Results for “activation-recompute”

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Agent validation overhaul: reward weight overrides, fitness decline gate, pinned data, staged experiments

Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.

Agent skill for pseudocode - invoke with $agent-pseudocode

Compares coding agents head-to-head on reproducible tasks, measuring pass rate, cost, time, and consistency.

Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Discover, find, compare, audit, repair, adapt, craft, run, debrief, and prepare repeatable AI-agent loops for publication. Use when a user asks to analyze code or coding threads for recurring work, find a published loop, interview them to turn a goal into a bounded loop, review a loop...

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

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations,...

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Agent skill for raft-manager - invoke with $agent-raft-manager

`task-agent`/`review-agent`: use when protected state, restore objectives, dependency order, or recovery evidence changes; skip backup-job-only work with no recovery decision.