team-polish

Orchestrates performance, art, audio, and QA subagents through a six-phase release polish pipeline.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/onemanking/the-operator --skill team-polish-onemanking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-polish
Source: https://github.com/onemanking/the-operator/tree/main/.github/skills/team-polish
Command: npx skills add https://github.com/onemanking/the-operator --skill team-polish-onemanking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating performance optimization, visual polish, audio polish, and QA hardening for a feature before release requires juggling multiple specialist roles and sequential phases, which is error-prone when done ad hoc. ## Core Features & Use Cases - Structured Six-Phase Pipeline: Runs assessment, optimization, visual polish, audio polish, hardening, and sign-off in a defined order with parallel phases where possible. - Specialist Subagent Delegation: Spawns performance-analyst, technical-artist, sound-designer, and qa-tester subagents via the Task tool with full context in each prompt. - User-Gated Decisions: Presents each subagent's proposals as selectable options with AskUserQuestion so the user approves before moving to the next phase. - Use Case: Before shipping a new game feature, invoke this skill to profile frame budget violations, fix hotspots, polish VFX and audio, soak test edge cases, and receive a READY FOR RELEASE or NEEDS MORE WORK verdict. ## Quick Start Ask the assistant to run the team-polish skill on the feature or area you want to prepare for release.

Frequently Asked Questions about team-polish

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I polish a game feature before release with AI agents?

Invoke the team-polish skill with the target feature or area. It delegates profiling to a performance-analyst, visual polish to a technical-artist, audio polish to a sound-designer, and hardening tests to a qa-tester, then reports release readiness.

What subagents does the polish pipeline use?

The pipeline uses four subagents spawned via the Task tool: performance-analyst for profiling and optimization, technical-artist for VFX and shaders, sound-designer for audio mixing, and qa-tester for edge case and soak testing.

Can visual and audio polish run in parallel?

Yes. Phases 3 (visual polish by technical-artist) and 4 (audio polish by sound-designer) run in parallel with Phase 2 optimization, since they are independent workstreams launched simultaneously.

Does the pipeline require user approval between phases?

Yes. At each phase transition the skill presents the subagent's proposals as selectable options using AskUserQuestion, and the user must approve before the pipeline advances to the next phase.

What does the final sign-off report include?

The sign-off report covers before/after performance metrics, visual and audio polish changes, test results, and a release readiness verdict of READY FOR RELEASE or NEEDS MORE WORK with remaining issues and severity.