Agent Skills Hub

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

log-focus-debug

Focus debug skill for DashPlayer: isolates log chains, injects temporary focus markers ([FOCUS:token]), and ensures clean removal of debug artifacts after task completion.

pr-operations

Manage PR review workflows, resolve threads, and handle discussion comments using specialized erk exec commands.

tavily-search

Real-time web search and content extraction tool using the Tavily API for research, news gathering, and up-to-date information retrieval.

creating-agents-md

Provides a standardized template and guidelines for creating agents.md files to deliver project-specific context to AI coding assistants.

pr-review

Automated PR review agent for Schmock projects ensuring BDD coverage, code quality, TypeScript standards, and conventional commit adherence.

ascii-art

A generative agent skill for creating ASCII art, optimized for rapid, single-pass artistic output without iterative refinement.

zai-cli

Execute z.AI CLI for multimodal analysis, web search, reader, and GitHub repo exploration via CLI and MCP.

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

codex-cli

Orchestrate Codex CLI for efficient parallel coding, task automation, and session-managed workflows to optimize token usage and development speed.

ralph

Convert markdown PRDs into structured prd.json files for the Ralph autonomous AI agent system to enable repeatable, context-aware software development.