Docs Write — AI skill for Claude Code
ALWAYS run this skill when writing or reviewing anything under tomevault-web/content/docs/ (the practitioner reference surface) or briefings/ that ships externally.
How to install Docs Write
Installs to ~/.claude/skills/tomevault-io-companyos-docs-write/SKILL.md
mkdir -p ~/.claude/skills/tomevault-io-companyos-docs-write && curl -fsSL https://raw.githubusercontent.com/tomevault-io/companyos/HEAD/skills/docs-write.md -o ~/.claude/skills/tomevault-io-companyos-docs-write/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Docs Write does
name: docs-write description: ALWAYS run this skill when writing or reviewing anything under `tomevault-web/content/docs/` (the practitioner reference surface) or `briefings/*` that ships externally. Encodes the post-LLM 2026 voice discipline: bans em-dashes in reference pages, enforces sentence-case headings, kills AI scaffolding phrases, and prescribes a per-doc-type voice (reference is austere, explanation is opinionated, tutorial is task-shaped). Apply BEFORE writing, then again as a pre
Alternatives in AI
- Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
- Codeseek — Rust-powered code intelligence CLI for AI coding agents 764 ★
- Academic Writing Skills — AI-powered post-writing toolkit for academic papers — format validation, grammar/style polishing, de-AI editin 430 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code t
Stop Slop Skill
Remove AI writing patterns from prose. Use this skill whenever you are drafting, editing, reviewing, rewriting
Collidemcp
Run multiple AI coding agents (Claude Code, Codex, Cursor) on one repo without conflicts: live awareness, writ
Collide
Run multiple AI coding agents (Claude Code, Codex, Cursor) on one repo without conflicts: live awareness, writ
AI Articles
Reference patterns and implementation guides for using multiple AI agents (Hermes, Claude Code, Minimax M3, Op
Opencues
Turn any text field into a two-way LLM channel: it reads what you write and fills what you ask. Flags a slip a
Related Agents
Release Verifier
Builds, renders and exercises the site, then reports pass or fail. Holds a fact veto — nothing ships that does
Keshet
Personal assistant - emails, calendar, tasks, daily briefings, weekly reviews. Use for anything about Sivan's
Signature Historian
Drift / change / evolution tracker. Ships with CogSig for signature-drift detection across sessions + availabl