LLM Skills
~/catalog/specialized ai agents//plugin.json

Autoresearch agent

/plugin.json

Ajoute Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min t

Alireza RezvaniAlireza Rezvani
★25.6k
May 28, 2026
MIT
// plugin content

Claude Code plugin indexed at GitHub. Source description: An autonomous experiment loop that optimizes any file based on a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10 minutes to monthly). Detected version: 2.9.0

// original public source
alirezarezvani/claude-skills
/engineering/autoresearch-agent/.claude-plugin/plugin.json
License: MIT
Independent project, not affiliated with Anthropic. This plugin remains the property of its original author.
// install this plugin
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/plugin.json" "https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/engineering/autoresearch-agent/.claude-plugin/plugin.json"
Then in Claude Code, type /plugin.json to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Stars★ 25.6k
LicenseMIT
UpdatedMay 28, 2026
Format.md
AccessFree
// similar

Plugins Specialized AI agents

View allarrow_forward

Requesting Code Review

★282.6k

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation - never your session's history. This keeps the reviewer focused on t

Specialized AI agents
obra

Subagent Driven Development

★282.6k

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Specialized AI agents
Agentobra

Dispatching Parallel Agents

★282.6k

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit

Specialized AI agents
Agentobra

Autonomous Loops

★252.2k

Models and architectures for Claude Code autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Specialized AI agents
Agentaffaan-m