A curated collection of AI agent skills for Claude Code. Layers on top of superpowers to add industry-standard code review, security auditing, and project management.
- superpowers plugin installed (core dependency — all NecturaLabs skills require it)
/plugin marketplace add NecturaLabs/AgentSkills
/plugin install necturalabs@necturalabs
After installation, skills are available as necturalabs:<skill-name>. Slash commands (e.g., /necturalabs:code-review) appear in auto-complete.
/plugin marketplace update necturalabs
/plugin uninstall necturalabs@necturalabs
/plugin marketplace remove necturalabs
| Skill | When to invoke |
|---|---|
using-necturalabs — Initializes all skills, verifies dependencies, sets up review triggers |
Conversation start, agent handoffs |
iterative-code-review — Code review (Google, Clean Code, SOLID, Fowler) until clean pass |
After any code changes, before commit/merge |
iterative-security-audit — Security audit (OWASP, CWE, NIST, CERT) until clean, then code review |
When changes touch security-sensitive code |
agent-context-loader — Loads global CLAUDE.md and project AGENTS.md into context |
On init, after context switches |
agents-md-manager — Creates or updates project AGENTS.md from codebase analysis |
Manual (/agents-md-manager) or after plan execution |
git-workflow — Conventional Commits format and git worktree isolation |
When committing or starting multi-commit work |
update-plugins — Concurrently updates plugin marketplaces and installed plugins |
Manual (/update-plugins) or when user asks to update |
docs-manager — Creates and maintains project docs/ with ADRs, design docs, guides |
Manual (/docs-manager) or when user asks to document |
using-necturalabsruns at conversation start — checks superpowers dependency, loads context, sets up mandatory review triggers- Code review must run after every code change, before committing or claiming work is done
- Security audit must run when changes touch security-related code (auth, crypto, input validation, etc.)
- When both apply: security audit first → code review second → combined summary
- Both produce a score (1-100) with positives, negatives, and informational findings
The docs-manager skill creates and maintains a docs/ folder following industry standards:
- ADRs (Architecture Decision Records, MADR 4.0) — append-only records of significant technical decisions with context, alternatives, and rationale
- Design docs (Google-style) — living documents for designs with goals, non-goals, alternatives, and cross-cutting concerns
- How-to guides — task-oriented step-by-step procedures (deployment, onboarding, debugging)
- Reference material — research, specs, and data models that informed decisions
Structure is scale-adaptive — directories are created only when the first document of that type is written. Every document has YAML frontmatter with status and last-reviewed date for staleness tracking. Invoke with /docs-manager or ask Claude to document a decision or design.
See CONCEPTS.md for a guide on Skills, MCP, LSP, and RAG — what they are, when to use each, and how they work together.
LSP gives Claude Code IDE-level code intelligence — semantic navigation instead of text-based grep. Highly recommended for code review and security audit accuracy.
Add to ~/.claude/settings.json:
{
"env": {
"ENABLE_LSP_TOOL": "1"
}
}Also add to your shell profile (.bashrc / .zshrc / PowerShell $PROFILE) as a fallback:
export ENABLE_LSP_TOOL=1| Language | Install |
|---|---|
| TypeScript/JS | npm i -g typescript-language-server typescript |
| Python | npm i -g pyright or pip install pyright |
| Go | go install golang.org/x/tools/gopls@latest |
| Rust | rustup component add rust-analyzer |
| C# | dotnet tool install -g csharp-ls |
| C/C++ | Install clangd via LLVM (brew install llvm / choco install llvm / apt install clangd) |
| Lua | brew install lua-language-server or download from GitHub releases |
claude plugin marketplace update claude-plugins-official
claude plugin install typescript-lsp@claude-plugins-official
claude plugin install pyright-lsp@claude-plugins-official
# ... repeat for each language you needVerify they're enabled:
claude plugin listIf any show Status: disabled:
claude plugin enable <plugin-name>Restart for changes to take effect. Verify in debug logs at ~/.claude/debug/latest — look for Total LSP servers loaded: N.
| Problem | Fix |
|---|---|
| LSP tool not available | Ensure ENABLE_LSP_TOOL=1 in settings.json, restart |
| Plugin not found | Run claude plugin marketplace update claude-plugins-official |
| Plugin disabled | Run claude plugin enable <name>, restart |
| Binary not found | Verify with which <binary>, ensure it's in PATH |
Once configured, Claude Code gains these tools:
goToDefinition/goToImplementation— jump to sourcefindReferences— all usages across the codebaseworkspaceSymbol— find any symbol by namedocumentSymbol— list all symbols in a filehover— type info without reading the fileincomingCalls/outgoingCalls— call hierarchy
This repo includes a recommended global CLAUDE.md. Copy it to your global Claude config:
~/.claude/CLAUDE.md
On Windows: C:\Users\<YourUsername>\.claude\CLAUDE.md
MIT