thiagofernandes1987-create/APEX - Page 32

azure-ai-openai-dotnet

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

Langue du texte source : anglais

bullmq-specialist

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

Langue du texte source : anglais

claude-in-chrome-troubleshooting

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

Langue du texte source : anglais

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.

Langue du texte source : Plusieurs langues

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

Langue du texte source : anglais

appdrag-automation

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

Langue du texte source : anglais

context-window-management

Apply — Strategies for managing LLM context windows including

Langue du texte source : anglais

conversation-memory

Apply — Persistent memory systems for LLM conversations including

Langue du texte source : anglais

devcontainer-setup

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

Langue du texte source : anglais

eval

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

Langue du texte source : anglais

github-workflow-automation

"Apply — "

Langue du texte source : anglais

hugging-face-evaluation

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

Langue du texte source : anglais

langfuse

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

Langue du texte source : anglais

linear-claude-skill

Apply —

Langue du texte source : anglais

llm-app-patterns

"Apply — "

Langue du texte source : anglais

local-llm-expert

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

Langue du texte source : anglais

loop

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

Langue du texte source : anglais

notebooklm

"Apply — "

Langue du texte source : anglais

paywall-upgrade-cro

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

Langue du texte source : anglais

prompt-caching

Apply — Caching strategies for LLM prompts including Anthropic prompt

Langue du texte source : anglais

prompt-engineering

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

Langue du texte source : anglais

sales-engineer

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

Langue du texte source : anglais

self-eval

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

Langue du texte source : anglais

senior-prompt-engineer

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

Langue du texte source : anglais

skill-developer

"Apply — "

Langue du texte source : anglais

wiki-llms-txt

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

Langue du texte source : anglais

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

Langue du texte source : anglais

maxia

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

Langue du texte source : anglais

mcp-builder-ms

"Apply — "

Langue du texte source : anglais

n8n-mcp-tools-expert

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

Langue du texte source : anglais

campaign-analytics

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

Langue du texte source : anglais

cfo-advisor

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

Langue du texte source : anglais

cmo-advisor

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

Langue du texte source : anglais

competitive-teardown

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

Langue du texte source : anglais

ai-ml-api-automation

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

Langue du texte source : anglais

cro-advisor

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

Langue du texte source : anglais

customer-success-manager

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

Langue du texte source : anglais

docx

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

Langue du texte source : anglais

financial-analyst

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

Langue du texte source : anglais

hugging-face-community-evals

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

Langue du texte source : anglais