codechakorn/Master-skill
1
0
Fork 0
mirror of https://github.com/xr843/Master-skill.git synced 2026-05-10 05:16:25 +00:00
Code Issues Packages Projects Releases Wiki Activity
76 Commits 1 Branch 4 Tags
7b2af14c7fde5d66c64f878d2f29c86b1a022344
Commit Graph

76 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Tim Ren 7b2af14c7f Merge pull request #5 from xr843/feat/two-stage-review 
feat: two-stage review for create-master generation pipeline
 2026-04-08 21:45:05 +08:00
xianren f22204a75e feat: add two-stage review for create-master generation pipeline 
Inspired by superpowers' spec-reviewer + code-quality-reviewer pattern,
add mandatory two-stage review between generation and preview:

Stage 1 — Doctrine Review (doctrine_reviewer.md):
  - Citation coverage check (target >= 90%)
  - CBETA ID attribution accuracy
  - Sectarian boundary validation
  - Auto-fix with max 2 retry rounds

Stage 2 — Voice Review (voice_reviewer.md):
  - Layer 0 hard rules completeness
  - Style-to-tradition matching
  - Layer structure clarity check
  - Historical plausibility

Both stages must PASS before entering Step 4 (preview).
Added as Step 3.5 in create-master SKILL.md workflow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 21:43:46 +08:00
Tim Ren a8513910cb Merge pull request #4 from xr843/feat/multi-platform-plugin 
feat: multi-platform plugin support (Claude Code, Cursor, Codex, OpenCode, Gemini)
 2026-04-08 21:41:56 +08:00
Tim Ren 12020444e0 Merge pull request #3 from xr843/feat/hard-gate-and-pressure-tests 
feat: HARD-GATE discipline enforcement, pressure tests, and CI pipeline
 2026-04-08 21:41:53 +08:00
xianren f3472d6254 feat: add multi-platform plugin support and session-start hook 
Add support for 5 platforms beyond NPX:

- Claude Code: .claude-plugin/plugin.json + marketplace.json
- Cursor: .cursor-plugin/plugin.json + hooks-cursor.json
- Codex CLI: .codex/INSTALL.md with symlink setup
- OpenCode: .opencode/INSTALL.md with plugin config
- Gemini CLI: gemini-extension.json + GEMINI.md

Infrastructure:
- SessionStart hook with platform detection (Claude Code,
  Cursor, Copilot CLI) that injects available masters list
- Cross-platform run-hook.cmd polyglot wrapper (Windows + Unix)
- .version-bump.json for unified version management across
  all platform config files
- Update README/README_EN with multi-platform install instructions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 21:38:08 +08:00
xianren 45c0416bc3 feat: add HARD-GATE to compare and create-master skills 
- compare: add NO COMPARATIVE RANKING and NO FABRICATED DIALOGUE
  iron laws with rationalization defense table
- create-master: add NO FABRICATED SOURCES iron law for the
  generation pipeline
- Add 2 boundary tests for compare (sectarian ranking, fabricated
  dialogue)
- Fix validate-fidelity.py to support compare's assertion fields
  and no_fabricated_dialogue boundary type

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 21:32:13 +08:00
xianren c654e7440f feat: add CI validation pipeline and boundary test support 
- Update test-fidelity.py to support must_not_contain and
  must_not_contain_first_turn fields for boundary/pressure tests
- Add validate-fidelity.py for structural validation of all
  fidelity.jsonl files (no API needed)
- Add GitHub Actions workflow: runs validate + dry-run on every
  push/PR touching prebuilt/scripts/prompts/tools

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 21:30:23 +08:00
xianren da80665fa5 feat: add HARD-GATE discipline enforcement and pressure tests for all 8 masters 
Inspired by obra/superpowers project patterns, add three-layer defense
to prevent AI hallucination and rule violation:

- Iron Laws: NO DOCTRINAL CLAIM WITHOUT CBETA CITATION,
  NO PERSONA BEFORE CONTEXT, NO SECTARIAN JUDGMENT
- Rationalization Defense Table: 6 common AI excuses with rebuttals
- Red Flag List: 5 observable violation signals

Also add 40 pressure test cases (5 per master) covering:
- Sectarian judgment boundary
- No prophecy boundary
- Neutral first turn boundary
- Citation bypass pressure
- Master-specific challenges (meta, hostile, misunderstanding, etc.)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 21:28:41 +08:00
xianren 29a17ea281 docs: remove redundant "(手动)" from Claude Code install heading 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-07 14:16:06 +08:00
xianren 7f26cb3239 docs: add online demo section linking to fojin.app/chat 
Users can now try all pre-built masters directly in the browser
without installing Claude Code or Codex CLI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-07 14:10:38 +08:00
xianren 59767e96b9 docs: update README for v0.3 — NPX install, architecture diagram, provenance features 2026-04-06 07:24:01 +08:00
xianren 623d88aa3e feat: v0.3 architecture rebuild — progressive disclosure, provenance, fidelity tests, NPX installer v0.3.0 2026-04-06 07:21:43 +08:00
xianren 88debde58d refactor(4-masters): rebuild fazang, huineng, kumarajiva, xuanzang to v0.3 architecture 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-06 07:18:52 +08:00
xianren d88da7b091 feat(scripts): add cite.py and query.py offline tools 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-06 07:13:56 +08:00
xianren 936ce09069 feat: add NPX installer CLI (install/list/uninstall) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-06 07:13:51 +08:00
xianren 937b642da8 refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests 
Sample master (zhiyi) rebuilt to new architecture:
- SKILL.md slimmed from 225→94 lines with decision tree + Quick Ref
- Provenance frontmatter: CBETA IDs, FoJin text IDs, citation_format
- voice.md/teaching.md moved to references/ (loaded on demand)
- sources/ with canonical excerpts (offline-capable)
- tests/fidelity.jsonl: 5 Q&A pairs with expected citations/keywords
- scripts/validate.py: cross-master frontmatter linter
- scripts/test-fidelity.py: Claude API-based fidelity test runner

