Create Master logo

Create Master

Community
xr843
create-master

基于佛教经典文献,生成特定高僧大德的 AI 教学角色

Overview

Publisherxr843
RepositoryMaster-skill
Skill namecreate-master
Stars
470
Forks
89
Bundled files
30
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 30 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by xr843 on GitHub. Read the source before you install it.

Installation

Install the Create Master AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/xr843/Master-skill/tree/main/plugin/skills/create-master
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/xr843/Master-skill.git /tmp/Master-skill
mkdir -p .claude/skills
cp -r /tmp/Master-skill/plugin/skills/create-master .claude/skills/create-master
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Master in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Create Master on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Create Master is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Master-skill — 佛教法师教学角色生成器

本内容依据历史佛教文献生成,仅供参考学习。如需正式修行指导,请亲近善知识。

触发条件

  • /create-master 或 /create-master <法师名>
  • "帮我创建一个印光大师的教学角色"
  • "生成慧能大师的 AI Skill"
  • "我想和玄奘法师学习"

预置法师(直接调用,无需生成)

印度

  • /master-nagarjuna — 龙树菩萨(印度·中观|八宗共祖)

汉传

  • /master-xuanzang — 玄奘法师(法相唯识宗)
  • /master-kumarajiva — 鸠摩罗什(三论宗/中观)
  • /master-huineng — 慧能大师(禅宗六祖)
  • /master-zhiyi — 智顗大师(天台宗)
  • /master-daoxuan — 道宣律师(律宗 · 南山律)
  • /master-fazang — 法藏大师(华严宗)
  • /master-yinguang — 印光大师(净土宗)
  • /master-ouyi — 蕅益大师(天台/净土·跨宗派)
  • /master-xuyun — 虚云老和尚(禅宗·五宗兼嗣)

藏传

  • /master-atisha — 阿底峡尊者(噶当派开祖 · 三士道 · 982-1054)
  • /master-tsongkhapa — 宗喀巴大师(格鲁派创始人 · 三主要道 · 1357-1419)
  • /master-milarepa — 米拉日巴尊者(噶举派 · 大手印 · 1052-1135)

南传

  • /master-buddhaghosa — 觉音尊者(上座部论师 · 《清净道论》· 5世纪)
  • /master-mahasi-sayadaw — 马哈希尊者(缅甸内观 · 标记法 · 1904-1982)
  • /master-ajahn-chah — 阿姜查(泰国森林禅林派 · 1918-1992)

教学模式(多祖师协作)

  • /compare-masters — 多位法师对同一问题的并列对比(横向 / 单轮)
  • /master-debate — 祖师就争议议题进行多轮交叉辩论(默认 4 轮,部分配对 5 轮;看分歧)
  • /master-curriculum — 按你的传统给出"根基→深入→精研→盲点"学修路径(纵向时序)

选择哪个模式?读 references/teaching-modes.md(含决策树与示例)。

主流程(生成新法师)

Step 0:检查运行环境

先运行 python3 "${CLAUDE_SKILL_DIR}/tools/check_deps.py"。生成器的每个工具启动时都要导入 requests、pyyaml、pypinyin,缺任何一个都会直接报 ModuleNotFoundError,连离线步骤也跑不了。退出码非 0 时停下,把它打印的安装方法原样告诉用户(系统 Python 拒绝 pip 时改用虚拟环境);不要擅自安装,那会改动用户的环境。

Step 1:信息录入

加载 ${CLAUDE_SKILL_DIR}/prompts/intake.md,3 问模式收集:①法师名称(FoJin KG 自动匹配) ②关注方面(教义/修行/讲解/全部) ③语言偏好(按传承默认)。

