Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From spml
Starts an Auto Research workflow that designs a research protocol, builds baseline code, and iterates autonomously with agent evaluation and git management.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spml:autoresearch-createThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Explicit entry point for creating an Auto Research project.
Explicit entry point for creating an Auto Research project.
Auto Research is an automated iteration loop that designs a research protocol, builds validated baseline code, then iterates autonomously — Agent A modifies + trains, Agent B evaluates, Supervisor manages git state — accumulating experience until the target is reached or max rounds complete.
spml:autoresearch-create (you are here)
-> spml:ml-brainstorming (autoresearch mode — 8 protocol questions)
-> spml:experiment-planning
-> spml:ml-subagent-dev
-> spml:autoresearch-handoff (Post-Completion Gate: "Research")
-> [new session] spml:autoresearch-run
When ml-brainstorming loads, go DIRECTLY to the autoresearch protocol definition flow (the 8 questions starting with Question 0: Experiment directory). Do NOT perform keyword detection — autoresearch intent is already confirmed by this command.
Do NOT explore the project first. Do NOT dispatch Explore agents or read code before asking the user. Ask the user questions first.
npx claudepluginhub qqhard/superpowers-mlExecutes an Auto Research loop by locating the protocol and starting autonomous iteration. Requires the protocol to exist from the creation flow.
Generates program.md for autonomous AI research experiments (Karpathy's autoresearch). Interviews user on codebase, metrics, constraints; explores code; tailors agent instructions from template.
Curated index of autonomous improvement loops and research agents following the keep-or-revert pattern for code optimization, ML experimentation, and any measurable metric.