From techdocs-authoring
Use when writing, structuring, or reviewing any README, how-to, tutorial, reference, ADR, runbook, release notes, or AI-agent-readable docs. Reference knowledge and an authoring playbook for technical documentation: picking a canonical style guide, the Diataxis four-mode model (tutorial/how-to/ reference/explanation), copy-paste templates and reviewer checklists, single-sourcing and content reuse, a writing process that leads with the bottom line, and writing docs that serve both humans and AI agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/techdocs-authoring:authoring-referenceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Reference and playbook for writing and reviewing technical documentation. This
Reference and playbook for writing and reviewing technical documentation. This file is the index; load a reference file only when a task needs it (progressive disclosure).
These are the canonical rules. Other files and the technical-writer agent
reference this list rather than restating it.
-v2, -new, -legacy).This skill carries portable writing craft. Your repository owns its enforcement — line-length limits (e.g. an MD013 character cap), numbered- heading validation, diagram linting, pre-commit / CI lint wiring, and the actual repo paths. Follow your repo's enforced limits where they exist; this skill defers the numbers and the tooling to it and never restates them. Where a mechanical rule here overlaps a craft principle your repo already adopted (Strunk-style economy, a grade-9 readability target, single-source-of-truth), treat them as the same shared baseline, not competing rulesets.
Starting or reviewing a doc:
pre-commit, markdownlint,
or vale) to catch line-length and other findings, then confirm the reader
can complete the task, every link resolves, and the page holds exactly one
mode.npx claudepluginhub pkloehn1/techdocs-authoring --plugin techdocs-authoringProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.