haowjy

What fiction readers want (reader reward channels) and the specific ways LLM training damages them. Load when drafting prose, critiquing, or diagnosing why a passage feels flat.

Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique. Load when a writer, critic, or muse needs how-to-write guidance rather than a production mode.

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.

Dispatch reference for composing writing teams. Teaches which extra skills to attach, which files to pass, which resources to reference, and when to fan out versus run parallel lanes. Load when staffing a workflow.

Review work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.

Planning work before prose: creative direction, story-planning, outlining, and story architecture. Load when deciding what should happen or how a story should be structured.

Read as a specified first-time reader persona and report the felt experience. Use for skill-only workflows when a draft needs persona-bound reader-response signal instead of analytical critique.

One-time project setup for creative writing: interview the author about the project, writing samples, and voice, then create the AGENTS.md, kb/ layout, and style files every writing agent reads. User-invoked; run it once when starting a project.

Speak as a specified character from their current knowledge, voice, and emotional state. Use for skill-only workflows that need in-character conversation, voice discovery, or relationship pressure tests.

Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.

Maintaining the story knowledge base: creating, updating, and organizing wiki-style reference pages in kb/. Use when capturing finalized story knowledge, updating character profiles, documenting world mechanics, or restructuring the kb.

Creative-writing domain knowledge for durable story state. Load when preserving or retrieving project memory — fact extraction, context scoping, reference writing, artifact layout, and issue tracking. If you are a knowledge agent such as kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.

Use before acting on human instructions: separate what they said from what they meant.

Use when establishing shared vocabulary: resolve terminology early, one name per concept, vocab files as record.

Use when grilling should be grounded primarily in project artifacts. Loads /grill, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.

Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.

Prose-level immersion patterns: psychic distance, free indirect discourse, rhythm, sensory grounding. Use when writing or revising narrative prose.

Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.

Arc structure, narrative design, and pacing at multiple scales: saga, arc, chapter, scene. Use when structuring story at any level, planning arcs, designing chapter outlines, or evaluating whether narrative structure serves the story's goals.