thiagofernandes1987-create/APEX - Página 32

azure-ai-openai-dotnet

"Apply — Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings,"

Idioma do texto original: inglês

bullmq-specialist

Apply — BullMQ expert for Redis-backed job queues, background processing,

Idioma do texto original: inglês

claude-in-chrome-troubleshooting

"Apply — Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools"

Idioma do texto original: inglês

claude-monitor

Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.

Idioma do texto original: Vários idiomas

claude-settings-audit

Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow

Idioma do texto original: inglês

appdrag-automation

Automate Appdrag tasks via Rube MCP (Composio). Always search tools first for current schemas.

Idioma do texto original: inglês

context-window-management

Apply — Strategies for managing LLM context windows including

Idioma do texto original: inglês

conversation-memory

Apply — Persistent memory systems for LLM conversations including

Idioma do texto original: inglês

devcontainer-setup

"Apply — Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes."

Idioma do texto original: inglês

eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Idioma do texto original: inglês

github-workflow-automation

"Apply — "

Idioma do texto original: inglês

hugging-face-evaluation

"Apply — Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content,"

Idioma do texto original: inglês

langfuse

Apply — Expert in Langfuse - the open-source LLM observability platform.

Idioma do texto original: inglês

linear-claude-skill

Apply —

Idioma do texto original: inglês

llm-app-patterns

"Apply — "

Idioma do texto original: inglês

local-llm-expert

"Apply — Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp,"

Idioma do texto original: inglês

loop

"Create — Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate"

Idioma do texto original: inglês

notebooklm

"Apply — "

Idioma do texto original: inglês

paywall-upgrade-cro

"Create — When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates."

Idioma do texto original: inglês

prompt-caching

Apply — Caching strategies for LLM prompts including Anthropic prompt

Idioma do texto original: inglês

prompt-engineering

"Use — Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt"

Idioma do texto original: inglês

sales-engineer

"Analyze — Analyzes RFP/RFI responses for coverage gaps, builds competitive feature comparison matrices, and plans proof-of-concept"

Idioma do texto original: inglês

self-eval

"Review — Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review,"

Idioma do texto original: inglês

senior-prompt-engineer

"Use — This skill should be used when the user asks to 'optimize prompts', 'design prompt templates', 'evaluate LLM"

Idioma do texto original: inglês

skill-developer

"Apply — "

Idioma do texto original: inglês

wiki-llms-txt

"Generate — Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification."

Idioma do texto original: inglês

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alo

Idioma do texto original: inglês

maxia

"Apply — Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A"

Idioma do texto original: inglês

mcp-builder-ms

"Apply — "

Idioma do texto original: inglês

n8n-mcp-tools-expert

"Apply — Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations,"

Idioma do texto original: inglês

campaign-analytics

"Analyze — Analyzes campaign performance with multi-touch attribution, funnel conversion analysis, and ROI calculation for"

Idioma do texto original: inglês

cfo-advisor

"Use — Financial leadership for startups and scaling companies. Financial modeling, unit economics, fundraising strategy,"

Idioma do texto original: inglês

cmo-advisor

"Use — Marketing leadership for scaling companies. Brand positioning, growth model design, marketing budget allocation,"

Idioma do texto original: inglês

competitive-teardown

"Analyze — Analyzes competitor products and companies by synthesizing data from pricing pages, app store reviews, job postings,"

Idioma do texto original: inglês

ai-ml-api-automation

Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.

Idioma do texto original: inglês

cro-advisor

"Use — Revenue leadership for B2B SaaS companies. Revenue forecasting, sales model design, pricing strategy, net revenue"

Idioma do texto original: inglês

customer-success-manager

"Monitor — Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring"

Idioma do texto original: inglês

docx

"Use — Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting"

Idioma do texto original: inglês

financial-analyst

"Use — Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction"

Idioma do texto original: inglês

hugging-face-community-evals

Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval.

Idioma do texto original: inglês