content translation via the Claude API (without breaking markdown structu
Plan Mode Arken
Create detailed technical implementation plans for Arken AI development. Ask clarifying questions one at a tim
Related Agents
Niche Hunter
Find 3 KDP niches with high demand and low competition, with sales evidence. Returns candidate niches across f
Wikiskill Grader
Strict LLM-judge grader — given a task's success criteria and an inference agent's transcript/final answer, re
Impl Architecture
Reviews implementation plans from a software architecture perspective. Use when evaluating module structure, s