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

Compare Masters — Multi-Tradition Buddhist Perspective Contrast

A meta-skill that picks 2–3 Buddhist masters from different schools and contrasts their answers to the same question in a fixed, citation-backed format.

EducationIntermediate★ 320⑂ 66AI score 8/10Last updated: Aug 18, 2026

What it does

  • Fires on comparison-style questions ("Chan vs Pure Land", "emptiness vs Yogacara", "how do different schools see this?") in Chinese or English.
  • Selects 2–3 masters from 15 personas across four traditions: Indian (Nagarjuna), Chinese (Huineng, Yinguang, Zhiyi, Fazang, Xuanzang, Kumarajiva…), Tibetan (Atisha, Tsongkhapa, Milarepa), and Theravada (Buddhaghosa, Mahasi Sayadaw, Ajahn Chah), via a keyword-weighting rule plus a topic→pairing table.
  • Emits a fixed output protocol: shared ground → each master's view with scriptural citations → core divergence → suitability-by-disposition table → a five-dimension "divergence radar" → labeled divergence types → source list.
  • Enforces hard rules: no doctrinal claim without a resolvable source, no ranking one school above another, no fabricated historical debates, no empty radar cells.

Who it's for

  • Buddhist students, teachers, and researchers doing comparative doctrinal study.
  • Anyone who wants an AI to handle religious topics neutrally and verifiably.
  • Users who already installed the sibling master-* persona skills from the same repo (this skill depends on their data files).

Examples

  1. "Is seeing one's nature required for rebirth in the Pure Land?" → pairs Yinguang with Ouyi and applies the built-in "Chan vs Pure Land" classic-debate template.
  2. "What separates Yogacara from Madhyamaka?" → pairs Xuanzang with Kumarajiva and maps the two-truths and three-natures disagreement onto the radar table.
  3. "Which meditation method should I use?" → contrasts Buddhaghosa's forty subjects, Mahasi noting, and Ajahn Chah's plain awareness, while refusing to certify anyone's attainment level.

· · · 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/prebuilt/compare-masters/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 prebuilt/compare-masters folder from the GitHub repo xr843/Master-skill into my ~/.claude/skills/compare-masters/.
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 /tmp/master-skill && mkdir -p ~/.claude/skills && cp -r /tmp/master-skill/prebuilt/* ~/.claude/skills/

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

  1. Open a terminal.
  2. Clone the repo to a temp folder: git clone https://github.com/xr843/Master-skill.git /tmp/master-skill
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. This skill reads other master persona data, so copy the whole prebuilt folder: cp -r /tmp/master-skill/prebuilt/* ~/.claude/skills/
  5. Confirm that ~/.claude/skills/compare-masters/SKILL.md exists.
  6. Restart Claude Code and try: "Compare how Chan and Pure Land masters view rebirth."
  7. To pick masters yourself, append --masters master-huineng,master-yinguang. Optional helper scripts (scripts/cite.py, scripts/query.py) require Python and should be run with --help first.
View source on GitHub ↗License: MIT