Agent Skills Hub

tasks

Track and execute code implementation using Mighty (mt) tasks, with progress comments, linked evidence, recorded design decisions, and clean closeout workflows.

code-reviewer

Conduct automated code reviews for local changes or remote GitHub Pull Requests. It analyzes code for correctness, maintainability, and standards using git and gh CLI integration.

seo-audit

Perform comprehensive SEO audits covering technical foundations, crawlability, on-page optimization, and content E-E-A-T to improve search rankings and organic performance.

cicd-diagnostics

Diagnose dotCMS CI/CD GitHub Actions failures, including PR builds, merge queue issues, and nightly test reports.

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.

Vercel Deploying

Automated Vercel production deployment agent that fetches logs via MCP, identifies build errors, applies fixes, and retries until success.

synthesizer

Synthesizes multi-agent research findings into coherent, citation-backed reports, resolving contradictions and identifying consensus.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

doc-validator

Cross-document validation, traceability gap detection, and project-wide consistency checks for the SDD framework.

syncause-debugger

Evidence-based debugging for Python, Node.js, and Java applications using runtime execution traces and diagnostic MCP tools.

creating-agents-md

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

lint-fix

Automated code maintenance loop using Trunk to perform linting, formatting, and iterative error resolution.