boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Validate and package a Claude Code Skill into a distributable zip file
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/package-skillContext preview
What this command does when you run it.
Validate and package a Claude Code Skill into a distributable zip file
Validate and package a Claude Code Skill into a distributable zip file
This command validates and packages an existing skill for distribution. Follow these steps:
1. **Identify the skill to package**
2. **Pre-package checks**
1. **Run quick validation**
2. **Run comprehensive validation** (if quick validation passes)
3. **Review validation results**
1. **Execute packaging script**
python .claude/commands/skills/scripts/package_skill.py <skill-path> [output-dir]
2. **Package creation process**
3. **Verify package**
1. **Personal distribution**
2. **Team distribution**
3. **Public distribution**
# Personal skills ls ~/.claude/skills/ # Project skills ls .claude/skills/
python .claude/commands/skills/scripts/quick_validate.py <skill-path>
Expected output:
.claude/commands/skills/scripts/validate-skill.sh <skill-path>
Expected output:
# Package to current directory python .claude/commands/skills/scripts/package_skill.py ~/.claude/skills/my-skill # Package to specific directory python .claude/commands/skills/scripts/package_skill.py ~/.claude/skills/my-skill ./dist
Expected output:
🔍 Validating skill... ✅ Skill validation passed! 📦 Creating package... Added: my-skill/SKILL.md Added: my-skill/scripts/helper.py Added: my-skill/references/api-docs.md ... ✅ Successfully packaged skill! 📦 Package: ./my-skill.zip 📊 Files: 8 💾 Size: 0.15 MB 📤 Ready for distribution!
The packaging script checks:
Include with your packaged skill:
# Installing {{SKILL_NAME}}
## Personal Installation
1. Download {{skill-name}}.zip
2. Extract to ~/.claude/skills/
3. Restart Claude Code
## Project Installation
1. Extract to .claude/skills/ in your project
2. Commit to version control
3. Team members get skill on pull
## Verification
After installation, test with:
"Use the {{SKILL_NAME}} skill to {{example task}}"For skill updates: 1. Update skill files 2. Document changes in SKILL.md 3. Increment version if using versioning 4. Re-package with same process 5. Distribute new package
**Issue**: Package script reports validation errors
**Solution**: 1. Run quick_validate.py to see specific errors 2. Fix reported issues 3. Re-run validation 4. Try packaging again
**Issue**: Zip file not generated
**Possible causes**:
**Issue**: Warning about non-executable scripts
**Solution**:
chmod +x <skill-path>/scripts/*.py chmod +x <skill-path>/scripts/*.sh
**Issue**: Package is very large
**Solutions**:
1. **Complete all TODOs** before packaging 2. **Test the skill** thoroughly before distribution 3. **Document dependencies** clearly 4. **Include examples** that work 5. **Version your skills** for updates 6. **Test installation** on clean system 7. **Include uninstall instructions** if complex
# Validate first python .claude/commands/skills/scripts/quick_validate.py ~/.claude/skills/commit-helper # Package if valid python .claude/commands/skills/scripts/package_skill.py ~/.claude/skills/commit-helper # Result: commit-helper.zip created
# Create dist directory mk
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles:…