chore: refactor agent to skill-first; structured skills dirs; enhance ReAct and tool logs

README.md

@@ -26,6 +26,7 @@ Now supports mutually exclusive message channels:
 	- If `telegram`: set `TELEGRAM_BOT_TOKEN`, keep `FEISHU_*` empty.
 	- If `feishu`: set `FEISHU_APP_ID` and `FEISHU_APP_SECRET`, keep `TELEGRAM_BOT_TOKEN` empty.
 3. Set log level with `LOG_LEVEL=debug|info|warn|error`.
+	- To inspect full skill/tool execution content and detailed ReAct step traces, use `LOG_LEVEL=debug`.
 4. Configure knowledge and reasoning:
 	- `SOUL_PATH` for bot personality markdown.
 	- `SKILLS_DIR` for skills markdown directory.
@@ -45,22 +46,13 @@ go run ./cmd/bot
 
 ## Telegram Usage
 
-- Normal text: forwarded to LLM with compressed recent memory.
-- Agent uses ReAct loop and may call tools automatically before final answer.
-- Tool call command:
-
-```text
-/tool <name> <input>
-```
-
-Examples:
-
-```text
-/tool shell pwd
-/tool file read ./workspace/note.txt
-/tool file write ./workspace/note.txt
-hello world
-```
+- Normal text enters unified agent pipeline:
+	1. Receive message and load recent memory context
+	2. Match relevant skill(s) from `skills/`
+	3. If no skill matched, respond via direct LLM
+	4. If skill matched, run ReAct and call tools (`shell` / `file`) only when needed
+	5. Return final answer
+- No `/tool ...` command is required for normal use.
 
 ## Feishu Usage
 
@@ -71,7 +63,7 @@ hello world
 
 - Soul file default path: `bot_context/soul.md`
 - Skills directory default path: `skills/`
-- Add new markdown files into `skills/` to describe capabilities; they are loaded at startup.
+- Skill format uses subdirectories: `skills/<skill_name>/skill.md`
 
 ## Security Notes