- Separate caller's format and standard format as if-else branches
- Add Sources and References (ALWAYS REQUIRED) to both branches
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move Scenario-Specific Strategies into Query Generation Phase (1.1-1.3)
- Merge Comparative Research into Best Practices (1.2)
- Add Academic Sources to Source Prioritization
- Merge Self-Verification and Escalation Strategy into Quality Assurance
- Restructure Standard Output Format with PART 1/PART 2 and example
- Add caller's format priority to Compilation Standards
- Update Core Capabilities with new sources
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Restructure skills/research-zh and skills/research-en to flat layout
- Each skill now in its own directory (research, research-deep, etc.)
- Update installation: cp -r skills/research-zh/* ~/.claude/skills/
- Update command references from /research:deep to /research-deep
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add user-invocable: true to all SKILL.md files (10 files)
- Update README with new command format (/research:deep)
- Keep backward compatibility notes for older versions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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>
- Translate all comments and docstrings to English
- Translate CLI help text and output messages to English
- Keep CATEGORY_MAPPING bilingual for compatibility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace raw YAML/JSON with plain language explanations
- Add "What happens" and "You get" for each phase
- More intuitive for newcomers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Show actual outline.yaml, JSON output, and report
- Keep examples concise and elegant
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- README.md for English (default)
- README.zh.md for Chinese
- Add language switch links at top
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add note about slash command conflict with built-in commands
- Update all command examples to use 'run' prefix
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add detailed explanations for each workflow phase
- Describe outputs for each stage
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rename skills/research to skills/research-en (English version)
- Add skills/research-zh (Chinese version with SKILL.md structure)
- Update README.md with bilingual documentation
- Add web-search-agent.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add AskUserQuestion for Step 1 framework confirmation
- Add TOC summary field selection in report generation
- Add detail_level hierarchy (brief -> moderate -> detailed)
- Add Chinese output requirement for JSON values
- Add long text formatting rules
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add validate_json.py for field coverage validation
- Add hard constraints and one-shot examples to prompt templates
- Add parameter retrieval sections before prompts
- Translate all SKILL.md files to English
- Update report.md with technical requirements
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New report command to generate markdown from JSON results
- Generates Python script for conversion
- Creates report with TOC and anchor links
- Skips uncertain fields and uncertain array
- Update deep.md with prompt template format
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add uncertain field to fields.yaml (reserved, auto-filled in deep phase)
- Hard constraint: mark uncertain values with [bu que ding] in field value
- Hard constraint: list uncertain field names in JSON uncertain array
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add items_per_agent field to control items per agent
- Confirm via AskUserQuestion in /research phase
- Deep research reads from outline config directly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Output to {topic}/ directory structure
- fields.yaml now independent file for field definitions
- outline.yaml contains items + execution config
- Deep research agents read fields.yaml independently (hard constraint)
- Update README with new directory structure
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
