By agent-sh
Find where to contribute to any project - matches developer skills to test gaps, stale docs, bugspots, and open issues
npx claudepluginhub agent-sh/agentsys --plugin can-i-helpContributor guidance for any project - matches developer skills to test gaps, stale docs, bugspots, and open issues.
Part of the agentsys ecosystem.
Point a contributor at a project and get specific, data-backed suggestions for where they can help. Collects project health signals automatically, asks about the developer's background, then matches skills to needs with concrete next steps.
agentsys install can-i-help
/can-i-help
Three phases run in sequence:
Beyond base project data (manifest, structure, git), the collector gathers signals specific to contribution opportunities:
| Signal | Source | What it reveals |
|---|---|---|
| Good-first areas | repo-intel can-i-help | Areas with clear patterns, low coupling, easy entry |
| Test gaps | repo-intel test-gaps | Hot source files without co-changing test files |
| Doc drift | repo-intel doc-drift | Documentation with low code coupling (likely stale) |
| Bugspots | repo-intel bugspots | Files with high bug-fix density |
| Open issues | gh issue list | GitHub issues with labels and assignees |
The Opus agent tailors recommendations based on developer profile:
| Developer says... | Recommended areas |
|---|---|
| "New to the stack" | Good-first areas with clear patterns and examples |
| "Experienced developer" | Hard problems in pain-point areas, architectural improvements |
| "I want to write tests" | Test gaps in frequently-changed files |
| "I want to fix bugs" | Bugspot files + relevant open issues |
| "I want to improve docs" | Stale documentation with concrete code examples |
Each recommendation includes:
/can-i-help # Current repo, normal depth
/can-i-help /path/to/repo # Specific repo
/can-i-help --depth=deep # Include repo-map AST data
The collector passes on 100 open-source repositories across 8 languages (JS/TS, Rust, Go, Python, C/C++, Java, Deno). Contributor signal queries validated on 8 repos with manual cross-checking against actual code: phantom directories filtered, source code prioritized over test/doc dirs, generated data excluded from recommendations.
gh) for open issues (optional)MIT
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Uses power tools
Uses Bash, Write, or Edit tools
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Complete developer toolkit for Claude Code
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use