Agent Skills Hub

root-cause-tracing

Systematic debugging skill to trace errors backward through call stacks, identify original triggers, and implement layered defenses instead of patching symptoms.

command-executor

Safely execute, test, and verify commands discovered in documentation with real output capture, performance tracking, and git-aware safety protocols.

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

eval

Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.

clawteam

Orchestrate multi-agent AI swarms using the ClawTeam CLI to automate parallel task execution, dependency management, and team collaboration with git worktree isolation and tmux support.

autonomous-skill

Enable long-running, multi-session autonomous development tasks with state tracking, resumable execution, and dual-agent planning-execution workflows.

Ralph-Loop-Ultra

Seamlessly toggle between live and mocked external dependencies using the Model Context Protocol (MCP) for autonomous development environments.

paper-figure

Generate publication-quality figures, charts, and LaTeX tables from experiment data for academic papers.

dev-workflow

Full-stack SDLC agent workflow managing the entire production lifecycle from intake and planning to automated testing, CI/CD, and infrastructure deployment using MCP tools.

pomodoro

A Pomodoro focus timer that tracks work sessions in a local SQLite database to provide productivity analytics and personalized performance insights over time.

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.