millitool
🧠

AI Agent Builder

Build AI-powered features: LLM integration, prompt engineering, RAG, tool calling, and agent patterns

aillmagent15 skills
One-click install
mkdir -p .claude/skills && \
  curl -sL https://raw.githubusercontent.com/anthropics/claude-plugins-official/main/plugins/agent-sdk-dev/agents/agent-sdk-verifier-py.md -o .claude/skills/agent-sdk-dev/agent-sdk-verifier-py.md && \
  curl -sL https://raw.githubusercontent.com/anthropics/claude-plugins-official/main/plugins/agent-sdk-dev/agents/agent-sdk-verifier-ts.md -o .claude/skills/agent-sdk-dev/agent-sdk-verifier-ts.md && \
  curl -sL https://raw.githubusercontent.com/Jeffallan/claude-skills/main/skills/rag-architect/SKILL.md -o .claude/skills/rag-architect.md && \
  curl -sL https://raw.githubusercontent.com/affaan-m/everything-claude-code/main/docs/zh-CN/skills/prompt-optimizer/SKILL.md -o .claude/skills/prompt-optimizer.md && \
  curl -sL https://raw.githubusercontent.com/rohitg00/awesome-claude-code-toolkit/main/skills/prompt-engineering/SKILL.md -o .claude/skills/prompt-engineering.md && \
  curl -sL https://raw.githubusercontent.com/Jeffallan/claude-skills/main/skills/prompt-engineer/SKILL.md -o .claude/skills/prompt-engineer.md && \
  curl -sL https://raw.githubusercontent.com/davepoon/buildwithclaude/main/plugins/all-skills/skills/agent-analytics/SKILL.md -o .claude/skills/agent-analytics.md && \
  curl -sL https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/community/sprint/skills/agent-patterns/SKILL.md -o .claude/skills/agent-patterns.md && \
  curl -sL https://raw.githubusercontent.com/qdhenry/Claude-Command-Suite/main/.claude/agents/agent-organizer.md -o .claude/skills/agent-organizer.md && \
  curl -sL https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/skills/embedding-strategies/SKILL.md -o .claude/skills/embedding-strategies.md

Installs top 10skills to your project's .claude/skills/ directory.

Skills in this pack

agent-sdk-dev/agent-sdk-verifier-py
4.7
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
agentagentagent-sdk-devagent-sdk-verifier-py

by Anthropic · anthropic-official-plugins

agent-sdk-dev/agent-sdk-verifier-ts
4.7
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
agentagentagent-sdk-devagent-sdk-verifier-ts

by Anthropic · anthropic-official-plugins

rag-architect
5.0
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing.
rag-architectragarchitectai

by Jeffallan · jeffallan-claude-skills

prompt-optimizer
5.0
分析原始提示，识别意图和差距，匹配ECC组件（技能/命令/代理/钩子），并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机：当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发：“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机：当用户希望直接执行任务，或说“直接做”时。不触发时机：当用户说“优化代码”、“优化性能”、“optimize performance”、“optimize this code”时——这些是重构/性能优化任务，而非提示优化。origin: community
prompt-optimizerpromptoptimizer

by affaan-m · everything-claude-code

prompt-engineering
5.0
Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design
prompt-engineeringpromptengineering

by rohitg00 · awesome-claude-toolkit

prompt-engineer
5.0
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
prompt-engineerpromptengineerllm

by Jeffallan · jeffallan-claude-skills

agent-analytics
5.0
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
agent-analyticsagentanalyticsai

by davepoon · buildwithclaude

agent-patterns
5.0
Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger w
agent-patternsagentpatterns

by jeremylongshore · plugins-plus-skills

agent-organizer
5.0
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team formation, and dynamic workflow management.
agentsagentorganizerai

by qdhenry · claude-command-suite

embedding-strategies
5.0
Guide to selecting and optimizing embedding models for vector search applications.
data-aiembeddingstrategies

by sickn33 (Antigravity) · antigravity-awesome-skills

embedding_model_benchmark
5.0
Embedding Model Benchmark 2024
engineeringembeddingmodelbenchmark

by alirezarezvani · alirezarezvani-claude-skills

rag-implementation
5.0
RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
data-airag

by sickn33 (Antigravity) · antigravity-awesome-skills

rag_evaluation_framework
4.8
Evaluating Retrieval-Augmented Generation (RAG) systems requires a comprehensive approach that measures both retrieval quality and generation performance. This framework provides methodologies, metrics, and tools for systematic RAG evaluation across different stages of the pipeline.
engineeringragevaluationframework

by alirezarezvani · alirezarezvani-claude-skills

prompt-caching
5.0
You're a caching specialist who has reduced LLM costs by 90% through strategic caching. You've implemented systems that cache at multiple levels: prompt prefixes, full responses, and semantic similarity matches.
data-aipromptcaching

by sickn33 (Antigravity) · antigravity-awesome-skills

prompt-engineering
5.0
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
architecturepromptengineering

by sickn33 (Antigravity) · antigravity-awesome-skills