sk-deep-research
CommunityAutonomous iterative research loop
Education & Research#dashboard#convergence#iterative#jsonl#deep-research#autoresearch#externalized-state
AuthorMichelKerkmeester
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enables autonomous, iterative deep-research loops with externalized state to keep track of lineage and decisions across many iterations.
Core Features & Use Cases
- Orchestrates a multi-iteration research lifecycle with fresh-context LEAF execution and reducer-backed dashboards.
- Detects convergence, captures ruled-out directions for negative knowledge, and preserves memory for resumable sessions.
- Provides runtime parity guidance for multiple AI runtimes (OpenCode, Claude, Codex, Gemini).
Quick Start
Invoke the deep research loop with a topic to start autonomous iterations.
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: sk-deep-research Download link: https://github.com/MichelKerkmeester/opencode--spec-kit-skilled-agent-orchestration/archive/main.zip#sk-deep-research 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.