Agent Skills Hub

spec-metadata

Generates standardized metadata, including git/jj version info and timestamps, for research docs, handoffs, and implementation plans.

dev-cycle

Interactive development workflow manager. Coordinates discovery, planning, review, and build phases using a specialized team of AI agents (Scout, Bob, Garry, Arlo) for consistent project delivery.

systematic-debugging

A rigorous, four-phase methodology to enforce systematic root cause analysis before applying any code fixes.

minimax-tts

Perform internet searches using the Zhipu AI web search API to retrieve real-time information, news, and current data.

shift-right-testing

Production-grade testing strategy implementing feature flags, canary releases, synthetic monitoring, and chaos engineering for continuous reliability in live environments.

hive

Automate GitHub issue triage by analyzing reports against the codebase, verifying technical claims, and providing expert-driven responses to resolve invalid issues.

codex

Delegates coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and automated issue fixing within Git repositories.

langchain-architecture

Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.

query-sub-agent

Specialized IDF (Information Display Frame) sub-agent for generating and reviewing CQRS Query Side implementations across Java, TypeScript, and Go.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

monitor

Automated PR CI monitoring and failure resolution agent.

etudes

An aggressive sprint coach that helps builders overcome procrastination and overplanning by generating 5-day actionable tasks, tracking progress, and managing project momentum.