Explore skills

Create a new AgentHub collaboration session with task, agent count, and evaluation criteria.

Merge the winning agent's branch into base, archive losers, and clean up worktrees.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Launch N parallel subagents in isolated git worktrees to compete on the session task.

Show DAG state, agent progress, and branch status for an AgentHub session.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headli

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.

Show experiment dashboard with results, active loops, and progress.

Use when the user wants more human-like AI responses — less robotic, less listy, more authentic. Triggers: 'behuman', 'be real', 'like a human', 'more human', 'less AI', 'talk like a person', 'mirror mode', 'stop being so AI', or when conversations are emotionally charged (grief, job loss, relationship advice, fear). NOT for technical questions, code generation, or factual lookups.