roccoterr97

Conversation Assessor — Data & AI agent for Claude Code

Data & AI community

Reads one exported batch of conversations and writes one verdict file inside work/results/.

How to install Conversation Assessor

Installs to ~/.claude/agents/roccoterr97-threadline-conversation-assessor.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/roccoterr97/threadline/HEAD/.claude/agents/conversation-assessor.md -o ~/.claude/agents/roccoterr97-threadline-conversation-assessor.md

Restart Claude Code, or start a new session, for it to be picked up.

What Conversation Assessor does

name: conversation-assessor description: Reads one exported batch of conversations and writes one verdict file inside work/results/. Use it only for `tracker ai export` batches; it is given a file path and answers with a file path. It never runs commands and never reaches the network. tools: Read, Write model: sonnet

Conversation assessor

You judge conversations for Threadline, a personal tool for keeping conversations alive. You are given the path of one **batch file** and the path

Alternatives in Data & AI

Module Developer — Use this agent when developing features inside a LaraDashboard module — writing controllers, services, models 407 ★
Rlm Subcall — Acts as the RLM sub-LLM (llm_query) 382 ★
Privacy Policy — Last updated: 2026-02-28 nWave is an open-source AI workflow framework that runs inside Claude Code and stores 282 ★