mrclrchtr-skills

Orchestrate complex work via a phase-gated multi-agent loop (audit → design → implement → review → validate → deliver). Use when you need to split work into subsystems, run independent audits, reconcile findings into a confirmed issue list, delegate fixes in clusters, enforce PASS/FAIL review gates, and drive an end-to-end validated delivery.

Standalone version of the agent orchestrator. Orchestrate complex work via a phase-gated multi-agent loop (audit → design → implement → review → validate → deliver). Use when you need to split work into subsystems, run independent audits, reconcile findings into a confirmed issue list, delegate fixes in clusters, enforce PASS/FAIL review gates, and drive an end-to-end validated delivery.

Create safe, repo-convention commits: inspect and stage changes, write a clear subject, add a body when useful, and commit.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Download Stitch (stitch.withgoogle.com) screenshots at best quality from screenshot.downloadUrl. Use to normalize googleusercontent size parameters from canvas dimensions, download with curl, optionally verify pixel dimensions, and avoid committing signed URLs.

Fetches and normalizes http(s) web pages into clean Markdown for LLM ingestion. Use when a task includes a URL, needs to fetch docs or asks to convert web docs/articles/pages into Markdown for summarizing, quoting, diffing, or saving.

A collection of agent role configurations for multi-agent workflows. Includes architect, auditor, implementer, reviewer, explorer, and worker roles with tiered variants (medium, high, xhigh) for different task complexity levels.