Agent skill

codex-qa

Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or wants to compare Claude's answer with Codex's response.

Stars 1
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/FunnelEnvy/agents_webinar_demos/tree/main/.claude/skills/codex-qa

SKILL.md

Codex Q&A

Use OpenAI's Codex CLI to answer questions about the codebase.

Prerequisites

Codex CLI must be installed and configured:

bash
npm install -g @openai/codex
# or
brew install --cask codex

An OpenAI API key must be configured (OPENAI_API_KEY environment variable or via codex initial setup).

Usage

Spawn the codex-qa subagent to handle the question:

Use the Task tool to spawn the codex-qa agent with the user's question.

The subagent will:

  1. Formulate a clear prompt for Codex
  2. Run codex exec "question" in read-only mode
  3. Return Codex's response

Direct Usage (without subagent)

If you prefer to run Codex directly:

bash
codex exec "your question here"

Command Options

  • Basic query: codex exec "question"
  • With image: codex -i image.png exec "question about image"
  • JSON output: codex exec --json "question"
  • Longer timeout: codex exec --timeout 300000 "complex question"

Common Use Cases

  • Code explanation: "What does this function do?"
  • Architecture questions: "How is the database layer structured?"
  • Finding patterns: "Where is error handling implemented?"
  • Code review: "Review this file for potential issues"
  • Comparison: Get a second opinion on a code question

Notes

  • Codex exec runs in read-only mode by default - it cannot modify files
  • Activity streams to stderr, final answer goes to stdout
  • For complex questions, use the subagent for better context isolation

Expand your agent's capabilities with these related and highly-rated skills.

FunnelEnvy/agents_webinar_demos

playwright-browser

Use when capturing screenshots, automating browser interactions, or scraping web content. Covers Playwright Python API for page navigation, screenshots, element selection, form filling, and waiting strategies.

1 0
Explore
FunnelEnvy/agents_webinar_demos

bq-query-optimization

Use when writing BigQuery queries, optimizing query performance, analyzing execution plans, or avoiding common SQL gotchas. Covers parameterized queries, UDFs, scripting, window functions (QUALIFY, ROW_NUMBER, RANK, LEAD/LAG), JSON functions, ARRAY/STRUCT operations, BigQuery-specific features (EXCEPT, REPLACE, SAFE_*), CTE re-execution issues, NOT IN with NULLs, DML performance, Standard vs Legacy SQL, and performance best practices.

1 0
Explore
FunnelEnvy/agents_webinar_demos

n8n-workflow

Use when creating, deploying, or managing N8N workflows. Automatically uses N8N_HOST and N8N_API_KEY from environment.

1 0
Explore
FunnelEnvy/agents_webinar_demos

gcp-bq-data-loading

Use when loading data into BigQuery from CSV, JSON, Avro, Parquet files, Cloud Storage, or local files. Covers bq load command, source formats, schema detection, incremental loading, and handling parsing errors.

1 0
Explore
FunnelEnvy/agents_webinar_demos

gcp-cli-gotchas

Use when encountering gcloud or bq CLI formatting errors, quote escaping issues, command substitution problems, or when debugging CLI commands. Provides solutions for backtick usage, heredoc syntax, timestamp filters, parameter escaping, and multiline command formatting.

1 0
Explore
FunnelEnvy/agents_webinar_demos

gcp-bq-table-management

Use when creating BigQuery tables, implementing partitioning or clustering, managing table schemas, or optimizing table structure. Covers time-based partitioning, range partitioning, clustering strategies, DDL commands, and table configuration.

1 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results