evo
Runs autoresearch loops on a codebase: it sets up a benchmark and baseline, iterates on code optimization experiments, reports results, and ships the winning change as a pull request.
7 skills1.5k
@evo-hqPlugins
1@evo-hqSkills
7discover
Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing…
@evo-hqfinetuning
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when…
@evo-hqinfra-setup
Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance.
@evo-hqoptimize
Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or…
@evo-hqreport
Read-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently,…
@evo-hqship
Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge…
@evo-hqsubagent
Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's…
@evo-hqAgents
3benchmark-reviewer
AgentReviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation,…
@evo-hqideator
AgentGenerates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (`failure_analysis`, `literature`,…
@evo-hqverifier
AgentRead-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set…
@evo-hqIs this you? Claim your profilePut a plugin at the top of Plugins, from $9