Npm Research
- 1 installs
- 1 repo stars
- Updated March 10, 2026
- ofershap/mcp-server-npm-plus
Helps with ai & agent building tasks.
About
npm-research is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
- npm-research
- AI & Agent Building
- AI-coding skill
Npm Research by the numbers
- 1 all-time installs (skills.sh)
- Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ofershap/mcp-server-npm-plus --skill npm-researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 1 |
| Last updated | March 10, 2026 |
| Repository | ofershap/mcp-server-npm-plus ↗ |
What it does
Helps with ai & agent building tasks.
Files
npm Package Research via MCP
Use this skill for in-depth npm package research: bundle sizes, vulnerability scanning, download comparisons, and dependency trees. No API keys needed.
Available Tools
| Tool | What it does |
|---|---|
search | Search npm packages by query |
package_info | Detailed info: description, license, repo, dependencies |
downloads | Download stats for a package |
compare_downloads | Compare download counts across multiple packages |
bundle_size | Bundle size (minified + gzip) via Bundlephobia |
vulnerabilities | Known vulnerability info and advisory links |
dependency_tree | Show direct dependencies as a tree |
download_trends | Daily breakdown with sparkline visualization |
Workflow
1. For "which library?" questions: compare_downloads + bundle_size for each candidate 2. For security audits: vulnerabilities on each dependency 3. For adoption analysis: download_trends to see growth patterns 4. For dependency footprint: dependency_tree before adding a new package
Key Patterns
bundle_sizecalls Bundlephobia — some packages may not be analyzable (native modules, very large packages)compare_downloadsaccepts multiple package names — ideal for "zustand vs jotai vs valtio" comparisonsvulnerabilitieschecks npm audit advisories — always run this before recommending a packagedownload_trendsincludes a text sparkline for quick visual trend assessment
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10AI & Agent Buildingagents