Tools & Utilities
Essential command-line tools and system utilities.
git-workflow
Git workflow best practices including commit messages, branching strategies, pull requests, and collaboration patterns. Use when working with Git version control.
castella-a2a
Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
claude-cli
Use claude CLI for interactive AI sessions, scripting with print mode, MCP server management, and plugin configuration. Master session management, tool control, and automation workflows.
plugin-setup-creator
Create a shareable Claude Code plugin package containing your commands, hooks, output styles, status lines, and agents. Use when you want to package and distribute your Claude Code customizations, create team plugins, or export your personal setup.
castella-mcp
Enable AI agents to introspect and control Castella UIs via MCP. Create MCP servers, expose UI resources, handle MCP tools, and use semantic IDs.
skill-developer
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, keyword triggers, hook mechanisms (UserPromptSubmit), session tracking, and the 500-line rule.
castella-agent-ui
Build chat interfaces and agent management UIs with Castella. Create chat components, display tool calls, manage multiple agents, and build agent hubs.
atlas-documentation
AI-friendly documentation generation for Java services following RFC-37 standards. Covers documentation structure, templates, change detection, and RAG optimization. Use when generating or updating service documentation.
api-security
API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.
rfc-37-documentation
Bitso's service documentation standardization based on RFC-37. Validates directory structure, Confluence metadata, and content with bitso-documentation-linter. Use when creating, validating, or fixing markdown documentation for Confluence mirroring.
sonarqube-integration
SonarQube integration via MCP for Java projects. The MCP server runs remotely and requires no local setup. Use natural language to query issues, analyze code, and check quality gates.
prow-job-analyze-metal-install-failure
Analyze OpenShift bare metal installation failures in Prow CI jobs using dev-scripts artifacts. Use for jobs with "metal" in name, for debugging Metal3/Ironic provisioning, installation, or dev-scripts setup failures. You may also use the prow-job-analyze-install-failure skill with this one.
java-coverage
JaCoCo code coverage configuration for Java/Gradle projects. Covers report generation, coverage thresholds, multi-module aggregation, and SonarQube integration. Use when setting up or troubleshooting code coverage.
dependabot-security
Fix Dependabot security vulnerabilities in Java/Gradle projects using severity-based processing, dependency substitution strategies, and dependency graph verification. Use when Dependabot alerts need resolution with proper CI validation.
mutation-testing
Use PIT (Pitest) mutation testing to identify weak tests and improve test quality in Java projects. Finds tests that pass but don't actually verify behavior correctly. Use when improving test suite quality beyond line coverage metrics.
quality-gateway
Orchestrates quality checks at key lifecycle points: before edits, after edits, and before completion. Coordinates sub-skills (test-augmentation, doc-sync, coding-standards, security-review) to ensure consistent code quality. Use when making significant code changes or before completing a task.
pr-lifecycle
GitHub CLI commands and workflows for managing pull requests, CI checks, CodeRabbit reviews, and branch protection
git-hooks
Set up, validate, and maintain Git hooks (pre-commit, pre-push, etc.) following best practices. Ensures hooks are version-controlled, automatically installed, and follow consistent patterns across the team. Use when creating new hooks, debugging hook issues, or ensuring hook compliance.