performance-goal

Orchestrate evaluator-gated performance optimization toward measurable objectives in Antigravity workflows.

3|Updated May 24, 2026

Search Tags:#performance optimization #latency #benchmarks #workflow state #durable artifacts #evaluator loop #evidence checkpointing

Ready to run

npx skills add https://github.com/shayne-snap/oh-my-antigravity --skill performance-goal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: performance-goal
Source: https://github.com/shayne-snap/oh-my-antigravity/tree/main/plugin/skills/performance-goal
Command: npx skills add https://github.com/shayne-snap/oh-my-antigravity --skill performance-goal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you achieve measurable performance improvements by turning optimization into a repeatable, evidence-driven evaluator loop instead of a one-off review.

Core Features & Use Cases

Evaluator-gated performance optimization: repeatedly run an evaluator command and only proceed when the declared pass/fail contract is satisfied.
Durable Omagy goal artifacts: preserves workflow state under .omagy/goals/performance/<slug>/ across turns for auditability.
Completion with verification evidence: prevents completion until a passing checkpoint exists and a completion audit confirms the objective is done.
Objective-first goal setup: uses the objective, evaluator command, and evaluator contract as the optimization target and source of truth.

Quick Start

Create a performance goal for reducing startup latency by 20%, run the evaluator loop, and complete it only after a passing checkpoint and final evidence are recorded.

Frequently Asked Questions about performance-goal

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

FAQPage Schema

How do I automate latency optimization and prevent regressions during development?▼

Automate latency optimization by running an evaluator-gated loop that repeatedly executes performance benchmarks and only proceeds when a declared pass/fail contract is satisfied. This turns optimization into a repeatable, evidence-driven process instead of a one-off review.

What is the best way to track performance benchmark state across multiple workflow turns?▼

Track performance benchmark state by preserving durable artifacts under the `.omagy/goals/performance/<slug>/` directory. This ensures your optimization progress and evaluator checkpoints remain auditable across multiple workflow turns and sessions.

How do I set up a measurable performance goal for memory and throughput optimization?▼

Set up a performance goal by defining a clear objective, an evaluator command, and an evaluator contract to serve as the optimization target and source of truth. This approach directly applies to memory, throughput, and speed targets.

Can I use an evaluator loop to gate performance completion for benchmark targets?▼

Yes, you can use an evaluator loop to gate performance completion. It prevents final completion until a passing checkpoint exists and a completion audit confirms the benchmark objective is successfully achieved and recorded.

Does performance optimization support host-goal parity for external benchmark contracts?▼

Yes, performance optimization supports optional host-goal parity via the `--host-goal-json` flag. This allows you to synchronize internal evaluator contracts with external benchmark targets during the optimization workflow.

Why does my performance optimization workflow fail to complete without a passing checkpoint?▼

Performance optimization workflows fail to complete without a passing checkpoint because the system enforces pass-only completion gating. It requires verification evidence from the evaluator command before marking the objective done.