Agent skills for Perplexity

Implements a multi-agent review workflow where Claude develops and Codex validates logic, planning, and code quality.

Ask Codex CLI (gpt-5.6-sol) to run local app verification that needs computer use, browser automation, simulators, screenshots, app…

Diagnose OpenAI Codex CLI, Desktop, IDE, skill, plugin, MCP, session, configuration, authentication, network, storage, and performance…

Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for…

Use when Codex feels slow, bloated, or heavy after heavy use.

Use when the user invokes /goal, asks for Codex goal mode, or starts long-horizon autonomous work that should be refined into a concrete…

Generate or edit images by invoking OpenAI's gpt-image-2 ("image 2") through headless `codex exec`.

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default.

Implement coding tasks with Codex as the only writer, then use OpenCode as a read-only reviewer and iterate on verified findings.

Drive local Codex CLI instances non-interactively from an external orchestrator, including unattended launch permissions…

Create or repair a full-featured Windows desktop launcher that forces the Codex or ChatGPT app through a user-specified local HTTP proxy…

Review documents using Codex exec. Supports review loop with context preservation.

Quick second-opinion using Codex MCP (diff only, no tests).

Run OpenAI Codex via the Codex App Server (JSON-RPC-over-stdio) for streaming multi-turn chat sessions with persistent threads, structured…

Maintain a Codex skill repository as source of truth.

Coordinate multiple Codex agents.

Generate high-quality Brazilian Portuguese text-to-speech narration and section-level audio for videos from plain text or Markdown scripts.

Use the six Codex Usage Tracker tools for exact local usage facts, bounded exploration, allowance observations, and evidence timelines.

AI service usage/quota via CodexBar CLI: Codex/OpenAI, Claude, Kimi and other provider limits, credits, reset times.

To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.

Use when asked to inspect, reconstruct, audit, compare, or summarize prior coding-agent work across Codex, Claude, OpenCode, or local…