udecode-dotai

Autonomous multi-agent coding system with 90+ specialized commands for development, testing, documentation, security, debugging, and Salesforce workflows.

96 skills · 109 commands · 15 agents · 1 MCP server · hooks

Intelligent task dispatch and performance tracking system for worker-agent coordination.

200 skills · 3 MCP servers

Configure persistent memory storage for OpenClaw skills to maintain state across conversations and interactions.

200 skills

Comprehensive open-source library of AI research and engineering skills enabling AI agents to conduct research and solve complex problems.

98 skills

Collection of specialized agents, commands, and templates for understanding, analyzing, and documenting codebases.

50 skills

Comprehensive guidance for designing, building, and troubleshooting Claude Code subagents with system prompts, tool access, and best practices.

44 skills · 1 MCP server

Agents for data engineering, machine learning, and AI development

12 agents

Context-management workflows for saving, loading, updating, sharing, and auditing Claude Code session memory.

1 skill · 5 commands

CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.

5 skills · hooks

Finish What You Start - Sessions that last, AI that learns, Features that ship. Context engineering + Theory of Mind + Knowledge Graph + Loop Mode + Task Mode. Features Project Knowledge Graph (unified search, experiential memory), unified workflow orchestration, auto-update on session start, ToM-based verification checkpoints, bilateral modeling, quality detection, enhanced context markers, and Loop Mode. 92% token reduction with proven strategies. Based on Riedl & Weidmann 2025 Human-AI Synergy research.

33 skills · 6 agents · hooks

Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.

17 skills · hooks

Stop guessing when to run /compact. Watches your session and suggests compaction at a completed checkpoint - after work lands, not mid-task - so you keep context you still need and drop what you do not. Optionally compacts for you. Judgment runs through the TypeSafe Jev API and needs your own key.