session-logs

Search and analyze local session log JSONL files for historical answers.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/dingdyan/openclaw-workspace-v2 --skill session-logs-dingdyan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-logs
Source: https://github.com/dingdyan/openclaw-workspace-v2/tree/main/skills/session-logs
Command: npx skills add https://github.com/dingdyan/openclaw-workspace-v2 --skill session-logs-dingdyan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of not remembering what you (or the assistant) said earlier, especially when the answer exists in older or parent chats stored on disk.

Core Features & Use Cases

  • Search your session history: Locate specific phrases, dates, or topics across JSONL transcript files.
  • Extract structured message content: Filter user vs. assistant messages and return only human-readable text segments.
  • Analyze usage and behavior: Compute message counts, total cost, token-related summaries, and tool-call breakdowns per session.
  • Use case: If a user asks “What did we decide about X last week?” or “Show me what you wrote earlier in that thread,” you can search and retrieve the relevant prior context.

Quick Start

Ask: Search my session logs for the keyword "keyword" and summarize the most relevant user and assistant messages.

Frequently Asked Questions about session-logs

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

FAQPage Schema
How do I search conversation history for a specific keyword in local session logs?

To search conversation history, you can retrieve specific phrases from local session log JSONL files by applying keyword search and filtering text content deterministically using tools like rg and jq.

Can I compute total token cost and usage breakdowns from past chat transcripts?

Yes, you can analyze usage and behavior from past chat transcripts by computing message counts, aggregated cost, and tool-call breakdowns per session directly from the JSONL session log data.

What is the best way to extract human-readable text from JSONL conversation logs?

The best way to extract human-readable text from JSONL conversation logs is to filter user versus assistant messages by parsing timestamps and message roles, returning only the relevant text segments.

How do I filter session logs by specific dates to find older conversation context?

You can filter session logs by specific dates by applying per-day filtering to local JSONL transcript files, allowing you to locate historical context from older or parent conversations on disk.

Do I need any external dependencies to parse and analyze my session log files?

No external dependencies are required to parse and analyze session log files; the process relies on standard command-line utilities like jq and rg to parse the JSONL data structure and index mapping.