agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Worked for most · soon
XiaoyangySkill

novel-check

Xiaoyangy/novel-studio/skills/novel-check/SKILL.md

LLM 连通性自检:对默认模型与各角色模型做一次最小真实调用,逐一报告 provider/model 是否真的可用。触发:「检查 LLM 能不能用」「测试模型连通」「创作前先确认配置」「为什么一调用就报错」,排查代理未启动 / key 失效 / base_url 写错时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-cocreate

Xiaoyangy/novel-studio/skills/novel-cocreate/SKILL.md

共创规划:与 AI 多轮对话澄清需求,逐轮累积出一份整本书的创作指令,定稿后可直接进入创作。触发:「还没想清楚写什么」「帮我把想法理清楚」「一起策划一本书」「共创」,冷启动、需求模糊时用它而非一次性 --prompt。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-diag

Xiaoyangy/novel-studio/skills/novel-diag/SKILL.md

诊断当前项目的 output 产物,从流程/质量/规划/上下文四维给出可执行发现,并写出脱敏报告。触发:「诊断这本书」「为什么卡住了」「检查创作有没有问题」「生成 diag 报告贴 issue」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-douban-write

Xiaoyangy/novel-studio/skills/novel-douban-write/SKILL.md

用 novel-studio 生成豆瓣阅读原创长篇小说的专项入口。适用于 15W-30W 字原创长篇,默认把豆瓣写作契约写入 prompt,并串联 review/rewrite/export;触发:「豆瓣长篇」「按豆瓣要求写」「生成豆瓣阅读原创小说」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-pipeline

Xiaoyangy/novel-studio/skills/novel-pipeline/SKILL.md

把各功能串成一条可恢复的流水线:(共创→)写作→评审→重写→交付,按阶段执行、断点续跑。触发:「一条龙写完整本书」「从头跑完整个流程」「中断后接着跑」,想要无人值守端到端、且能中断恢复时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-review

Xiaoyangy/novel-studio/skills/novel-review/SKILL.md

通过 novel-studio pipeline 的 review 阶段对已有项目逐章跑 Editor 评审,只产出审阅意见、不改原文。触发:「评审我的小说」「逐章审一遍」「给章节挑问题」,需要质量诊断但要保留原文时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-rewrite

Xiaoyangy/novel-studio/skills/novel-rewrite/SKILL.md

通过 novel-studio pipeline 的 rewrite 阶段按评审反馈逐章 Writer 重写,会改动章节原文。触发:「按评审改写」「重写这几章」「根据意见润色正文」,在 novel-review 之后据反馈落地修改时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-simulate

Xiaoyangy/novel-studio/skills/novel-simulate/SKILL.md

分析 simulate/ 参考语料合成「仿写画像」注入后续创作,或导入此前生成的画像。触发:「学这些范文的写法」「按这批文章的风格写」「导入仿写画像」,想让 Agent 借鉴结构/节奏/钩子手法时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-steer

Xiaoyangy/novel-studio/skills/novel-steer/SKILL.md

为当前项目排队一条干预指令,下次启动 / 恢复创作时自动注入 Coordinator。触发:「下次跑的时候改一下」「加一条修改意见」「主角改成女性」「加快节奏」,在两次创作运行之间排队修改指令时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-write

Xiaoyangy/novel-studio/skills/novel-write/SKILL.md

用一句创作需求驱动 novel-studio 走可恢复 pipeline 完整创作(写作→评审→重写→导出)。触发:「帮我写本小说」「按这个设定写」「跑一次创作」,已有明确创作要求且希望无人值守端到端产出章节时使用。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

novel-writing-assets

Xiaoyangy/novel-studio/skills/novel-writing-assets/SKILL.md

查看、启用、停用、组合、绑定、试写和重新编译 novel-studio 的长期写法资产。触发:「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

ai-novel-audit

Xiaoyangy/novel-studio/skills/review/SKILL.md

审核一段/一篇小说(或任意叙事性文本)的「AI 创作度」——判断它有多大可能由 AI 生成、或 AI 参与了多少。当用户想知道一段文字是不是 AI 写的、AI 味重不重、是人工还是 AI、AI 辅助了多少、帮忙鉴别/检测/审稿 AI 生成内容、给稿件的「人味/机味」打分时,都使用本技能。触发词包括但不限于:AI 创作度、AI 味、是不是 AI 写的、AI 生成检测、人工还是 AI、鉴别 AI、查稿、审稿、AIGC 检测、机器味、文风鉴定。哪怕用户没明说「AI 创作度」这五个字,只要意图是评估一段叙事文本的 AI 生成可能性,就用本技能。注意:本技能只产出「概率性信号 + 证据」,绝不输出武断的非黑即白判决。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-deslop

Xiaoyangy/novel-studio/skills/story-deslop/SKILL.md

网文去AI味。检测并清除文本中的AI写作痕迹,让文字回归自然、非模板化。触发方式:/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-douban-long-write

Xiaoyangy/novel-studio/skills/story-douban-long-write/SKILL.md

豆瓣阅读原创长篇专项方法论与 novel-studio pipeline 适配器。用于把 15W-30W 字原创长篇的主题、类型、开头、文字、标签、简介和提交自检要求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-douban-long-write、/豆瓣长篇、/豆瓣写作、「写一部豆瓣阅读原创长篇」「按豆瓣要求写长篇」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-long-write

Xiaoyangy/novel-studio/skills/story-long-write/SKILL.md

长篇网文写作方法论与 novel-studio pipeline 适配器。用于把长篇开书、大纲、日更、续写、重写等需求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-review

Xiaoyangy/novel-studio/skills/story-review/SKILL.md

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn;缺失/异常 agents 或 spawn 失败时自动降级 solo,参考文件不可读时使用内置 rubric fallback。触发方式:/story-review、/审查、「审查一下」「帮我审一下」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-setup

Xiaoyangy/novel-studio/skills/story-setup/SKILL.md

网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录,支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-short-analyze

Xiaoyangy/novel-studio/skills/story-short-analyze/SKILL.md

短篇网文拆文。拆解爆款短篇小说(番茄短篇 / 故事会 / 知乎盐选 / 追妻 / 世情 / 重生 / 虐渣等通俗题材)的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道:跑完 Stage 2-6 产出完整拆文报告,落盘到 deconstruction-library/{书名}/,下游 story-short-write 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。触发方式:/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」「分析这篇短篇」——均进入同一管道。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story-short-write

Xiaoyangy/novel-studio/skills/story-short-write/SKILL.md

短篇网文写作方法论与 novel-studio pipeline 适配器。用于把短篇、盐言故事、拆文续写等需求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。

1222mo agoReviewMountCreate a free account to mount
XiaoyangySkill

story

Xiaoyangy/novel-studio/skills/story/SKILL.md

网络小说工具箱主入口。根据用户需求自动路由到对应 skill;当用户意图不明确时触发,由路由逻辑分发到具体的拆文/写作/去AI味/审查 skill。触发方式:/story、$story、/网文、「我想写小说」「帮我写书」「写网文」。

1222mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.