By sjawhar
Personal development workflow tools: code review agents, jj/git workflows, CI automation, and productivity skills
Re-anchor work on the original user goal when scope drifts.
Stop goal evasion and require immediate remediation paths.
Use when buying groceries, shopping on smrey.com, or placing delivery orders from Supermercados Rey.
Run end-to-end verification now and provide evidence before any completion claim.
Find subtle bugs, edge cases, and potential failure modes in recently written code. Use after implementing a feature to stress-test the logic. Excels at adversarial thinking.
Background agent that maintains and updates CLAUDE.md files based on project changes. Invoked at session start and after major milestones (feature completion, refactoring, new dependencies, architecture changes). Works independently without interrupting other agents.
Design system architecture, make structural decisions, evaluate trade-offs between approaches. Use when balancing simplicity with extensibility, decomposing complex modules, or choosing technologies.
Review code for adherence to project guidelines, style guides, and best practices. Use proactively after writing or modifying code, especially before committing changes or creating pull requests.
Analyze code for simplification opportunities: abstractions, unnecessary complexity, more elegant solutions. Use after writing substantial code to ensure it's as clean and maintainable as possible.
Run code quality agents on recent changes
Use when scraping websites, extracting structured data from listing sites, running prebuilt scrapers/actors, or automating stubborn web research workflows. Make sure to use this whenever apartment hunting, marketplace scraping, anti-bot-resistant extraction, or batch website data collection would benefit from a dedicated scraping platform rather than ad hoc browser clicks.
Use when browsing websites, clicking elements, filling forms, taking screenshots, reading page content, or automating browser interactions via BrowserMCP
Harden an EC2 instance used as a development machine
Collaborative code review: you narrate, Claude tracks, challenges your ideas, then we generate a friendly GitHub review together
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
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.
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
npx claudepluginhub sjawhar/dotfiles --plugin sjawharOpenCode orchestration for autonomous development
Skills for writing Pivot pipeline stages - file I/O annotations, loaders, and output types
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions
General purpose Claude Code toolkit with research agents, skills, and introspection commands
Non-technical progress summaries for Claude Code work (hides diffs/log noise).
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
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.
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.