← Back to Skills Marketplace
Chat History Analyzer
by
austindixson
· GitHub ↗
· v1.0.5
508
Downloads
1
Stars
5
Active Installs
6
Versions
Install in OpenClaw
/install chat-history-analyzer
Description
Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions, saving findings to the journal.
README (SKILL.md)
Chat History Analyzer | OpenClaw Skill
Description
Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions, saving findings to the journal.
Chat History Analyzer | OpenClaw Skill
Extracts chat history from Cursor IDE's local SQLite databases, analyzes the last hour of conversations for key discoveries, obstacles, and solutions, and saves structured findings to the OpenClaw journal directory.
Usage
- As a scheduled cron job to continuously track insights from chat history
- Manually to analyze recent chat activity
- To identify recurring patterns, problems, or solutions in your workflow
# Combined log and chat history analysis (for cron jobs)
python3 /Users/ghost/.openclaw/workspace/skills/chat-history-analyzer/scripts/analyze_logs.py
# Analyze last hour of chat history only
python3 /Users/ghost/.openclaw/workspace/skills/chat-history-analyzer/scripts/chat_history_analyzer.py
# Analyze last 2 hours
python3 /Users/ghost/.openclaw/workspace/skills/chat-history-analyzer/scripts/chat_history_analyzer.py --hours 2
# Output JSON format
python3 /Users/ghost/.openclaw/workspace/skills/chat-history-analyzer/scripts/analyze_logs.py --json
What this skill does
- Extracts chat history from Cursor's SQLite databases (global and workspace-specific)
- Analyzes the last hour of messages for patterns indicating discoveries, obstacles, and solutions
- Saves structured findings to
/Users/ghost/.openclaw/journal/as markdown files - Runs automatically via cron job every hour
Integration as a Cron Job
This skill is designed to run hourly via OpenClaw cron. The analyze_logs.py script combines both log analysis and chat history analysis.
Example Cron Job Configuration:
{
"payload": {
"kind": "agentTurn",
"message": "Run analyze_logs.py script to analyze the last hour of logs and Cursor chat history, saving findings to journal.",
"model": "openrouter/google/gemini-2.5-flash",
"thinking": "low",
"timeoutSeconds": 180
},
"schedule": {
"kind": "cron",
"cron": "0 * * * *"
},
"delivery": {
"mode": "announce"
},
"sessionTarget": "isolated",
"name": "Chat History & Log Analysis"
}
Or run directly via shell script:
# Add to crontab (crontab -e)
# Run every hour at minute 0
0 * * * * /Users/ghost/.openclaw/workspace/skills/chat-history-analyzer/scripts/analyze_logs.py --json >> /Users/ghost/.openclaw/logs/analyze_logs.log 2>&1
Output Format
Findings are saved to /Users/ghost/.openclaw/journal/chat_analysis_YYYY-MM-DD_HHMMSS.md with sections for:
- Key Discoveries: Successful findings, realizations, and implementations
- Obstacles Encountered: Errors, failures, and blockers
- Solutions Found: Fixes, workarounds, and resolutions
Requirements
- Cursor IDE installed with chat history stored locally
- SQLite3 available (usually pre-installed on macOS)
- OpenClaw journal directory writable
How it works
- Connects to Cursor's SQLite databases at
~/Library/Application Support/Cursor/User/globalStorage/state.vscdband workspace-specific databases - Extracts messages from the last N hours (default: 1 hour)
- Analyzes message content using pattern matching for discoveries, obstacles, and solutions
- Saves structured markdown report to the journal directory
Usage Guidance
This skill appears to do what it says: reading Cursor's local SQLite chat storage, scanning recent messages for discoveries/obstacles/solutions, and writing reports to your OpenClaw journal. Before installing, consider the following:
- Privacy: the skill reads local chat history files that may contain sensitive secrets or private content. Only install if you trust the skill and want those chats processed and stored in ~/.openclaw/journal.