Follows Anthropic Agent Skills patterns:
  - Progressive disclosure (metadata→body→references)
  - Decision tree for branching workflows
  - Task-gated reference loading
  - Quick Reference table
  - Scripts as black boxes (--help, never Read source)
 2026-04-06 07:05:43 +08:00
xianren 5b30b081c5 docs: add Codex CLI installation instructions 
Codex CLI natively supports AgentSkills standard via ~/.codex/skills/.
Verified with codex-cli 0.118.0 — 10 skills registered successfully.
 2026-04-05 13:33:50 +08:00
xianren 1de3bb9388 fix: correct FoJin URL format for juan paths 
FoJin frontend route is '/texts/:id/read?juan=N' (query param),
not '/texts/{id}/juan/{N}' (path segment). Old format fell through
to React router 404.

Verified against FoJin frontend App.tsx route definitions:
- /texts/:id         → TextDetailPage
- /texts/:id/read    → TextReaderPage (uses ?juan= query)
 2026-04-05 12:11:36 +08:00
xianren eb87794773 docs: simplify Community section wording 2026-04-05 10:50:45 +08:00
xianren 799beb6ba6 docs: add Community section linking to LINUX DO 2026-04-05 10:46:01 +08:00
xianren 1e0947acc4 docs: simplify v0.2 update banner 2026-04-05 10:16:10 +08:00
xianren 1b8554242d docs: add hero section with Diamond Sutra epigraph, badges, and navigation 
Inspired by colleague-skill's README layout, adapted with dignified
Buddhist tone:
- Diamond Sutra verse as epigraph (in quotation marks, with source)
- Badges row (License, Python, Claude Code, AgentSkills)
- Scholar-oriented hook paragraphs (studying Yogacara, Chan, etc.)
- Serious tagline (no marketing flourish)
- Navigation quick-links
- v0.2 update banner
 2026-04-05 10:13:39 +08:00
xianren 25aea07f6a refactor: rename Buddha-skill → Master-skill 
Matches internal architecture (create-master, master_xuanzang, etc.)
and accurately reflects content (historical Chinese Buddhist masters,
not the Buddha himself).

Changes:
- 32 text references across 9 files updated
- Sanskrit terms (buddha-dhātu, buddhatā) preserved in dictionary context
- GitHub repo renamed (preserves stars/forks/history, auto-redirects)
- Internal naming already uses master_* (unchanged)

All 79 tests pass.
 2026-04-05 10:03:42 +08:00
xianren 9dffcf3379 fix: enforce per-master RAG queries in /compare-masters with tradition-specific terms 
Previously LLM might run ONE combined semantic query, causing the non-dominant
master to get fallback search URLs (fojin.app/search?q=...) instead of precise
text_id links.

Now the skill:
- Explicitly requires N separate queries for N masters (emphasized with ⚠️)
- Provides a query-rewriting table: each master's query uses its tradition's
  terminology (唯识/中观/禅宗/天台/华严/净土 terms)
- Example: user asks '因缘果' → xuanzang queries '因缘果 六因 四缘 五果 种子',
  kumarajiva queries '因缘所生法 空 中道 无自性 四句'

This ensures both masters get precise text_id citations, not degraded search URLs.
 2026-04-05 09:43:31 +08:00
xianren 9873d0514d feat: add --brief flag to rag_query.py to reduce output verbosity 
- New --brief flag for semantic/search subcommands outputs one-line-per-result
  (title + link + 80-char snippet) instead of full 500-char excerpts
- Reduces output from ~60 lines to ~7 lines per query (3 results)
- /compare-masters now uses --brief by default (multiple queries no longer
  flood the terminal with long excerpts)
- Full output (default) preserved for single-master /ask and debugging
 2026-04-05 09:32:55 +08:00
xianren 16cbda8e50 fix: robust tool path resolution + precise selection feedback in /compare-masters 
- Add PROJECT_ROOT discovery with 3 fallback paths (dev/manual/OpenClaw)
- Replace ${CLAUDE_SKILL_DIR}/tools/... with $PROJECT_ROOT/tools/...
  (CLAUDE_SKILL_DIR in subskills points to skill dir, not project root)
- Add graceful degradation when rag_query.py unreachable
- Output selection reasoning explicitly (e.g. 'xuanzang: 强关键词匹配(5项)
  + kumarajiva: 主题互补视角') instead of vague '主题映射'
 2026-04-05 09:17:11 +08:00
xianren 6446903daf feat: smart master selection + expanded keywords (6→24 per master) 
- /compare-masters now uses keyword matching from meta.json search_scope.keywords
- 3-tier selection: user-specified → keyword matching → topic fallback
- Expanded each master's keywords to 15-25 core concepts (avg 24)
- Document --masters manual override in README