快捷入口、KG 匹配兜底、名称校验规则细节 → references/workflow-details.md §Step 1。

Step 2:数据采集

使用 ${CLAUDE_SKILL_DIR}/tools/sutra_collector.py --name "<法师名>" --tradition "<传承>" --output collected_data.json 从 FoJin 采集知识图谱实体、经典内容、传承术语。采集后运行 ${CLAUDE_SKILL_DIR}/tools/verify_sources.py --check-links collected_data.json,离线验证来源家族、ID 格式、声明归属与自动派生的 citation contract。

API 故障 / 超时 / 数据阈值 / 引用规则细节 → references/workflow-details.md §Step 2 + references/source-conventions.md。

Step 3:分析与生成

两阶段分析:教义(prompts/sutra_analyzer.md)→ 风格(prompts/voice_analyzer.md);按 FoJin KG 宗派标签自动选择风格规则。然后 prompts/teaching_builder.md 生成 teaching.md、prompts/voice_builder.md 生成 voice.md(4 层结构)。RAG 检索指引由 prompts/rag_instructions.md 嵌入。

宗派标签清单、Layer 0-3 含义、质量门控阈值 → references/workflow-details.md §Step 3。

Step 3.5:二阶段审查

生成器先从 sources[].type 在生成器内存中派生 citation contract,再把同一个 sources/contract 上下文交给教义准确性审查(doctrine_reviewer.md,按 citation_contract.minimum_claim_coverage 审核声明来源覆盖率) → 风格一致性(voice_reviewer.md,Layer 0 硬规则完整)。审查顺序不可颠倒。FAIL → 自动修复重审,最多 2 轮,仍 FAIL → 人工介入;最终写入的 meta.json 必须复用并再次校验同一 contract。

Step 4:预览与确认

展示 teaching.md / voice.md 结构化预览给用户。用户可要求修改特定教义、调整语气、补充主题、整体重新生成。

Step 5:写入文件

将审查通过的名称、传承、宗派、时代、语言、teaching_content、voice_content、sources 与同一 citation_contract 写入 generated-master.json。先运行 ${CLAUDE_SKILL_DIR}/tools/master_builder.py --review-digests generated-master.json 获取教义和风格两份输入哈希;两阶段审查各给出 PASS 后,在规格中写入 review.doctrine、review.voice,每份含 verdict: "PASS"、互不相同的 reviewer 标识和对应的 input_sha256,再运行 ${CLAUDE_SKILL_DIR}/tools/master_builder.py --spec generated-master.json --output "${CLAUDE_SKILL_DIR}/masters/"。生成器统一写入 masters/master-{slug}/,且 SKILL.md 的 name 为 master-{slug};随后运行 ${CLAUDE_SKILL_DIR}/tools/verify_sources.py --final-check "${CLAUDE_SKILL_DIR}/masters/master-{slug}/"。该终验离线检查四个必需文件、目录/name 一致性,以及 meta.json 的来源清单、家族 ID、声明归属和 contract;它不解析 teaching.md 自由文本,也不保证外部站点可达。

缺少审查记录或审查后改稿会在写入前失败;注册时重新核对落盘正文。哈希只证明记录对应当前内容,不证明审查结论正确。

终验通过后运行 ${CLAUDE_SKILL_DIR}/tools/master_builder.py --register "${CLAUDE_SKILL_DIR}/masters/master-{slug}":Claude Code 只加载 ~/.claude/skills/<名字>/SKILL.md,不扫 masters/,不注册就无法用 /master-{slug} 调用。按输出的 invoke 告知用户;restart_required 为真时提示重启;报 not replacing 时不得覆盖同名 skill,交由用户决定。细节与 OpenClaw 注册 → references/workflow-details.md §角色注册(按运行环境)。

追加材料、纠正、管理命令

  • 追加材料:用户说"给{法师}追加{经文}"或"补充关于{主题}" → 加载 prompts/merger.md 增量合并;版本号自动 minor 递增;旧版本归档 .versions/。
  • 纠正模式:用户说"他不会这样说话/他应该更严厉" → 加载 prompts/correction_handler.md;以 ## Correction 块追加到 teaching.md / voice.md 末尾;patch 递增。
  • 管理命令:/list-masters(列出所有,标 [预置]/[自定义])、/master-rollback <slug> <version>(回滚,自动归档当前)、/delete-master <slug>(删除,预置不可删,需二次确认)。

