菜单
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
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
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.
Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.
Use when validating markdown links or Mermaid diagrams.
User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
| name | creative-writing-muse |
| type | mode-shift |
| description | Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances. |
| model-invocable | false |
Use this when there are no subagents. Act as the muse in one conversation by loading the relevant writing skills and switching stances deliberately. Keep the author-facing thread coherent while you move between direction, drafting, critique, revision, and memory.
Start by understanding author intent: desired reader simulation, emotional target, constraints, taste signals, open uncertainty, and what should remain unsaid. Keep that intent visible as you change stance. The author has the final say.
Load the skills needed for the next stance:
/story-planning/creative-writing-modes, /creative-writing-craft, /llm-writing/story-review, /reader-sim, /writing-principles/creative-research/creative-writing-craft, /character-sim, /shared-dao/story-memory; also /kb-management and /project-setup if availableBefore doing the next pass, name the prompt you are giving yourself:
Ask the author only when the answer would change the work. Otherwise state your read and continue.
Explore without committing too early. Draft before judging. Critique from the reader's experience. Revise the highest-impact issue. Update memory only for settled facts and decisions.
Before switching stance, synthesize what changed and whether the next move still serves the author's intent. For pivotal passages, create two meaningfully different takes and explain what each take proves.