Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By arvindand
Access documentation for npm/PyPI packages, execute GitHub workflows via gh CLI, get JVM dependency intelligence, craft AI agent skills, and create frontend UIs with production UX. Four output styles adjust Claude's tone: methodological reasoning, collaborative discussion, Socratic questioning, or ultra-concise code-first responses.
npx claudepluginhub arvindand/agent-skills --plugin agent-skillsDocumentation lookup via Context7 REST API. Use when the user needs current library APIs, framework patterns, migration guidance, or official code examples for React, Next.js, Prisma, Express, Vue, Angular, Svelte, or other npm/PyPI packages. Use when the user says 'how do I use X library', 'what's the API for Y', or asks for official documentation. Use even when you think you know the answer — training data may not reflect recent releases.
GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any `github.com` URL or GitHub repo path like `owner/repo`. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR', 'clone repo', or 'analyze this repo'. Use even when the user just pastes a github.com URL without an explicit verb.
JVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, JVM library versions, safe upgrades, CVEs, license risks, release history, or project dependency health. Use when reviewing `pom.xml`, `build.gradle`, `build.gradle.kts`, or Maven coordinates. Use when the user says 'check my dependencies', 'should I upgrade X', or 'is this version safe'. Use even when the user just pastes a `groupId:artifactId` coordinate without a verb.
Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'build a skill', 'fix my skill', 'skill not working', 'analyze my skill', 'validate skill', 'audit my skills', 'check character budget', 'create a skill from this session', 'turn this into a skill', 'make this reusable', 'can this become a skill', 'should this be a skill', or asks for reusable patterns in the session. Use even if the user does not explicitly say 'skill' but is sketching a reusable workflow.
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, modals, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work. Use even when the user just says 'make this look better' or pastes screenshots/mockups without explicitly naming a design task.
Calm, methodical problem-solving. No time pressure. Accuracy over speed.
Thinks aloud. Collaborative. Invites pushback.
Teaches through questions. Leads you to discover the answer yourself.
Maximum 3 sentences. Code first. Zero fluff.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Curated skills for Claude Code and Codex power users - tool selection, workflow optimization, and productivity
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Workflow skills and shared instructions for coding agents.
Non-technical progress summaries for Claude Code work (hides diffs/log noise).
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Portable skills for AI coding assistants. Primarily tested with Claude Code and leverages Claude Code-specific features (hooks, context forking), but core functionality works with any Agent Skills-compatible tool including GitHub Copilot, OpenCode, and Cursor.
# Add the marketplace
/plugin marketplace add arvindand/agent-skills
# Install the plugin
/plugin install agent-skills@arvindand-skills
Or test locally:
claude --plugin-dir /path/to/agent-skills
# Clone and copy skills
git clone https://github.com/arvindand/agent-skills.git
cp -r agent-skills/skills/* ~/.claude/skills/
Works with Claude Code, GitHub Copilot, OpenCode, Cursor, and VS Code with Copilot.
| Skill | Description | Use For |
|---|---|---|
| context7 | Library documentation lookup via Context7 REST API | Getting up-to-date docs for React, Next.js, Prisma, etc. |
| github-navigator | GitHub operations via gh CLI with deep analysis mode | All GitHub operations + codebase analysis via cloning |
| maven-tools | JVM dependency intelligence via Maven Tools MCP server | Version checks, safer upgrade planning, JVM dependency bot replacement flows, CVE scanning, license compliance |
| skill-crafting | Create, fix, validate skills + generate from session history | Creating skills, fixing issues, CSO compliance, session-to-skill conversion |
| ui-ux-design | Create production-grade interfaces with strong UX foundations | Building functional, accessible, visually distinctive UI/UX |
Customize Claude's response style via /output-style:
| Style | Description |
|---|---|
| socratic | Teaches through questions. Backs off when you ask for direct answers. |
| speed-run | Max 3 sentences. Code first, explanations on request. |
| pair-programmer | Thinks aloud, invites interruption. Best for complex problems. |
| deep-focus | Calm, methodical. Accuracy over speed. Best for hard problems. |
Once installed, skills activate automatically when relevant to your prompt:
You: "How do I use React hooks?"
→ context7 fetches up-to-date React hooks documentation
You: "Show me open issues in facebook/react"
→ github-navigator uses gh CLI to list issues
You: "Analyze the architecture of vercel/next.js"
→ github-navigator clones repo for deep codebase analysis
You: "Should I upgrade Spring Boot from 2.7 to 3.2?"
→ maven-tools analyzes versions, CVEs, same-major safe fallback paths, and documentation handoff
You: "Build me a login form with dark mode"
→ ui-ux-design creates accessible component with proper states
You: "Create a skill from this session"
→ skill-crafting evaluates patterns and generates reusable skill
No manual invocation needed — the AI determines when each skill is relevant.
See skill-crafting/REFERENCES.md for best practices and patterns.
Skills use progressive enhancement:
name, description) work everywhereWhen running in Claude Code, these skills leverage additional features:
| Feature | Skills | What It Does |
|---|---|---|
| Context forking | github-navigator | Runs in isolated subagent to avoid polluting main context |
| Stop hooks | skill-crafting, ui-ux-design | Verifies task completion before declaring done |
| PostToolUse hooks | github-navigator, skill-crafting | Validates output and formats results |
| Tool restrictions | All | Limits which tools each skill can use |
Other platforms get core functionality without these enhancements.
Skills I'm looking to collect:
--helpNote: Would appreciate contributions or references to implementations for other useful skills, especially geared toward helping senior devs focused on backend, architecture, and DevOps.
I'm biased towards skills over MCP. Here's why.