一键导入
proofread
Check text against Swarm voice and style guidelines, flag violations, and optionally apply fixes
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Check text against Swarm voice and style guidelines, flag violations, and optionally apply fixes
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | proofread |
| description | Check text against Swarm voice and style guidelines, flag violations, and optionally apply fixes |
| allowed-tools | Read, Edit, AskUserQuestion |
| argument-hint | [text-or-filepath] |
Trigger: "Proofread: [text or file path]" or /proofread [text-or-file]
Purpose: Check writing against Swarm's voice and style guidelines, return a corrected version with the changes called out, and optionally apply the fixes to the original file.
Config keys used: None.
From the argument:
If the input is unclear or missing, ask. Don't proceed without real content.
Read style/Swarm-identity-guideline.md. It is the source of truth for voice, tone, and the non-negotiables — don't rely on a remembered list (per SKILL-STANDARD §1: discover, don't hardcode).
Run the text through every rule in the guideline. The current non-negotiables include — but always cross-check the file:
For each problem, capture: the exact phrase, which rule it violates, and the proposed fix.
Show the user:
Never fabricate corrections to make the text "punchier" — only flag real guideline violations.
If the input was a file, ask the user (AskUserQuestion): apply the corrections to the file now, or leave it?
If the input was inline text, skip this step.
If fixes were applied, re-read the file and check:
Report: number of changes made, number of items flagged but not auto-fixed.
If the text is already clean, say so plainly. A 0-changes report is a fine outcome.
style/Swarm-identity-guideline.md.