GitHub
claude-tool-calling-patterns
Comprehensive guide for AI agents on proper Claude-style tool calling with correct syntax, patterns, and examples
☆ 0View skill
research llm ai AI Skills
Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: research llm ai
research llm ai Clear filters
Browse skills
GitHub
strands-agents
Build AI agents with the Strands Agents SDK, an open-source framework from AWS. Use when building autonomous agents, creating custom tools with @tool decorator, orchestrating multi-agent systems (swarm, graph,...
☆ 0View skill
GitHub
delegate-task
Analyzes requests and routes them to the appropriate specialized skill or sub-agent.
☆ 0View skill
GitHub
integrao-ai-e-prompts-o-orculo
Padronização, robustez e controle nas chamadas de IA (Gemini), separando prompts do código.
☆ 0View skill
GitHub
update-skill
Update a skill from the canonical ClaudeSkills repository. Use to sync local skills with latest versions.
☆ 0View skill
GitHub
update-skill
Update a skill from the canonical ClaudeSkills repository. Use to sync local skills with latest versions.
☆ 0View skill
GitHub
ai-security-engineer
AI Security Engineer focused on preventing prompt injection, data exfiltration, and model abuse in LLM-enabled products.
☆ 0View skill
GitHub
shared
Shared contracts, schemas, and helper prompts for all skills
☆ 0View skill
GitHub
baml
Learn how to use the BAML programming language for LLM structured outputs
☆ 0View skill
GitHub
ralph-loop
Autonomous development loop with fresh context per iteration. Uses an external bash loop that spawns fresh Claude sessions, storing state in files to prevent context drift. Based on the original Ralph Wiggum te...
☆ 0View skill
GitHub
creating-skills
Generates high-quality, predictable, and efficient `.agent/skills/` directories based on user requirements. Use when the user wants to create a new skill or capability.
☆ 0View skill
GitHub
creating-skills
Generates high-quality, predictable, and efficient .agent/skills/ directories based on user requirements. Use when the user asks to create a new skill or "habilidad".
☆ 0View skill
GitHub
config-restore
This skill should be used when users want to restore, reload, or copy their Claude Code configuration files (commands, skills, agents) from a backup directory back to ~/.claude/. Triggered by phrases like "rest...
☆ 0View skill
GitHub
button-language-audit
Use this agent to audit and replace button text with compassionate, non-demanding language. User: "Buttons say 'Submit' and 'Delete' - feels demanding" Agent: Use button-language-audit to soften language U...
☆ 0View skill
GitHub
workspace-orchestrator-adapter
Adapts orchestration based on workspace context AND observed user prompt behavior over time.
☆ 0View skill
GitHub
mcp-expert
Expert in Model Context Protocol (MCP) server development. Use when building MCP servers, creating tools for Claude, implementing resources, debugging MCP connections, or integrating databases with Claude Code.
☆ 0View skill
GitHub
engenharia-de-prompts-e-refinamento-o-estrategista
Skill focada em transformar solicitações simples em prompts de alta engenharia, utilizando técnicas avançadas (CoT, Persona, Constraints) para maximizar resultados de LLMs.
☆ 0View skill
GitHub
pm7y-ralph-loop
Set up a cross-platform Ralph Wiggum loop for continuous autonomous Claude execution. Use when the user wants to run Claude in a loop, implement the Ralph technique, or needs continuous autonomous operation. Th...
☆ 0View skill
GitHub
multi-agent
启动或推进多 Agent 并行开发流程。用于协调多个 Claude Code 实例并行开发项目。
☆ 0View skill
GitHub
call-claude
Call claude to perform a task.
☆ 0View skill
GitHub
create-skill
when generating a skill, always follow this template.
☆ 0View skill
GitHub
oe-real-e2e-verification
Full E2E verification with REAL APIs (OpenAI + Gemini). Use when stub tests pass but you need to verify real LLM behavior. Requires hybrid mode (I:ope/E:gem/V:ope). NEVER uses AGENT_MODE=stub.
☆ 0View skill
GitHub
claude-agent-sdk-for-python
Expert guidance for building autonomous AI agents using Anthropic's Claude Agent SDK (Python). Covers: agent loop patterns (GTVR: gather context, take action, verify, repeat), ClaudeSDKClient and query() APIs,...
☆ 0View skill
GitHub
ragtrieval
Answer questions from indexed vault content using RAGtriever search, plus setup, configuration, and troubleshooting
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.