Agent Skills Hub

project-guidelines-example

A project-specific template skill providing standardized architecture, file structures, coding patterns, and deployment workflows for production-grade AI applications.

github-navigator

GitHub operations via gh CLI. Use for repository inspection, issues, PRs, releases, and deep codebase analysis including cloning for architectural insights.

claude-code-skill

Control Claude Code via MCP protocol for autonomous development. Features persistent sessions, agent teams, precise execution planning, and advanced tool management for complex coding tasks.

metacognition

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

building-logseq-plugins

Expert guidance for Logseq plugin development, specifically optimized for the new database architecture, API integration, and property management.

build-iphone-apps

CLI-only iOS development agent for Swift, SwiftUI, and UIKit. Handles the full lifecycle: build, debug, test, and release without Xcode.

claude-code-project-bootstrap

Project bootstrap for Claude Code with safety guardrails, git workflow automation, project auditing, and structured multi-phase planning.

webapp-test-docker-demo

Dedicated E2E testing agent for Playwright and Docker-based web applications, supporting automated test execution, report generation, and test creation.

doc-coauthoring

A structured workflow for co-authoring documentation, technical specs, and proposals, guiding users through context gathering, collaborative refinement, and reader verification.

coding-aider-plan-generator

Generate structured development plans, checklists, and file contexts compatible with the IntelliJ coding-aider plugin.

serena-mcp

Semantic code analysis guide for Serena MCP. Automatically prioritizes Serena tools for symbols, references, and code memory to optimize context and efficiency.

context-degradation

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