Cconductor — Development skill for Claude Code
Claude Code -powered Research, Orchestrated.
How to install Cconductor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open yaniv-golan/cconductor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cconductor does
Claude Code -powered Research, Orchestrated.
Alternatives in Development
- Creator Buddy — Creator Buddy: orchestrated Agent Skills for cross-platform content search, creator analysis, and viral trend 1.4k ★
- Claude Prism — An offline-first scientific writing workspace powered by Claude 1.1k ★
- Claude Code Bmad Skills — BMAD Method skills for Claude Code - Auto-detection, Memory integration, Slash commands 393 ★
README

CConductor 🔍
**AI Research, Orchestrated**
CConductor is a multi-agent AI research system that conducts comprehensive, adaptive research on any topic. Powered by Claude and specialized AI agents, it finds, analyzes, and synthesizes information from academic papers, web sources, PDFs, and code repositories—delivering well-cited, validated research reports.
Why CConductor?
- 🧠 Multi-Agent Intelligence - Specialized agents for planning, research, synthesis, and validation work together
- 📚 Multi-Source Research - Handles academic papers, web content, PDFs, code, and market data
- ✅ Built-In Validation - Automatic fact-checking, citation tracking, and quality assessment
- 🎯 Adaptive Research - Identifies gaps, explores leads, and improves iteratively until high confidence
- 📊 Quality Scores - Know exactly how reliable your research is (0-100 with detailed breakdown)
- 🔒 Configurable Security - Control which domains to trust with flexible security profiles
- 🌍 Cross-Platform - Works on macOS, Linux, and Windows (WSL2)
Getting Started
Prerequisites
- Claude Code CLI access – You need a Claude Pro/Max subscription or API credits plus the Claude Code CLI (run
claude, then/statusto confirm your account). Install via the native script (curl -fsSL https://claude.ai/install.sh | bash) or, if you already have Node.js 18+,npm install -g @anthropic-ai/claude-code. - Supported platforms – macOS 10.15+, Linux distros with GNU coreutils (Ubuntu 20.04+, Debian 10+, Fedora 33+), or Windows via WSL2.
- System packages – Bash ≥ 4.0,
git,jq,curl,bc, andripgrep. The quick-start commands below install them for you. - Python 3 – Used for knowledge graph tooling (pre-installed on most systems).
- Optional (installed in quick start):
dialogfor the full interactive TUI experience.
Quick Start (Non-Technical)
Use the commands for your platfo
Related Skills
Openshell Deepagent
A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and p
Z4n4 Automated Research Skills
An interoperable system of agent skills for academic research, powered by Agent Bayes
Yaad Memory Fabric
Yaad Memory Fabric — NVIDIA-powered knowledge/memory layer for the Open Agent Hackathon 2026 (Tinkerer Track).
Client Intelligence
Claude-powered multi-agent research workspace for consulting PMs, automating client and industry intelligence
Agentfs Claude
Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows
Hamr
ᚺᚨᛗᚱ — The Shape-Skin Engine. Open-source parametric 3D anime character forge. Linux-native, headless-first, a
Related Agents
Wmux Worker
Worker agent for wmux orchestrated tasks. Executes a specific subtask within strict file boundaries, reports r
Ideator
Ideator teammate for bmad-swarm orchestrated work — spawned by the orchestrator via the team flow. Not for ad-
Deep Crawl
Sequential fallback for deep codebase investigation. For orchestrated parallel execution with sub-agents, use