GitHub
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
academic-review
Interactive review sessions with academic PDFs (lectures, research papers, book chapters). Extract concepts, run Q&A sessions, generate quizzes with scoring. Preserves mathematical formulas in LaTeX format. Pri...
GitHub
agent-specification
This skill should be used when the user asks to "write agent spec", "define agent role", "specify an agent", "agent specification", "what should my agent do", "agent inputs outputs", "agent design discovery", "...
GitHub
coordination-patterns
This skill should be used when the user asks about "agent coordination", "MAS architecture", "blackboard pattern", "orchestrator pattern", "how agents communicate", "multi-agent workflow", "event-driven agents"...
GitHub
production-readiness
This skill should be used when the user asks about "MAS production", "agent observability", "MAS cost optimization", "agent monitoring", "multi-agent governance", "MAS compliance", "token budget", "ops runbook"...
GitHub
mas-decision-gate
This skill should be used when the user asks "should I use multi-agent", "MAS vs single agent", "when to use multiple agents", "do I need multi-agent", "single agent or multi-agent", "simplicity test", "agent n...
GitHub
template-skill
Replace with a clear and informative description of what this skill does and when Claude should use it. Include specific scenarios and file types that trigger the skill.
GitHub
reflect
Analyze and improve skills based on session outcomes. Use when: user says "reflect", "improve the skill", "what went wrong with the skill", "optimize skills", or wants to analyze skill effectiveness after using...
GitHub
interview-project
Interview users in-depth about project requirements to create a comprehensive specification. Use when starting a new project, gathering requirements, or when user wants to document project decisions. Triggers o...
GitHub
agent-creator
This skill should be used when the user asks to "create a new agent", "make a subagent", "build an agent for X", "generate agent configuration", or wants to create a new Claude Code sub-agent. Triggers on "agen...
GitHub
skill-creator
Specialized skill for creating new OpenCode agent skills. Detailed instructions on triggers, structure, and best practices. Triggers: 'create a skill', 'make a new skill', 'add a skill', 'new skill'.
GitHub
init-project
Initialize a project with a CLAUDE.md file by exploring the codebase and auto-detecting development workflows. Use when user wants to set up Claude Code for a new project, create a CLAUDE.md, or run /init-proje...
GitHub
interview
This skill should be used when the user asks to "interview me about the plan", "validate my implementation plan", "review my design decisions", "question my architecture choices", or when finishing plan mode be...
GitHub
reflect
Analyze conversation to extract reusable engineering rules. Use when user says 'reflect', 'remember this', 'learn from this', or after receiving corrections/feedback.
GitHub
role-management
Guidelines for identifying the appropriate AI persona (Flash, Sonnet, Pro) for a given task.
GitHub
council
Gather design feedback from AI consultants (Gemini and Codex). Use for architecture decisions, design review, or when you want multiple expert perspectives on SENTINEL development. (project)
GitHub
deploy
Deploy Codex or Gemini as working agents to implement tasks. Use when you want another AI to actually write code, not just review. (project)
GitHub
portrait
Generate character portraits using Gemini NanoBanana. Reads from character YAML and calls gemini directly with full guardrails.
GitHub
profile
Generate full NPC profiles from character YAML and save JSON to sentinel-agent/generated_npcs. Native (no external agent call).
GitHub
skill-creator
Create new Agent Skills that conform to the Agent Skills open standard (SKILL.md frontmatter + instructions), using progressive disclosure and optional scripts/references/assets. Use when the user asks to creat...
GitHub
using-jules
Guide for using Google Jules, the asynchronous AI coding agent. Use when delegating tasks to Jules, writing Jules prompts, using the `jules` CLI, or when the user mentions "jules", "send to jules", or wants to...
GitHub
session-manager
Activates when the user asks to "create session summary", "summarize this session", "end the session", "start a session", "load context", "what did we work on", "session notes", "document this session", or want...
GitHub
rest-api-design
Expert REST API design patterns, resource modeling, HTTP semantics, pagination, filtering, and RESTful best practices. Use when designing REST endpoints, reviewing API specifications, establishing REST conventi...
GitHub
agents-commands-creator
Create Claude Code agents and commands with proper markdown structure, YAML frontmatter, and plugin.json arrays. Use when creating commands, slash commands, agents, autonomous assistants, and command-line utili...
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.