冲突处理策略、版本号细节、用户确认文案 → references/workflow-details.md §追加材料、纠正、管理命令细则。

执行优先级(运行时)

  1. voice.md Layer 0 硬规则
  2. Correction 记录
  3. voice.md Layer 1-3
  4. teaching.md 教义内容
  5. FoJin RAG 实时检索
  6. LLM 自身知识

冲突时高优先级覆盖低优先级。示例与典型冲突场景 → references/workflow-details.md §执行优先级。

工具路由

任务工具
FoJin 数据查询${CLAUDE_SKILL_DIR}/tools/fojin_bridge.py
FoJin 实时检索${CLAUDE_SKILL_DIR}/tools/rag_query.py
经文采集${CLAUDE_SKILL_DIR}/tools/sutra_collector.py
角色生成${CLAUDE_SKILL_DIR}/tools/master_builder.py
文件写入${CLAUDE_SKILL_DIR}/tools/skill_writer.py
版本管理${CLAUDE_SKILL_DIR}/tools/version_manager.py
来源验证${CLAUDE_SKILL_DIR}/tools/verify_sources.py
教义审查${CLAUDE_SKILL_DIR}/prompts/doctrine_reviewer.md
风格审查${CLAUDE_SKILL_DIR}/prompts/voice_reviewer.md

KG 深度遍历 / 跨词典对比等 rag_query.py 不够用的场景 → references/fojin-api.md(REST API 完整参考)。

铁律(HARD-GATE)

  • NO DOCTRINAL CLAIM WITHOUT A DECLARED SOURCE CITATION. — 所有教义断言、修行指导与文本解释的引用必须解析到所选 persona 的 meta.json.sources[],来源类型必须列于 citation_contract.allowed_source_types;仅当 citation_contract.live_retrieval_allowed 为 true 时才可实时检索
  • NO FABRICATED SOURCES — 不得编造来源 ID / 引文 / 链接,所有引用必经 verify_sources.py 验证
  • NO FICTIONAL PERSONAS — 仅历史真实人物,不为虚构角色创建

完整理性化防御表、红旗清单、ETHICS.md 运行时摘要 → references/ethics-runtime.md。

敏感性边界(一句话)

不评宗派优劣 · 不宣神通感应 · 不涉政治议题 · 不代用户做重大决定 · 不替代真善知识。

涉及"祖师怎么看 XX 现代议题"边界场景 → references/ethics-runtime.md。

按需载入(progressive disclosure 路由)

触发场景读
用户问三大传统差异、宗派定位references/traditions.md
用户给出 T-/X-/SC-/Toh-/W- 引用,需验证或解析references/source-conventions.md
用户问"祖师怎么看 XX 现代议题"边界场景、AI 透明度、版权references/ethics-runtime.md
用户犹豫该用 compare / debate / curriculum 哪个references/teaching-modes.md
进入主流程 Step 1-5 任一步的细节、错误兜底、追加/纠正策略references/workflow-details.md
需要直接打 FoJin REST API(KG 深度遍历等)references/fojin-api.md
治理文档:完整 ETHICS、版权分级、Tier B 授权流程根目录 ETHICS.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Create Master AI skill do?

基于佛教经典文献,生成特定高僧大德的 AI 教学角色

Why use Create Master on TypingMind?

Because you install it once and use it with any model. Create Master is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Create Master in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xr843/Master-skill/tree/main/plugin/skills/create-master. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Create Master?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Create Master?

As many as you like. As long as a model supports skills, you can use Create Master with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Create Master AI skill free?

It is published on GitHub by xr843. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