Loading...
Loading...
Found 14 Skills
Your AI creative partner. Describe what you're imagining — Pexo thinks with you, picks the best AI models, and delivers a finished, ready-to-share result. No prompts. No editing. No learning curve. Use when the user wants to create content and expects a finished result — not raw assets to assemble.
Structured software development framework for coding agents. Composable skills enforcing planning, testing, and systematic execution. Prevents code-first chaos.
Use when the user explicitly asks to invoke another coding agent CLI as a subagent. Triggers include phrases like 'get a second opinion from Codex', 'have Gemini review this', 'run this through Claude Code', 'ask another agent', or 'use a different model for this'. Supports Claude Code, Codex CLI, and Gemini CLI. Never invoke autonomously.
Surface Claude's assumptions about a phase approach before planning, checking what Claude thinks, or validating understanding before planning. Triggers include "list assumptions", "what are you thinking", "show assumptions", "phase assumptions", and "what's the plan".
Debate implementation plans between Claude Code and Codex CLI. After Claude Code creates a plan, invoke this skill to have Codex review it. Both AIs debate through multiple rounds until reaching full consensus before implementation begins.
Run agency-orchestrator YAML workflows directly in Claude Code / OpenClaw / Cursor — no API key required, using the current session's LLM as the execution engine. Triggered when users provide a .yaml workflow file or request multi-role collaboration to complete a task.
Systematic three-phase approach to feature development using Requirements, Design, and Tasks phases. Transforms vague feature ideas into well-defined, implementable solutions that reduce ambiguity, improve quality, and enable effective AI collaboration.
Exploratory discussion pattern for unsolved problems. Replicate the thinking of Staff+ engineers: "When there's no clear answer, expose blind spots by confronting diverse perspectives." True multi-agent discussions where experts directly engage with each other through team-based + messaging architecture.
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates
AI Debugging Collaboration Solution. Convert console.log into HTTP requests to collect logs. After the user completes operations, AI can automatically view and analyze the logs without the need for screenshots or copying console content. Supports Claude Code, OpenCode, Cursor.
Multi-Agent Swarm Parallel Collaboration, pure Git self-organization, suitable for large-scale project development. Use this when users mention "swarm mode", "multi-agent", "parallel development", "agent swarm".
Convene 11 role-specialized Claude agents to debate technical decisions in parallel, with the invoking Claude acting as CEO