GitHub
langgraph-workflows
Design and implement multi-agent workflows with LangGraph 0.2+ - state management, supervisor-worker patterns, conditional routing, and fault-tolerant checkpointing
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
spawn-research-agents
Use when conducting codebase research to orchestrate specialized agents in parallel for comprehensive investigation.
GitHub
agent-awareness
ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools.
GitHub
collaborative-outline
This skill should be used when the user asks to "创建大纲", "outline", "文章结构规划", "plan article structure", or needs help structuring their content before writing. Provides collaborative outline creation w...
GitHub
prompt-writing
Generates, analyzes, and optimizes prompts for skills, commands, subagents, reference docs, and free-form text. Use when generating prompt content, analyzing prompt files, or optimizing prompt text to apply tec...
GitHub
meta-prompt-framework
Three-phase task execution framework with refinement strategies and role-specific prompting. Automatically activates when designing prompts, optimizing task flows, or implementing iterative improvement patterns...
GitHub
learning-design-checklist
Generate a quick compliance checklist from the Four Learning Design Pillars. Use when users want a practical checklist for reviewing content, a quick audit tool, or verification questions for specific pillars.
GitHub
candidate-kb
Manage candidate knowledge base. Use when ingesting CVs, adding profile information, or querying candidate details for resume/cover letter generation.
GitHub
prompt-versioning
Track prompt versions, A/B test variants, and measure prompt performance
GitHub
guardrails-safety
Instrument safety checks, content filters, and guardrails for agent outputs
GitHub
instrumentation-planning
Plan what to measure in AI agent systems using tiered approach
GitHub
session-conversation-tracking
Instrument sessions, conversations, and multi-turn interactions
GitHub
multi-agent-coordination
Instrument multi-agent workflows, handoffs, and parent-child relationships
GitHub
llm-call-tracing
Instrument LLM API calls with proper spans, tokens, and latency
GitHub
memory-rag-instrumentation
Instrument RAG retrieval, memory operations, and context management
GitHub
decision-tracing
Trace agent decision-making, tool selection, and reasoning chains
GitHub
tool-call-tracking
Instrument agent tool executions with proper context and error handling
GitHub
build-assistant
Build Claude Code framework components (agents, slash commands, skills, plugins) following standardized templates. Use when creating new agents, commands, skills, or plugins for the multiagent framework.
GitHub
meta-automation-architect
Use when user wants to set up comprehensive automation for their project. Generates custom subagents, skills, commands, and hooks tailored to project needs. Creates a multi-agent system with robust communicatio...
GitHub
bulk-generate-concepts
Use when generating multiple curriculum-aligned concept files in parallel (5+ concepts) - researches curriculum, creates concept list, spawns parallel generation agents, orchestrates review loop until all pass
GitHub
researcher
Researches topics in-depth and generates comprehensive summaries and references. Use when trying to deeply understand a topic or use a new framework.
GitHub
plugin-creator
Use this skill when asked to "create a plugin", "build a new plugin", "make a Claude Code plugin", "scaffold plugin", "plugin structure", "add commands/agents/skills/hooks to plugin", or when helping with plugi...
GitHub
using-superpowers
Core skill activation protocol - establishes mandatory workflows for finding and applying skills before any task
GitHub
hooks-reference
Use this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automatio...
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.