GitHub
skill-activation-patterns
Design patterns for automatic skill activation at plugin or project level. Use when implementing keyword-based skill suggestions.
Skills IA DevOps
Découvrez les skills DevOps, comparez leurs dépôts et consultez leurs instructions.
Catégories: DevOps
DevOps Effacer les filtres
Explorer
GitHub
plugin-test-framework
Virtual test environment for Claude Code hooks, plugins, and agents. Use when testing or validating plugin components without affecting production.
GitHub
hook-templates
Comprehensive Claude Code hook patterns for automation, state management, and external integration. Use when implementing hooks for validation, workflow gates, MCP integration, or state machines.
GitHub
cleanup-guide
Detect unnecessary files and provide cleanup recommendations
GitHub
comprehensive-validation
Language, style, and comment quality guidelines for plugin content
GitHub
hook-capabilities
Claude Code Hook system reference for capabilities, possibilities, and limitations. Use when you want to know what hooks can do.
GitHub
forge-analyzer
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
GitHub
skill-catalog
Categorize and display available skills. Use when listing or selecting skills.
GitHub
agent-tools-patterns
Patterns for configuring agent tools correctly
GitHub
critical-analysis-patterns
Philosophical/meta project analysis - critical analysis framework that asks "why?"
GitHub
hook-sdk-integration
LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.
GitHub
llm-sdk-guide
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.
GitHub
hook-system
Claude Code Hook system entry point. Guides you to the right skill based on your needs.
GitHub
orchestration-patterns
Single-skill vs multi-skill subagent architectures. Use when designing subagents.
GitHub
workflow-enforcement
Protocol-based workflow enforcement with validation dependencies and anti-bypass protection
GitHub
wizard
Smart routing wizard for creating skills, agents, commands with complexity-based skill loading
GitHub
mcp-daemon-isolation
Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.
GitHub
mcp-gateway-patterns
MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.
GitHub
workflow-state-patterns
Hook-based state machine patterns for multi-phase workflows. Use when designing sequential workflows with quality gates.
GitHub
designing-nextjs-ui
Create professional, attractive, and visually striking user interfaces in Next.js. Use when building beautiful websites, landing pages, dashboards, or any UI that needs to stand out. Covers Tailwind CSS utiliti...
GitHub
research-methodology
This skill should be used when the user asks about "how to research", "research best practices", "evaluate sources", "source credibility", "academic research", "find reliable information", "cite sources", "rese...
GitHub
granola-meeting-notes
This skill should be used when the user asks about "meeting notes", "what did we discuss", "find meeting", "show meeting", "recent meetings", "meeting transcript", "export meeting", "search meetings", "who was...
GitHub
buttondown-newsletter
This skill should be used when the user asks to "manage newsletters", "create an email draft", "list my drafts", "schedule a newsletter", "get email analytics", "check newsletter stats", "send a newsletter", "c...
GitHub
civitai-analyst
Generate and execute SQL queries against the civitai_records PostgreSQL database to analyze video performance on Civitai. Use when users ask about: video engagement metrics (likes, hearts, comments), content pe...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.