Highlight differences from official Anthropic docs:
- Visual tutorials with diagrams vs reference docs
- Production-ready templates vs basic snippets
- Progressive learning path vs feature-organized
- Guided roadmap with time estimates
- Make agent self-contained by embedding rules (no external file reference)
- Remove redundant sections and verbose examples
- Consolidate evaluation categories into concise checklist
- Simplify output format template
- Replace simple Stop-only context-usage hook with hook pair pattern
- Add UserPromptSubmit + Stop hook combination for tracking delta
- Include both char-estimation and tiktoken versions as separate files
- Show how to use session_id for isolated state tracking
The hook was converting total_chars to string before calculating tokens,
resulting in ~0 tokens reported. Fixed to calculate directly from char count.
- Remove unused estimate_tokens() function
- Calculate tokens as total_chars // 4 directly
- Archive fix-context-usage-hook change
- Add Managing Skills section (viewing, testing, updating, removing)
- Expand Troubleshooting with debugging tips for skipped skills, YAML errors, permissions
- Add Version History best practice section with example
- Enhance allowed-tools documentation with security use cases
- Add Multi-File Skill Example showing complex skill structure
- Add version history to code-review SKILL.md example
Based on: https://code.claude.com/docs/en/skills
- Update README with all official features:
- Built-in subagents (General-Purpose, Plan, Explore)
- /agents command for interactive management
- CLI-based configuration with --agents flag
- Resumable agents with agentId
- File locations and priority order
- Configuration fields (name, description, tools, model, permissionMode, skills)
- Chaining subagents for multi-agent workflows
- Update existing subagent examples to new format:
- Add model field
- Update YAML frontmatter format
- Add proactive usage hints in descriptions
- Add new example subagents:
- debugger.md - Root cause analysis specialist
- data-scientist.md - SQL/BigQuery data analysis expert
Based on: https://code.claude.com/docs/en/sub-agents
Add Example 6 showing how to create a hook that reports context/token
usage after each Claude response:
- Python script reads transcript_path to access conversation history
- Estimates tokens using ~4 chars/token heuristic
- Outputs one-line report: "Context: ~45k/200k tokens (77% remaining)"
- Documents both Stop and UserPromptSubmit hook configurations
- Explains limitations (estimate vs exact /context command)
- Added blog-posts/ to .gitignore to prevent tracking of blog-related files.
- Included rule to ignore all EPUB files in the root directory for cleaner repository management.
- Migrate SKILL.md files to new format (lowercase names, consolidated descriptions)
- Remove deprecated fields: version, tags, when_to_use
- Add Creating Custom Skills section with format requirements
- Add Troubleshooting Guide and team sharing sections
- Enhance Best Practices with specific examples
- Remove Pre-built Skills section (no longer in official docs)
- Introduced a new script to build an EPUB from markdown files, enhancing documentation accessibility.
- Added a GitHub Actions workflow for automated EPUB builds on version tag pushes.
- Created the initial EPUB file 'claude-howto-guide.epub' for distribution.
This update streamlines the process of creating and releasing the Claude How-To guide in EPUB format.
Luong NGUYEN