← ClaudeAtlas

output-style-engineeringlisted

Design and maintain Claude Code output styles: choosing the mechanism, setting the frontmatter, and writing the role, voice, and rules the style installs in the system prompt.
xobotyi/cc-foundry · ★ 23 · AI & Automation · score 84
Install: claude install-skill xobotyi/cc-foundry
**An output style modifies the system prompt.** It holds two powers no alternative has: it turns part of the default prompt off, and the harness reinforces it with adherence reminders through the conversation. Every other file-based mechanism only adds text, and then competes with the default it could not remove. <prerequisite> An output style is a system prompt. Invoke `prompt-engineering` for the wording, instruction budget, and timelessness rules that govern every line written here. This skill covers only what is specific to the output-style artifact — the mechanism choice, the frontmatter, and the register the style installs. </prerequisite> ## Choose the mechanism first - **Use a style when the role or the register must change and hold for a whole session.** The body lives in the system prompt, so it survives compaction, and the harness reminders carry adherence without persistence prose in the body. - **Additive mechanisms stay additive.** CLAUDE.md arrives as a user message after the system prompt, and `--append-system-prompt` appends for one session; neither removes the default the body is arguing with. A body that would work identically as CLAUDE.md content is not a style. - **Route the rest away.** A rule that must never break belongs in a hook — prose steers, the lifecycle mechanism enforces. A procedure a user invokes belongs in a skill. Work that needs an isolated context belongs in a subagent: a style governs the main conversation only, and a subage