
Optimize
Structured autoresearch loop that runs iteration rounds with subagent analysis, frontier selection, and stall-triggered ideation.
- skills.sh installs
- 142
- GitHub stars
- 1.5K
- last updated
- Jun 11, 2026
What it does
- Covers the post-discover loop: round briefs, scan-subagent analysis between rounds, frontier-based parent selection, and stall-triggered ideator dispatch
- Includes
evo:ideatorsubagents for failure analysis, literature, and frontier extrapolation, plusevo:verifierpre- and post-run audits on every experiment - Enforces a resource cap so live concurrency never exceeds
subagents=N, and a stop rule that ends bounded runs after one round - Designed for evo workspaces after
evo:discoverand the baseline commit, at any round width including serial workloads
Install
$ npx -y skills add evo-hq/evo --skill optimize -yInstalls into .agents/skills for every agent it finds here, and .claude/skills for Claude Code.
Files
Run the evo optimization loop. Each round, the orchestrator writes structured briefs and spawns subagents that execute within them. Each subagent is semi-autonomous: it reads the pointer traces, forms the concrete edit, runs experiments, and can iterate within its branch. Runs until interrupted or the stall limit is reached.
This skill is the canonical loop for ALL post-discover work — including serial workloads. If the workspace's resource profile forces width 1 (single GPU, single-process benchmark, etc.), you still invoke /evo:optimize -- just pass subagents=1. The loop's value is the STRUCTURE around each experiment (scan-subagent cross-cutting analysis between rounds, verifier pre/post hooks via the subagent skill, ideator spawning on stall, frontier reconciliation, stop-hook discipline), NOT just parallelism. Bypassing optimize because "I'm running serial work anyway" loses every piece of that structure -- you've reverted to ad-hoc experiment iteration with none of evo's loop benefits, just the bookkeeping.
Details
- Repository
- github.com/evo-hq/evo
- Categories
- Frontend Development, Git & Pull Requests, AI & Agent Building, Automation & Workflows
- License
- Apache-2.0
- First seen
- Jun 11, 2026
More from evo-hq/evo
All 6Similar to Optimize
More Frontend Development
pseudo-elementsraphaelsalaja/userinterface-wiki139 installsAudit CSS for pseudo-element best practices and View Transitions API usage. Use when reviewing hover effects, decorative layers, or page transitions. Outputs fi
axiom-realitykit-refcharleswiltgen/axiom136 installsRealityKit API reference — Entity, Component, System, RealityView, Model3D, anchor types, material system, physics, collision, animation, audio, accessibility
sn-search-academicopensensenova/sensenova-skills135 installs搜索学术论文和百科知识:ArXiv 预印本、Semantic Scholar(含引用数)、PubMed 生医文献、Wikipedia 百科。支持按章节读取 ArXiv HTML 全文和 PMC 开放获取全文,适合学术调研和深度阅读。
arxiv-vieweractionbook/actionbook133 installsView, search, and download academic papers from arXiv. Supports API queries, web scraping via Actionbook, and HTML paper reading via ar5iv. Use when user asks a
kami-decknexu-io/open-design133 installsProduce a print-grade slide deck in the kami (紙 / 纸) design system — warm parchment background (or ink-blue for cover / chapter slides), serif at one weight, in
youtube-video-hookmanojbajaj95/claude-gtm-plugin132 installsSkill for creating optimized YouTube video opening hooks (first 5-30 seconds) that maximize viewer retention and watch time. Use when planning video scripts, re