eyadsibai

eyadsibai/ltk

Plugin Claude Code

LTK Plugin Collection - Development Mode (ltk-core only). Use install.sh for full installation.

eyadsibai/ltk

Settings file Claude Code

Agent settings declaring 4 allowed tools.

eyadsibai/ltk

MCP server Claude CodeCodexCursor +2

Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package. Needs 1 environment variable to run.

eyadsibai/ltk

MCP server Claude CodeCodexCursor +2

MCP server "sqlite" as configured in eyadsibai/ltk. Runs locally from the @modelcontextprotocol/server-sqlite npm package.

eyadsibai/ltk

MCP server Claude CodeCodexCursor +2

Lets the agent inspect a PostgreSQL database schema and run read-only SQL queries against it. Runs locally from the @modelcontextprotocol/server-postgres npm package. Needs 1 environment variable to run.

eyadsibai/ltk

Instructions file

Claude Code instructions for eyadsibai/ltk, covering claude.md, what this is, multi-plugin architecture, plugin directory structure and component types.

eyadsibai/ltk

Agent

Comprehensive code reviewer covering spec compliance, quality, security, and simplicity. Use proactively after writing code. Examples: Context: User completed a feature implementation user: "I've finished implementing the authentication system" assistant: "Let me use the code-reviewer agent to review this…

eyadsibai/ltk

Agent

Expert at creating new Claude Code custom commands with proper structure and best practices. Use when needing to create well-structured custom commands.

eyadsibai/ltk

Agent

Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.

eyadsibai/ltk

Agent

Documentation generator for docstrings, README, CLAUDE.md, and API docs. Use when documentation needs to be created or updated. Examples: Context: User wrote new functions without documentation user: [Writes new functions] assistant: "I'll use the docs-generator agent to create docstrings for these functions" New code…

eyadsibai/ltk

Agent

Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.

eyadsibai/ltk

Agent

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

eyadsibai/ltk

Agent

Identifies refactoring opportunities and assists with safe code restructuring.

eyadsibai/ltk

Agent

Orchestrate complex tasks with four specialist sub-agents: Architect, Research, Coder, and Tester. Examples: Context: User has a complex implementation task user: "I need to implement a caching layer for our API" assistant: "I'll use the ultrathink-coordinator to analyze this from architecture, research…

eyadsibai/ltk

Command

Structured brainstorming before creative or implementation work.

eyadsibai/ltk

Command

Cancel an active Ralph Loop.

eyadsibai/ltk

Command

Full autonomous engineering workflow - plan, work, review, test, and ship.

eyadsibai/ltk

Command

Start iterative self-referential development loop - runs until completion promise or max iterations.

eyadsibai/ltk

Command

Intelligently sync and deduplicate skills, commands, agents, and hooks from all git submodules.

eyadsibai/ltk

Command

Enhanced analytical thinking for complex problems.

eyadsibai/ltk

Command

Ultra-comprehensive analytical thinking for the most complex problems.

eyadsibai/ltk

Command

Orchestrate multi-perspective analysis for complex problems.

eyadsibai/ltk

Command

Launch coordinated multi-agent analysis for complex tasks using Architect, Research, Coder, and Tester specialists.

eyadsibai/ltk

Skill Claude CodeCodex

Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks".