Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
Back to list

Master-skill — Buddhist Teacher Persona Generator

Generates source-grounded AI teaching personas of historical Buddhist masters from canonical texts and the FoJin knowledge graph.

EducationIntermediate31866AI score 8/10Last updated: Aug 12, 2026

What it does

  • /create-master <name> builds a teaching persona for a historically real Buddhist master, producing teaching.md and a 4-layer voice.md.
  • Collects KG entities, scripture passages and tradition-specific terminology via sutra_collector.py, then validates source families, ID formats and the derived citation contract offline with verify_sources.py.
  • Runs a two-stage review — doctrinal accuracy first, then voice consistency — with up to two auto-repair rounds before escalating to a human.
  • Ships ~15 preset masters across Indian, Chinese, Tibetan and Theravada traditions (Nagarjuna, Xuanzang, Huineng, Zhiyi, Yinguang, Xuyun, Atisha, Tsongkhapa, Milarepa, Buddhaghosa, Mahasi Sayadaw, Ajahn Chah, and more).
  • Offers multi-master modes: /compare-masters, /master-debate (4-round debate) and /master-curriculum (staged study path), plus versioning, rollback, deletion, material merging and tone correction.
  • Enforces hard gates: no doctrinal claim without a declared source, no fabricated citations, no fictional personas.

Who it's for

  • Students and researchers of Buddhism who want to compare doctrinal positions across schools.
  • Religion/humanities content creators who need every claim tied to a verifiable citation.
  • Developers looking for a reference design of a persona-generation pipeline with a citation-verification gate.

Example uses

  1. "Create a teaching persona for Master Yinguang" → confirm name, pick focus area and language, get a persona with Pure Land voice rules applied.
  2. Use /compare-masters to ask "How do I work with a scattered mind?" and see Huineng, Zhiyi and Ajahn Chah answer side by side.
  3. Use /master-curriculum for a foundation→depth→close-study→blind-spot path, then say "add this sutra to that master" to merge new material with an automatic minor version bump.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/xr843/Master-skill/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the SKILL.m folder from the GitHub repo xr843/Master-skill into my ~/.claude/skills/create-master/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/xr843/Master-skill.git ~/.claude/skills/master-skill

This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and make sure the skills directory exists: mkdir -p ~/.claude/skills
  2. Clone the repository: git clone https://github.com/xr843/Master-skill.git ~/.claude/skills/master-skill
  3. Verify the contents: ls ~/.claude/skills/master-skill — you should see SKILL.md, prompts/, references/ and tools/.
  4. The workflow calls Python helpers, so check python3 --version; if the repo ships a requirements.txt, run pip install -r requirements.txt.
  5. Restart Claude Code and type /list-masters or /create-master to confirm the skill is registered.
  6. Steps that query FoJin need network access; if a call fails, consult the error-handling sections in references/workflow-details.md.