opencode-conversation-analysis

Analyze OpenCode conversation chunks to identify recurring themes and steering patterns.

1|Updated Apr 17, 2026

Search Tags:#analysis #conversation #themes #sessions #opencode #jsonl #agent-steering

Ready to run

npx skills add https://github.com/alexgorbatchev/ai-registry --skill opencode-conversation-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: opencode-conversation-analysis
Source: https://github.com/alexgorbatchev/ai-registry/tree/main/harnesses/opencode/skills/opencode-conversation-analysis
Command: npx skills add https://github.com/alexgorbatchev/ai-registry --skill opencode-conversation-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Analyze OpenCode conversation history to identify themes, patterns, and steering cues in user messages, enabling teams to understand user intents and improve AI behavior.

Core Features & Use Cases

Extracted conversation chunks are analyzed to surface recurring themes, user-guidance patterns, and decision-making styles across sessions.
Parallel subagent analysis yields scalable, chunk-level insights that can be aggregated into a global theme report.
Output is a structured narrative plus a quantitative theme ranking suitable for product optimization and developer tooling.

Quick Start

Run the extraction and analysis workflow to generate chunked data, then run the analysis tool to derive themes from the history.

Frequently Asked Questions about opencode-conversation-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze OpenCode conversation history to identify recurring user themes?▼

Analyze OpenCode conversation history by processing chunked JSONL outputs from stored messages to identify recurring themes, steering patterns, and decision-making styles across multiple sessions. The analysis produces a structured JSON with theme counts and representative quotes for ranking.

What is agent steering and how does it appear in AI coding assistant conversations?▼

Agent steering in AI coding assistant conversations refers to how users guide the assistant's behavior through specific communication patterns and cues. Analyzing these patterns from chunked JSONL session data surfaces user intents, guidance styles, and decision-making trends for product optimization.

Can I extract conversation themes across multiple OpenCode sessions and timeframes?▼

Yes, you can extract conversation themes across multiple sessions and timeframes. The analysis applies parallel subagent processing to chunked JSONL outputs, aggregating chunk-level insights into a global theme report that spans the entire conversation history.

What format does the conversation analysis output use for ranking and display?▼

The conversation analysis outputs a structured JSON format containing identified themes, occurrence counts, and representative quotes. This quantitative theme ranking is suitable for product optimization and developer tooling display.

How do I prepare JSONL files for conversation theme extraction?▼

Prepare JSONL files by running the extraction workflow to generate chunked data from OpenCode conversation history. These extracted chunks serve as the input for the analysis tool to derive themes, user-guidance patterns, and decision-making styles.

Does conversation analysis work without parallel subagents for large JSONL datasets?▼

Parallel subagent analysis provides scalable processing for large JSONL datasets by yielding chunk-level insights that aggregate into a global theme report. Without this approach, processing large conversation histories across multiple sessions would lack the necessary scalability.