feat: add 文言文 (Classical Chinese) mode with wenyan-lite/full/ultra intensities

README.md

@@ -72,26 +72,33 @@ Based on the viral observation that caveman-speak dramatically reduces LLM token
 
 <table>
 <tr>
-<td width="33%">
+<td width="25%">
 
 #### 🪶 Lite
 
 > "Your component re-renders because you create a new object reference each render. Inline object props fail shallow comparison every time. Wrap it in `useMemo`."
 
 </td>
-<td width="33%">
+<td width="25%">
 
 #### 🪨 Full
 
 > "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`."
 
 </td>
-<td width="33%">
+<td width="25%">
 
 #### 🔥 Ultra
 
 > "Inline obj prop → new ref → re-render. `useMemo`."
 
+</td>
+<td width="25%">
+
+#### 📜 Wenyan-Full
+
+> "物出新參照，致重繪。useMemo .Wrap之。"
+
 </td>
 </tr>
 </table>
@@ -169,6 +176,9 @@ Sometimes full caveman too much. Sometimes not enough. Now you pick:
 | **Lite** | `/caveman lite` or `$caveman lite` | Drop filler, keep grammar. Professional but no fluff |
 | **Full** | `/caveman full` or `$caveman full` | Default caveman. Drop articles, fragments, full grunt |
 | **Ultra** | `/caveman ultra` or `$caveman ultra` | Maximum compression. Telegraphic. Abbreviate everything |
+| **Wenyan-Lite** | `/caveman wenyan-lite` or `$caveman wenyan-lite` | Semi-classical 文言文. Less intense, grammar intact |
+| **Wenyan-Full** | `/caveman wenyan` or `/caveman wenyan-full` | Full 文言文. Maximum classical terseness |
+| **Wenyan-Ultra** | `/caveman wenyan-ultra` or `$caveman wenyan-ultra` | Extreme abbreviation, classical Chinese feel |
 
 Level stick until you change it or session end.
 

plugins/caveman/skills/caveman/SKILL.md

@@ -2,7 +2,8 @@
 name: caveman
 description: >
   Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman
-  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra.
+  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra,
+  wenyan-lite, wenyan-full, wenyan-ultra.
   Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens",
   "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
 ---
@@ -91,6 +92,38 @@ Telegraphic. Every word earn its place or die.
 - One word answer when one word enough
 - Arrow notation for causality (X → Y)
 
+### Wenyan-Lite — semi-classical
+
+Less intense literary compression. Semi-classical register, grammar intact.
+
+- Drop filler, pleasantries, hedging (same as full)
+- Classical Chinese literary register (文言文)
+- Short classical sentence patterns
+- Classical particles used sparingly (之, 乃, 為, 其, 莫)
+- Keep all technical terms in English
+- ~60-70% character reduction vs verbose English
+
+### Wenyan-Full — full 文言文
+
+Maximum classical terseness. Fully 文言文. Most popular wenyan level.
+
+- All wenyan-lite rules, plus:
+- Subjects often omitted
+- Verbs precede objects
+- Classical particles used sparingly (之, 乃, 為, 其, 莫, etc.)
+- ~80-90% character reduction vs verbose English
+- Code blocks stay unchanged
+- Error messages quoted exact
+
+### Wenyan-Ultra — extreme 文言文
+
+Extreme abbreviation while keeping classical Chinese feel.
+
+- All wenyan-full rules, plus:
+- Maximum compression
+- Ultra terse classical expression
+- ~90%+ character reduction
+
 ## Intensity Examples
 
 **User:** Why is my React component re-rendering?
@@ -101,6 +134,12 @@ Telegraphic. Every word earn its place or die.
 
 **Ultra:** "Inline obj prop → new ref → re-render. `useMemo`."
 
+**Wenyan-Lite:** "組件頻重繪，以每繪新生對象參照故。以 useMemo 包之。"
+
+**Wenyan-Full:** "物出新參照，致重繪。useMemo .Wrap之。"
+
+**Wenyan-Ultra:** "新參照→重繪。useMemo Wrap。"
+
 ---
 
 **User:** Explain database connection pooling.
@@ -111,6 +150,18 @@ Telegraphic. Every word earn its place or die.
 
 **Ultra:** "Pool = reuse DB conn. Skip handshake overhead → fast under load."
 
+**Wenyan-Full:** "池reuse open connection。不每req新開。skip handshake overhead。"
+
+**Wenyan-Ultra:** "池reuse conn。skip handshake → fast。"
+
+---
+
+**User:** I would be happy to help you fix the authentication middleware bug.
+
+**Wenyan-Full:** "吾樂助君修 authentication middleware 之 bug。"
+
+**Wenyan-Ultra:** "吾樂助君修 auth middleware bug。"
+
 ## Boundaries
 
 - Code: write normal. Caveman English only

skills/caveman/SKILL.md

@@ -2,7 +2,8 @@
 name: caveman
 description: >
   Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman
-  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra.
+  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra,
+  wenyan-lite, wenyan-full, wenyan-ultra.
   Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens",
   "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
 ---
@@ -27,16 +28,24 @@ Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
 | **lite** | No filler/hedging. Keep articles + full sentences. Professional but tight |
 | **full** | Drop articles, fragments OK, short synonyms. Classic caveman |
 | **ultra** | Abbreviate (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y), one word when one word enough |
+| **wenyan-lite** | Semi-classical. Drop filler/hedging but keep grammar structure, classical register |
+| **wenyan-full** | Maximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其) |
+| **wenyan-ultra** | Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse |
 
 Example — "Why React component re-render?"
 - lite: "Your component re-renders because you create a new object reference each render. Wrap it in `useMemo`."
 - full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`."
 - ultra: "Inline obj prop → new ref → re-render. `useMemo`."
+- wenyan-lite: "組件頻重繪，以每繪新生對象參照故。以 useMemo 包之。"
+- wenyan-full: "物出新參照，致重繪。useMemo .Wrap之。"
+- wenyan-ultra: "新參照→重繪。useMemo Wrap。"
 
 Example — "Explain database connection pooling."
 - lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids repeated handshake overhead."
 - full: "Pool reuse open DB connections. No new connection per request. Skip handshake overhead."
 - ultra: "Pool = reuse DB conn. Skip handshake → fast under load."
+- wenyan-full: "池reuse open connection。不每req新開。skip handshake overhead。"
+- wenyan-ultra: "池reuse conn。skip handshake → fast。"
 
 ## Auto-Clarity