Explorar skills

Optional initial project context (e.g., "Python API for payments on AWS")

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill should be used when the user is auditing a "polyglot monorepo", "multi-language codebase", "microservices with different languages", "Go + Python + TypeScript", or any codebase with services written in different programming languages. Provides strategies for cross-service security analysis and unified threat modeling.

This skill should be used when the user asks about "dangerous functions", "security sinks", "what functions are dangerous in PHP/Java/Python", "find vulnerable functions", "code execution functions", "command injection sinks", "SQL injection functions", or needs to identify security-sensitive functions in source code during whitebox security review.

Use em vez de encadear 3+ chamadas Bash, pipelines grep/cat/find, ou qualquer processamento de dados em várias etapas. Esta skill deve ser usada quando o usuário pede para "iniciar um scratchpad", "usar o REPL", "modo scratchpad", "sessão Python persistente", ou quando uma tarefa envolve exploração, análise ou processamento de arquivos que se beneficiaria da composição de operações em código em vez de fazer chamadas de ferramentas individuais.

Environment configuration and secrets management skill using UV for Python projects. Handles .env files, environment variables, secrets encryption, multi-environment setups, and secure configuration patterns. Use when setting up project environments, managing API keys, or implementing configuration best practices.

Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, measures recall, precision, confidence calibration — reveals whether self-reported confidence scores track actual quality.

Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a phased implementation plan mapped to the codebase. Delegates deep analysis to the research:scientist agent and codebase

Minimal codex-native management loop. Use to create, update, or remove Codex agents/skills/config entries with guardrails.

Minimal codex-native sync loop. Use to keep project and home Codex configs aligned and report drift.

Oferece um loop de melhoria contínua de métricas com commits atômicos, auto-rollback e registro de experimentos. Ele itera com agentes especialistas, aceita um caminho de arquivo program.md e suporta várias opções de linha de comando.

One-time snapshot extracting patterns from work history and accumulated lessons, distills into concrete improvements — new agent/skill suggestions, roster quality review, memory pruning, consolidating lessons into rules/agent updates, or performing bin/ extraction from /audit --efficiency candidates.