Skip to content

/autoresearch

Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's

From plugin
47200 skills13 agents1 hooks3 MCP
shell
$ npx -y skills add naveedharri/benai-skills --skill autoresearch --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/autoresearch
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's
Ships withbenai-skills

Expert automation skills for Claude Code, organized by department.

Get the whole plugin, auto-invoked
Stats
47
Stars
0
Views
24
Forks
Active
Maintenance
JavaScript
Language
MIT
License
1h ago
Last commit
6mo ago
Created

Repo: naveedharri/benai-skills

Other skills on benai-skills.