autoresearch
autoresearch
Autoresearch is a closed-loop ML experimentation workflow:
- human writes
program.md - agent edits
train.py prepare.pystays fixed- every run gets the same 300-second budget
- lower
val_bpbwins - regressions get reverted
This skill should behave like a routing-first front door, not a giant tutorial. Pick the user's mode, enforce the immutable-harness rules, then hand them to the smallest useful script or reference.
When to use this skill
More from akillness/skills-template
backend-testing
>
71data-analysis
>
54plannotator
>
35task-planning
Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
35omc
Use when you need Teams-first multi-agent orchestration in Claude Code. Triggers on: omc, autopilot, ralph, ulw, ccg, team. 29+ specialized agents, smart model routing (Haiku→Opus), persistent execution loops, skill layers, real-time HUD.
33vibe-kanban
Manage AI coding agents on a visual Kanban board. Run parallel agents through a To Do→In Progress→Review→Done flow with automatic git worktree isolation and GitHub PR creation.
32