agent-exploration
OfficialParallel research that writes analysis artifacts.
Education & Research#agent orchestration#knowledge synthesis#codebase exploration#parallel research#analysis artifacts#compozy exec
Authorcompozy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill turns a broad research question into multiple non-overlapping, deeply read slices that produce written analysis artifacts instead of chat-only output.
Core Features & Use Cases
- Parallel scoped research dispatch: Splits the operator’s prompt into up to 8 independent slices and runs
exploreragents concurrently viacompozy exec. - Written, schema-validated outputs: Each slice writes one seven-section analysis file under your chosen directory.
- Automated synthesis summary: Produces a
summary.mdthat consolidates and compares findings across slice files.
Quick Start
Run: compozy exec --skill agent-exploration -- --path ./research-current --agents 3 --prompt "How should we structure a local-first agent runtime to support durable, inspectable sessions?"
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-exploration Download link: https://github.com/compozy/agh/archive/main.zip#agent-exploration Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.