From haowjy-creative-writing-skills
Staffs agent teams for writing workflows: spawns agents, counts, focus areas, effort scaling. For critic panels, researchers, draft/revise loops, brainstorm fan-outs.
npx claudepluginhub haowjy/creative-writing-skills --plugin creative-writing-skillsThis skill uses the workspace's default tool permissions.
Compose the right team for each writing task. The goal is coverage across perspectives — critics with different focus areas, researchers with different scopes, brainstormers exploring different angles — not redundant passes from the same angle.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Compose the right team for each writing task. The goal is coverage across perspectives — critics with different focus areas, researchers with different scopes, brainstormers exploring different angles — not redundant passes from the same angle.
Delegation is mandatory for orchestrators. An orchestrator's value is coordination and judgment, not solo execution. Orchestrators never write prose, draft outlines, or edit wiki pages directly — not even for small fixes. Writing your own drafts bypasses the critique and revision lanes that catch what the writer can't see in their own work. If no team composition was provided by your caller, compose one yourself before starting — use the catalogs in the resources below.
Review convergence. Critic loops run until convergence (no new substantive findings), not a fixed number of passes. The orchestrator can stop early, but must log the reasoning in the decision log so future agents understand what was decided and why.
Brainstorm diversity over brainstorm volume. Three brainstormers exploring different angles beats five exploring the same angle. Creative diversity comes from different perspectives, not more of the same perspective.
Style creation vs style evaluation are separate roles. The style-creator produces style reference files from sample chapters or author requirements. It does not evaluate prose against those styles. Style evaluation — checking whether a draft maintains the project's voice, detecting voice drift, flagging register breaks — is the critic agent with a voice focus. If you need new style files, spawn the style-creator. If you need to check whether a draft matches the style, spawn a critic with voice focus.
Effort scaling applies mainly to critics — the role that fans out within a draft/revise cycle. Writers don't scale within a phase (one writer per scene/chapter; split the brief if it's too big).
For critics, scale to the stakes and complexity of the content:
Think about what depends on what:
See resources for detailed catalogs of available agents and when to use each:
resources/critics.md when composing critique panels — covers critic focus areas and the continuity-checker specialist.resources/researchers.md when dispatching research — covers research focus areas and when web search is warranted.resources/builders.md when staffing writing, outlining, or wiki work — covers writer, outliner, and wiki-editor.resources/knowledge.md when triggering knowledge maintenance — covers session-miner, chronicler, and graph-maintainer.resources/character-sim.md when setting up character exploration — covers character-sim dispatch and multi-character fan-out patterns. Read it alongside resources/reader-sim.md when a workflow also needs experiential reader-response data on a draft.