Claude Code expects repository field to be a string, not an object.
Error: repository: Expected string, received object
Changed from:
"repository": { "type": "git", "url": "..." }
To:
"repository": "https://github.com/czlonkowski/n8n-skills"
This follows Claude Code's plugin.json schema where repository is a simple
string URL rather than npm's package.json format.
Distribution package regenerated with corrected plugin.json.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en
Change source from "." to "./" to comply with Claude Code marketplace
schema validation requirement.
Error: plugins.0.source: Invalid input: must start with "./"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en
Clean up all README files to focus on user value rather than research metrics.
Remove telemetry numbers and research context that isn't useful for end users.
## Changes
**Main README.md**:
- Removed "Based on 447,557 real MCP tool usage events" section
- Replaced failure rate metrics with user benefits
- Removed entire "Data-Driven Design" section with telemetry statistics
- Fixed all GitHub links to use czlonkowski/n8n-mcp
- Updated "Repository Stats" to "What's Included" with user-focused content
**dist/README.md**:
- Changed "HIGHEST PRIORITY" to "recommended to install first"
- Added link to n8n-mcp repository
- More user-friendly language throughout
**Skill README.md files**:
- n8n-mcp-tools-expert: Removed "447,557 events", "20% failure rate" metrics
- n8n-workflow-patterns: Removed "Based on 31,917 real workflows"
- n8n-validation-expert: Removed "From 7,841 validate → fix cycles"
- Replaced frequency percentages with priority levels (Highest/High/Medium/Low)
- Reframed "Success Metrics" as "What You'll Learn"
- Changed "Critical Insights from telemetry" to "Key Insights" for users
## Kept What Matters
- Template counts (2,653+) - this is a feature, not research
- Node counts (525+) - this is a feature
- Practical insights (validation takes 2-3 iterations, false positives exist)
- Best practices and common patterns
## Result
Documentation now focuses on what users need to know to use the skills
effectively, rather than the research that informed their creation.
All distribution packages regenerated with cleaned documentation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en