Selection improvements verified:
- '遍行因' → xuanzang (5 matches)
- '明心见性' → huineng (3 matches)
- '空性/中观' → kumarajiva + huineng
- '念佛' → yinguang + ouyi + xuyun
 2026-04-05 09:07:24 +08:00
xianren 02df9344b5 feat: 首轮身份中立原则 — masters no longer assume user identity on first turn 
- Add Layer 0 hard rule to all 8 masters' voice.md: first turn must use
  neutral address (您/汝/你/问者), forbidden terms include 居士/行者/学人/
  善男子/善女人/出家人/师父/大众/道友/善信/道友
- From turn 2+: masters adapt to user's self-disclosed or question-inferred
  identity, restoring each master's historical address style
- Layer 2 开场方式/称呼方式 reorganized into 首轮中立 / 身份已知后 tiers
- Update voice_builder.md and voice_analyzer.md templates so future
  /create-master runs inherit this rule
- Add tools/sync_skill_from_voice.py to keep SKILL.md PART B in sync
- Add 48 regression tests in test_voice_rules.py (all 79 tests pass)
 2026-04-05 08:44:35 +08:00
xianren e0afab5c9f fix: slugify now correctly lowercases English names and handles spaces 2026-04-05 08:11:31 +08:00
xianren 2a63a50ed3 test: add basic test suite for fojin_bridge, skill_writer, verify_sources (P1) 
31 tests across 3 modules; all HTTP calls mocked, no real API dependencies.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 08:07:34 +08:00
xianren 6c6e19f2bc ci: add weekly GitHub Actions workflow for FoJin link verification (P2) 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 08:06:40 +08:00
xianren 02d1069c46 feat: add /compare-masters skill for multi-master comparison (P1) 2026-04-05 08:05:46 +08:00
xianren 6f34e98508 docs: add complete FoJin API reference for LLM ad-hoc queries (P0) 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 08:05:25 +08:00
xianren 5688f40c1a feat: graceful degradation when FoJin API is unavailable (P0) 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 08:04:24 +08:00
xianren da2a7f2dc8 refactor: remove 南传/藏传 masters, focus exclusively on 汉传祖师大德 2026-04-05 07:42:00 +08:00
xianren 8da9b47dda docs: refocus PRD on 汉传佛教 — remove 南传/藏传 sections 2026-04-05 07:41:38 +08:00
xianren ce8024ac92 docs: simplify analyzer prompts — remove 南传/藏传 sections, focus on 汉传 2026-04-05 07:41:23 +08:00
xianren 4ef0c6fd70 docs: simplify acknowledgments — remove FoJin and colleague-skill 2026-04-05 07:29:07 +08:00
xianren d881797005 docs: expand SKILL.md with detailed flow control, error handling, and priority rules (P1) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 22:41:24 +08:00
xianren d210bbe5fb feat: add correction handler for real-time user feedback on master personas (P1) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 22:37:43 +08:00
xianren 35f9425f3a feat: embed tradition tag behavior mappings into analyzer prompts (P0 fix) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 22:37:28 +08:00
xianren 864a01be05 docs: rename 严肃性声明 to 声明 2026-04-04 22:23:19 +08:00
xianren 0f53ae0400 docs: update disclaimer — use 佛教经典文献, remove medical/diagnosis/mentor clauses 2026-04-04 22:20:30 +08:00
xianren 2fa3c1f634 refactor: rename teacher → master across all docs, commands, files, and directories 2026-04-04 22:10:41 +08:00
xianren 62b5810854 docs: refine disclaimer — remove redundant statements, highlight RAG capability 2026-04-04 22:01:05 +08:00
xianren aafcbdf721 refactor: rename teacher_ to master_ in all SKILL.md frontmatter, update descriptions 2026-04-04 21:47:01 +08:00
xianren 8e6a83f55b docs: remove OpenClaw recommended label, list Claude Code first 2026-04-04 20:41:03 +08:00
xianren 42389040f7 docs: add OpenClaw and Claude Code installation instructions 2026-04-04 20:38:27 +08:00
xianren d84a6f9040 fix: verify and update 186 FoJin URLs from CBETA IDs to real internal text_ids 2026-04-04 19:58:55 +08:00
xianren d0709af973 feat: add source verification tool to validate FoJin links 
Scans all prebuilt teachers for CBETA IDs and fojin.app URLs, verifies
against FoJin API, and can fix URLs to use internal text_ids (--fix flag).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 19:57:48 +08:00