fix: address code review issues from Claude and GPT-5.2

- report/SKILL.md: add AskUserQuestion to allowed-tools
- validate_json.py: remove unused imports (List, Any)
- validate_json.py: sort output lists for deterministic order
- validate_json.py: limit recursion to category level only
- validate_json.py: add list-of-dict handling
- EN validate_json.py: remove Chinese from CATEGORY_MAPPING
- EN deep/SKILL.md: change output language from Chinese to English
- deep/SKILL.md: add slug handling for filenames
- report/SKILL.md: fix uncertain_fields -> uncertain naming
- README: add PyYAML dependency note

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

skills/research-en/report/SKILL.md

@@ -1,6 +1,6 @@
 ---
 description: Summarize deep research results into markdown report, cover all fields, skip uncertain values.
-allowed-tools: Read, Write, Glob, Bash
+allowed-tools: Read, Write, Glob, Bash, AskUserQuestion
 ---
 
 # Research Report - Summary Report
@@ -75,7 +75,7 @@ CATEGORY_MAPPING = {
 Collect fields that exist in JSON but not defined in fields.yaml, put in "Other Info" category. Note to filter:
 - Internal fields: `_source_file`, `uncertain`
 - Nested structure top-level keys: `basic_info`, `technical_features` etc.
-- `uncertain_fields` list: Display each field name on separate line, don't compress into one line
+- `uncertain` array: Display each field name on separate line, don't compress into one line
 
 **5. Uncertain Value Skipping**
 Skip conditions: