output-style-selector
Automatically choose the best output style (tables, bullets, YAML, HTML, concise) to improve scanability and save tokens
Profile →npx skills add majiayu000/claude-skill-registry --skill output-style-selector --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Output Style Selector ## Purpose Select a response style that maximizes readability and minimizes back-and-forth. ## Behavior 1. Infer intent from prompt keywords and task type. 2. Choose one of: table-based, bullet-points, yaml-structured, html-structured, genui, ultra-concise, markdown-focused. 3. Emit a short “Style Block” (1–2 lines) describing the chosen style. 4. Respect overrides: `[style: <name>]` or `[style: off]`. ## Guardrails - Only inject when helpful; avoid long style instructions. - Keep the Style Block compact. ## Integration - `UserPromptSubmit` and sub-agent prompts (documentation, reviewer, PM). ## Example Style Block > Style: Table Based. Use a summary paragraph and then tables for comparisons and actions.
- Purpose
- Behavior
- Guardrails
- Integration
- Example Style Block
What does the output-style-selector skill do?
Automatically choose the best output style (tables, bullets, YAML, HTML, concise) to improve scanability and save tokens
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill output-style-selector --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.