← all publishers

smter

@smter source repo

7 published skills

  1. Review Plan · smter
    Dispatch a sub-agent to audit planning artifacts for cross-document disconnections, vague/underspecified design points, spec violations, and architecture depth — then independently judge each finding before fixing.
    0
    installs
  2. Wiki Review · smter bundle
    Use when reviewing an Obsidian wiki with FSRS scheduling, especially when the user wants to sync reviewable notes, ask recall questions, submit ratings, or inspect due items.
    0
    installs
  3. Internalized Wiki · smter bundle
    Use when building or maintaining an Obsidian-friendly LLM wiki with raw sources, compiled wiki notes, internalization metadata, review readiness, ingest, query, archive, and lint workflows.
    0
    installs
  4. Novel Delivery · smter bundle
    Use when 中文小说项目已经具备完成且审查通过的书稿,并需要做导出就绪检查、基于 Pandoc 的 PDF/EPUB 打包或交付诊断
    0
    installs
  5. Novel Drafting · smter bundle
    Use when 中文小说项目已经具备调研文件,并需要按章节起草、经过审查闸门、执行连续性检查或从阻塞状态恢复起草
    0
    installs
  6. Novel Research · smter bundle
    Use when 需要为新的中文小说项目完成设定澄清、背景或世界观调研、风格约束与起草前项目脚手架搭建
    0
    installs
  7. Harness Engineering Zh · smter bundle
    为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent 质量时也会触发(例如:'Agent 总是无视规范'、'它从不听从指令'、'为什么它总是做错 X'、'Agent 坏了')— 因为 Agent 输出质量差几乎总是意味着 Harness 缺失,而不是模型问题。涵盖:Context 工程、架构约束、多 Agent 协作、评估、长运行任务 Harness 以及 Agent 质量问题诊断。
    0
    installs