Use when creating a full or partial set of genre wrapper skills under a genre directory. Builds `.github/skills/` subfolders and `SKILL.md` skeletons for a specified genre, keeps the `题材名-能力名` naming rule, and writes hard requirements that each genre skill must load and use its corresponding common skill when that common skill already exists.
npx skills add https://github.com/lornshrimp/Lorn.NovelWriteSkills --skill create-genre-skill-skeletons
<!-- ===== Layer 1: 永久缓存 ===== -->
根据指定题材,在该题材目录下批量建立标准题材 Skill 的目录与 SKILL.md 骨架。
这个 Skill 的目标不是直接写厚内容,而是先把题材目录下的 Skill 入口层 / 包装层 / 路由层 批量立起来,并把“必须加载并使用对应通用 Skill”的硬要求写进每个骨架里。
<!-- ===== Layer 3: 场景缓存 ===== -->
以下所列 references 文件必须通过 read_file 工具逐文件读取,不得因"已有相关知识"、"之前执行时已读过"、"该文件只是参考"为理由跳过任何一条。 每条 references 按其标注的必读等级强制执行:
reference_missing_{refName},不得静默跳过。references/standard-genre-skill-list.md — 标准题材 Skill 清单,决定本次是建全量还是子集references/genre-skill-skeleton-template.md — Skill 骨架模板,每个入口骨架的正文结构依据以下文件用于输出平台 Prompt → Skill 的无损迁移场景。仅当本次任务涉及补建或修复输出类 Skill 骨架时才需读取:
references/all-13-platform-section-recovery-mapping.md — 13 个输出平台的分节级补救映射总图references/dual-genre-output-platform-migration-ledger.md — 双题材(异能志怪 / 都市悬疑)输出平台迁移总台账references/output-platform-lossless-mapping-ledger-template.md — 输出平台 Skill 无损迁移台账模板(迁移新平台时参考)references/output-platform-migration-audit-checklist.md — 输出平台迁移审计检查清单(完工后审计用)references/pilot-shared-platform-lossless-mapping-ledger.md — 首批共享平台(番茄 / 知乎 / WebNovel)迁移状态台账,供参考references/pilot-shared-platform-section-mapping.md — 首批共享平台分节级无损映射施工图,供参考references/section-ledgers/ — 目录内含各平台的分节级台账文件(番茄.md、知乎.md、起点中文网.md 等 13 个平台),可按目标平台名读取对应文件.github/skills/ 骨架.github/skills/ 目录。references/standard-genre-skill-list.md,确定本次是创建全量清单,还是只创建一个子集。题材名- + 能力名”的命名规则创建目录。SKILL.md 骨架,至少包含:references/ 占位目录,供后续补入题材专属规则、检查清单、模板与增补说明。10. 若本次任务同时要求补题材 Prompt 入口,且目标题材目录已经采用“薄 Prompt 入口 + 题材 Skill 路由”模式,则在 Skill 骨架完成后,同步补建对应 .github/prompts/*.prompt.md;Prompt 必须只路由到题材 Skill,不得直接引用通用 Skill。
11. 复核命名、frontmatter、references/ 占位目录、一致性与通用 Skill 路由要求;若本次也补了 Prompt 入口,还要复核 Prompt → 题材 Skill → 通用 Skill 的链路是否成立。
通用- 替换为 题材名- 得到。name 与一级标题应保持一致。必须加载、必须调用、组合调用 等强约束表述。通用-生成章节控制卡 与 通用-管理连续性冷热线。通用-创建小说正文 为正文创作母入口,再按需组合 通用-生成章节控制卡、通用-管理连续性冷热线、通用-执行场景单元、通用-强化章节开头、通用-强化章末钩子、通用-正文润色 与 通用-去AI味重写。执行本 Skill 时,默认应产出:
SKILL.md 骨架references/ 占位目录.github/prompts/*.prompt.md 薄入口列表题材名- 为前缀。references/ 占位目录。题材名/.github/skills/SKILL.md 是否具备最小结构references/ 占位目录是否已一并创建Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take lornshrimp/create-genre-skill-skeletons from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.