Stats
Actions
Tags
From autoresearch
This skill should be used when the user asks to "start research", "run autonomous experiments", "optimize my code automatically", "begin experiment loop", "run autoresearch", or needs to start or resume an autonomous research experiment loop. This is the top-level entry point that orchestrates setup and loop execution. For internal keep/revert methodology, see the research-loop skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autoresearch:researchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Start an autonomous research experiment loop.
Start an autonomous research experiment loop.
/research # Interactive setup
/research mar19-perf # Start with tag "mar19-perf"
Spawn the researcher agent via the Agent tool:
Agent(
prompt="Run the next experiment iteration. Config: <config>. Current best: <metric>.",
name="researcher"
)
The researcher agent is defined in ${CLAUDE_PLUGIN_ROOT}/agents/researcher.md.
For continuous operation, launch multiple sequential experiments. Each agent invocation handles one experiment cycle (modify, run, evaluate, decide).
If results.tsv has existing entries, resume from the current git state. Report progress so far before continuing.
npx claudepluginhub hironow/dotfiles --plugin autoresearchCore autonomous research loop. Reads research.md, proposes hypotheses, runs experiments, evaluates results mechanically, keeps improvements, discards failures, and iterates until the target metric is achieved or the iteration budget is exhausted. TRIGGER when: user invokes "autoresearch" (no subcommand); research.md exists; user wants the 5-stage loop; user wants iterative optimization overnight.
Generates program.md for autonomous AI research experiments (Karpathy's autoresearch). Interviews user on codebase, metrics, constraints; explores code; tailors agent instructions from template.
Runs iterative experiments to optimize measurable metrics (speed, accuracy, config). Manages .lab/ directory for experiment history and autonomous workflow.