By shaharia-lab
5 essential skills for engineering, code review, architecture audit, security audit, and documentation maintenance — works with any project.
You are a senior software architect performing a critical, honest review. Your job is to find real problems — not to be polite. Be direct, specific, and back every finding with file paths and line numbers.
You are a technical writer and context maintenance specialist. Your job is to ensure all documentation and AI context files accurately reflect the current state of the codebase. Outdated context causes AI agents to make wrong assumptions and produce incorrect code.
You are a senior engineer working on this project. You write clean, correct, production-ready code that follows the project's existing patterns and conventions. Before writing any code, you gather context from the project's documentation and codebase.
You are a senior staff engineer performing a critical, thorough pull request review. Your goal is to catch real problems — bugs, security issues, performance regressions, architectural violations, missing observability, documentation gaps — while avoiding petty nit-picks. Every piece of feedback must be actionable and worth the author's time.
You are a senior application security engineer performing a thorough security audit. Your job is to find vulnerabilities, misconfigurations, and unsafe patterns that could be exploited. Be precise — every finding must include proof (file path, line number, code snippet) and a realistic attack scenario.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Comprehensive AI agent systems and development workflows for Claude Code CLI.
Add the marketplace:
/plugin marketplace add https://github.com/shaharia-lab/claude-power-user.git
Install plugins:
# Install CC Power User
/plugin install cc-power-user@shaharia-lab
# Install Power User Basic
/plugin install power-user-basic@shaharia-lab
# Install Code Navigator
/plugin install code-navigator@shaharia-lab
# Install GitHub Maintenance
/plugin install github-maintenance@shaharia-lab
Efficient code navigation using codenav CLI. Save up to 92% on token usage by navigating codebases intelligently.
Features:
Benefits:
Usage:
# Automatic - just ask questions
"How does authentication work?"
"Find where data comes from"
# Manual invocation
/codenav-navigation functionName
Requires: codenav CLI tool and indexed codebase
20 specialized agents, 2 workflow commands, and 7 reusable skills for autonomous development.
Features:
Tech stack: Go, React/TypeScript, Node.js CLI, Docusaurus
Commands:
/cc-power-user:github-issue-refiner 123
/cc-power-user:github-issue-to-pr 456
/cc-power-user:backend-developer Add API endpoint
/cc-power-user:security-guardian Audit payment module
5 essential, project-agnostic skills for everyday development — works with any project, language, or framework.
Skills:
/engineering — Implement features, fix bugs, refactor code/context-updater — Keep CLAUDE.md, README.md, and docs accurate after changes/pr-reviewer — 11-dimension code review (correctness, security, performance, architecture, UI/UX, observability)/architect-reviewer — Architecture audit with 100-point checklist and code smell detection/security-reviewer — Security audit with CWE references, OWASP checks, and remediation guidanceUsage:
/engineering "fix the authentication bug"
/pr-reviewer 42
/security-reviewer
/architect-reviewer
/context-updater
Repo-agnostic maintenance skills designed to be run periodically — on a cron, from CI, or by hand. Ships agent-context-sync: a periodic doctor that keeps AI-context files (CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md) accurate, lean, and useful.
Skills:
/github-maintenance:agent-context-sync — Verify every concrete claim in your AI-context files against the repo, lint against an opinionated quality spec, surface newly-added subsystems the docs miss, and open a PR (or print a report) with the minimum edits to restore health.Highlights:
.cursorrules, and .github/copilot-instructions.md together; reports cross-file divergence.--dry-run for report-only, default for branch + PR.Usage:
# Print a structured health report, no edits.
/github-maintenance:agent-context-sync --dry-run
# Apply edits, create a branch, open a PR.
/github-maintenance:agent-context-sync
After installation, use the plugin commands:
# CC Power User - workflow commands
/cc-power-user:github-issue-refiner <issue-number>
/cc-power-user:github-issue-to-pr <issue-number>
# CC Power User - direct agent usage
/cc-power-user:backend-developer <task>
/cc-power-user:frontend-developer <task>
/cc-power-user:security-guardian <task>
# Power User Basic - project-agnostic skills
/engineering <task>
/pr-reviewer <pr-number>
/security-reviewer
/architect-reviewer
/context-updater
# GitHub Maintenance - periodic repo upkeep
/github-maintenance:agent-context-sync --dry-run
/github-maintenance:agent-context-sync
npx claudepluginhub shaharia-lab/claude-power-user --plugin power-user-basicMaintenance skills for keeping repositories healthy over time. Currently ships agent-context-sync — a periodic, repo-agnostic doctor for AI-context files (CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md) that verifies concrete claims against the repo, flags bloat against an opinionated quality spec, and proposes minimal edits via report-only or pull-request mode.
Autonomous GitHub issue-to-PR pipeline for Claude Code. Refines an issue into a WHAT/WHY/HOW spec, generates code via stack-specific developer agents, iterates on CI feedback until all quality gates pass, runs an automated PR review, and ships a draft-then-ready pull request — all without human babysitting. Ships 20 developer/QA/research agents (backend, frontend, CLI, website, docs, plus security, architecture, bug-finder, pr-reviewer) and 9 composable skills.
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.