Update knowledge files with corpus analysis and feedback system docs

- CLAUDE.md: added corpus-analysis.md to reference table, documented chair feedback system
- block-schema.md: added content_checklist constraint to block-yod
- legal-decision-lessons.md: added lessons 12-16 from corpus analysis (planning discussion, 5 subtypes, feedback system)
- SKILL.md: added section 12 (content checklists, planning discussion patterns, chair feedback)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docs/block-schema.md

@@ -371,6 +371,7 @@ Conclusion → Rule → Explanation → Application → Conclusion.
 - MUST: מסקנה בפתיחת הדיון (לא בסוף)
 - MUST: מענה לכל טענה שהוצגה בבלוק ז
 - MUST: ציטוט פסיקה בבלוקים ארוכים (200-600 מילים)
+- MUST: **צ'קליסט תוכן** — הפרומפט מזריק `{content_checklist}` אוטומטית לפי סוג הערר (מתוך `lessons.py: CONTENT_CHECKLISTS`). ראה `docs/corpus-analysis.md` לדפוסי תוכן לפי סוג.
 - ⚠️ **MUST NOT ("ללא כפילות"):** חזרה על עובדות/טענות מבלוקים קודמים. השתמש בהפניות: "כאמור בסעיף X לעיל", "כפי שפורט", "כפי שציינו"
 - MUST NOT: כותרות משנה (חריג: נושאים נפרדים לחלוטין)
 - Dependencies: **ALL** previous blocks (ה-ט)

docs/legal-decision-lessons.md

@@ -161,3 +161,44 @@ Our skill was "over-indexed" on one case type (הכט = rejected appeal). The co
 - Created `create-decision-structure.cjs` script for generating structure DOCX
 - Key innovation from Arieli: "ההליכים בפני ועדת הערר" as separate section (Block ח)
 - "Judge Test": every block written as if administrative court judge reads cold
+
+---
+
+## Lessons from Systematic Corpus Analysis (24 decisions, April 2026)
+
+### Source
+- All 24 proofread decisions in `/data/training/proofread/`
+- Full analysis: [`docs/corpus-analysis.md`](corpus-analysis.md)
+- Date: April 2026
+
+### 12. System Learned Style but Not Substantive Content
+- **Problem:** Dafna reviewed Kiryat Yearim draft and noted missing planning discussion in block-yod
+- **Root cause:** The block-yod prompt taught CREAC methodology and "answer all claims" but never said "in licensing cases, include comprehensive planning discussion"
+- **Fix:** Content checklists added to `lessons.py` (`CONTENT_CHECKLISTS`), injected into block-yod prompt via `{content_checklist}`
+- **Applied to:** `lessons.py`, `block_writer.py`
+
+### 13. Corpus Composition — All Licensing, No Betterment Levy
+- All 24 training decisions are licensing/construction (1xxx)
+- Zero betterment levy (8xxx) decisions in corpus
+- Not a current priority gap — focusing on licensing first
+
+### 14. Planning Discussion Patterns in Licensing Decisions
+- **Always present** when the appeal reaches substantive planning questions
+- **Never present** when the appeal is purely jurisdictional or property-based
+- **Structure**: broad planning context → direct plan provision citations (200-600 words) → application to specific case → planning conclusion
+- **Deepest planning**: פרומר (pure plan interpretation), לבנון (height/building appendix), בית הכרם (multi-plan TAMA 38)
+- **No planning**: טלי-אביב (property only), גבאי (jurisdiction only)
+
+### 15. Five Appeal Subtypes Identified (Not Just Three)
+Licensing appeals are not homogeneous — the discussion structure varies significantly:
+1. **Substantive licensing** — full planning discussion + legal analysis (majority of cases)
+2. **Threshold/jurisdiction** — legal analysis only, no planning
+3. **Property-focused** — תימוכין קנייניים, minimal planning
+4. **TAMA 38** — balancing public interest + planning + neighbor impact
+5. **Deviant use (שימוש חורג)** — deep plan interpretation across multiple plans
+
+### 16. Chair Feedback System Established
+- DB table `chair_feedback` records Dafna's comments on drafts
+- Categories: missing_content, wrong_tone, wrong_structure, factual_error, style, other
+- MCP tools + UI page for recording and reviewing feedback
+- First entry: Kiryat Yearim — missing planning discussion (2026-04-12)