npm-publishing
Use when publishing npm packages - covers package.json configuration, versioning, and provenance
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install mcclowes/lea/npm-publishingskilz install mcclowes/lea/npm-publishing --agent opencodeskilz install mcclowes/lea/npm-publishing --agent codexskilz install mcclowes/lea/npm-publishing --agent geminiFirst time? Install Skilz: pip install skilz
Works with 22+ AI coding assistants
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/mcclowes/leacp -r lea/.claude/skills/npm-publishing ~/.claude/skills/Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
command-name
by anthropics
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components"...
mcp-integration
by anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Contex...
rule-identifier
by anthropics
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs g...
bloblang-authoring
by redpanda-data
This skill should be used when users need to create or debug Bloblang transformation scripts. Trigger when users ask about transforming data, mappi...
Agentic Skill Details
- Repository
- lea
- Stars
- 3
- Type
- Technical
- Meta-Domain
- productivity
- Primary Domain
- json
- Market Score
- 16
Agent Skill Grade
B Score: 89/100 Click to see breakdown
Score Breakdown
Areas to Improve
- Second-person in README
- Missing workflow template
- No error scenarios
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 2026-01-24
Developer Feedback
I found your npm-publishing skill while reviewing package tooling approaches—the way you've structured the package.json validation logic is particularly clean. At 89 points, you're hitting solid ground, but I'm curious what you're doing differently compared to standard publishing workflows that warranted this depth of documentation.
Links:
The TL;DR
You're at 89/100, B grade—solidly production-ready. This is based on Anthropic's best practices for agentic skills. Your strongest area is Progressive Disclosure Architecture (27/30)—the SKILL.md is genuinely concise with proper delegation to reference files. Weakest spots are Spec Compliance (12/15) and Utility (18/20), where you're missing trigger phrases and complete workflow templates.
What's Working Well
- Dense, practical content: Your code examples earn their tokens without fluff. The scopes.md and tags.md references are exactly one level deep—textbook PDA structure.
- Clear command patterns: The versioning and publishing commands flow logically with validation steps (npm pack, dry-run). The prepublishOnly hook examples show real feedback loops.
- Strong npm specifics: You're covering real pain points—provenance badges, exports field configuration, scoped packages with --access public, dist tags. That's the kind of depth that matters.
- Consistent terminology: "npm/package.json/versioning" runs through everything without wavering.
The Big One: Missing Complete Workflow
Your skill jumps between topics—versioning here, publishing there, validation scattered—but doesn't show a human-readable end-to-end flow. Someone publishing their first package needs: npm login → version bump → validation → publish → verification.
Why it matters: Right now, use...
Browse Category
More productivity Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?
Report Security Issue
Thank you for helping keep SkillzWave secure. We'll review your report and take appropriate action.
Note: For critical security issues that require immediate attention, please also email security@skillzwave.ai directly.