메뉴
Apply Strunk's writing rules to prose—documentation, commits, error messages, UI text. Clearer, stronger, more professional.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | prose |
| description | Apply Strunk's writing rules to prose—documentation, commits, error messages, UI text. Clearer, stronger, more professional. |
William Strunk Jr.'s The Elements of Style (1918) teaches you to write clearly and cut ruthlessly.
WARNING: elements-of-style.md consumes ~12,000 tokens. Read it only when writing or editing prose.
Use this skill whenever you write prose for humans:
If you're writing sentences for a human to read, use this skill.
When context is tight:
elements-of-style.mdAlphabetical reference for usage questions
Writing for humans? Read elements-of-style.md and apply the rules. Low on tokens? Dispatch a subagent to copyedit with the guide.
Product interrogation before commitment. Challenges whether you're solving the right problem for the right user at the right time. Use when starting a feature, exploring an idea, or before writing a spec. Triggers: "should I build this", "office hours", "is this worth building", "product check", "challenge this idea".
Find-fix-verify-regress loop for web apps using Chrome MCP. Use when asked to "qa this", "test the app", "find bugs", "does this work in the browser", "check the UI", "smoke test". Navigates the app, finds bugs, fixes code, verifies fixes, writes regression tests.
Trace how a change in one orchestration stack project (Ralph, Flow, Bach) affects the others. Invoke when editing contract-adjacent code — signal handling, state.json writes, task envelopes, worker dispatch, or iteration logic.
This skill should be used when the user asks to "research X", "investigate Y", "look into Z", "find out about", "what are the options for", "compare X vs Y", "how does X work", or requests technical investigation of libraries, APIs, frameworks, or architectural approaches.
Framework for code review that captures context future maintainers need—concerns raised, alternatives rejected, risks accepted. Use for PRs, local changes, or architecture review when the decision matters more than the diff. Produces structured feedback with must-address issues, suggestions, and observations "for the record."