agent-doc-discipline
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and…
One layered standard for shipping prose — docs, RFCs, readmes, PR descriptions, commit messages: outcome first, one meaning one home, checkable statements, no filler. Composes with minimal-prose-discipline.
Claude Code
$ npx -y skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing --agent claude-code
Codex
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a codex -y
Cursor
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a cursor -y
Gemini CLI
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a gemini-cli -y
GitHub Copilot
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a github-copilot -y
OpenCode
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a opencode -y
Windsurf
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill technical-writing -a windsurf -y
name: technical-writing
description: "One layered standard for shipping prose — docs, RFCs, readmes, PR descriptions, commit messages: outcome first, one meaning one home, checkable statements, no filler. Composes with minimal-prose-discipline."
aliases: []
metadata:
credits:
layered-writing-standard: pstack
author: Lauren Tan
url: "https://github.com/cursor/plugins/tree/main/pstack"
port: pstack-claude
port-author: Michael Denyer
port-url: "https://github.com/michael-denyer/pstack-claude"Prose that ships — docs, RFCs, readmes, PR descriptions, commit messages — follows one standard so readers can navigate any of them the same way.
1. **Outcome first.** The first sentence says what changed for whom and what the reader can now do. Context comes after the reader knows why they care. 2. **One meaning, one home.** Each fact lives in exactly one place; every other mention links there. Duplicated facts rot at different speeds. 3. **Checkable statements.** Prefer a statement the reader can verify with a command or a glance over an adjective. "Builds in ~40s" beats "fast". 4. **Layered structure.** Summary, then detail, then edge cases — each layer readable alone, each deeper layer skippable. 5. **No filler.** No restating the obvious, no throat-clearing, no AI tells (`ai-slop-cleaner` territory; this skill composes with it).
says why, and the constraint that made the change necessary.
`pr` skill owns the full template.
everything else.
losers lost (feeds from `architect`), decision, migration.
these patterns.
(`principles` skill, Minimize reader load).
For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI. Liked OmC but found it a bit overkill? Try gajae-code.
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and…
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Settle types and module shape before cross-boundary code — competing designs explored in parallel, compared on API surface and…
Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical…
Run N parallel candidates at one brief and synthesize: rubric-first framing, isolated fan-out, a cross-judge on a different…
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration