Agent Skills Hub

vibe-run

A deterministic orchestration engine for autonomous coding agents, managing workflow loops, state persistence, and checkpoint-based execution.

typescript-testing

Standardizes Vitest unit and integration testing workflows for TypeScript, enforcing 70% coverage, proper mocking, and CI/CD-ready verification patterns.

reviewing-code

Perform rigorous code reviews for FastMCP projects, focusing on API design, dependency management, and codebase consistency.

data-extraction-patterns

Proven patterns for extracting, caching, and processing analytics data from GA4 and GSC using MCP servers.

Global Coding Style

Apply reality-first coding standards: intentional naming, focused functions, guard clauses, and deterministic side effects, with no speculative features.

upgrade-flake

Updates flake.lock to pull in the latest versions of Nix flake inputs without performing a full NixOS system release upgrade.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.

lambda

Manage AWS Lambda serverless functions: deploy code, configure event triggers, debug invocations, optimize cold starts, and maintain layers.

mcp-patterns

Maintenance patterns for the @youdotcom-oss/mcp STDIO bridge, focusing on transport lifecycle management, shutdown guards, and robust error handling.

metacognition

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

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

triage-ci-flake

Systematic triage and reproduction workflow for investigating flaky CI test failures in Payload CMS repositories.