- Review code: the repository includes Python scripts; inspect them (and the referenced self-optimizer skill) if you have privacy or security concerns. The skill imports a sibling 'self-optimizer' module via sys.path — that dependency influences runtime behavior.
- Cron examples: SKILL.md contains example absolute paths with a specific username (e.g., /Users/ghost/...); adjust paths to your environment rather than copying them verbatim.
- Limit execution scope: if you plan to schedule it, consider running manually first or restricting the cron to run under a user account with appropriate access. Monitor the journal directory for files the skill creates.
- If you need higher assurance: run the scripts in a sandbox or examine runtime logs to confirm no outbound network activity occurs. If you cannot review the code, treat the skill as sensitive because it accesses private chat data.
Capability Analysis
Type: OpenClaw Skill
Name: chat-history-analyzer
Version: 1.0.5
The skill functions as described, extracting Cursor IDE chat history from local SQLite databases (~/Library/Application Support/Cursor/User/globalStorage/state.vscdb) to identify workflow insights. It processes data locally using regex patterns to find discoveries and obstacles, saving the results to a local journal directory. No evidence of data exfiltration, remote execution, or malicious intent was found; the hardcoded paths (e.g., /Users/ghost/) appear to be environment-specific configurations rather than indicators of compromise.
Capability Assessment
Purpose & Capability
Name/description claim to extract and analyze Cursor IDE chat history; the packaged Python scripts explicitly open Cursor's local SQLite files under the user's home directory, parse messages, analyze them with pattern matching, and save markdown reports to the OpenClaw journal directory — this is coherent and proportional to the stated purpose.
Instruction Scope
SKILL.md and the scripts instruct the agent to read Cursor's local storage (global and workspace state.vscdb), parse recent messages, and write reports to ~/.openclaw/journal. These actions are within scope but involve reading potentially sensitive chat content from a user's machine; SKILL.md includes example hard-coded paths (e.g., /Users/ghost/...) that are just examples but could confuse users if copied verbatim. There are no instructions that read unrelated system areas or send data to external endpoints.
Install Mechanism
There is no external install/download step (instruction-only skill with embedded Python scripts). No network downloads, package installs, or archive extraction are used. The code relies on Python and sqlite3 which are typical on target systems.
Credentials
The skill declares no required environment variables, credentials, or config paths beyond standard user-home locations. It does import a sibling 'self-optimizer' module (via sys.path manipulation) — that dependency is reasonable for combined log analysis but means the overall behavior depends on the code of that other skill.
Persistence & Privilege
always is false and the skill is user-invocable; SKILL.md suggests running it as an hourly cron job (expected for periodic analysis). Autonomous agent invocation is allowed by default (not flagged here), so if the agent is permitted to schedule or run this skill it will read local chat data on each run — this is a privacy consideration rather than a code-level privilege escalation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install chat-history-analyzer - After installation, invoke the skill by name or use
/chat-history-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
No changes detected in this version.
- No file changes found between versions.
- SKILL.md content remains unchanged.
- Version metadata and functionality are the same as previous release.
v1.0.4
- No changes detected in this version; the SKILL.md file remains unchanged.
v1.0.3
No visible changes detected in this release.
- No file changes were made for version 1.0.3.
- Skill behavior, usage, and documentation remain unchanged from the previous version.
v1.0.2
No user-facing changes in this version.
- No file changes detected between previous and current versions.
- SKILL.md content remains unchanged.
v1.0.1
No changes detected in this version.
- Version number updated to 1.0.1, but no file or documentation changes were made.
- Functionality, usage, and documentation remain unchanged from the previous release.
v1.0.0
- Initial release of Chat History Analyzer for OpenClaw.
- Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions.
- Supports analysis of recent messages (default: last hour), with adjustable timeframe via command line.
- Saves structured findings as markdown files in the OpenClaw journal directory.
- Includes cron job integration for automated, scheduled analysis.
Metadata
Frequently Asked Questions
What is Chat History Analyzer?
Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions, saving findings to the journal. It is an AI Agent Skill for Claude Code / OpenClaw, with 508 downloads so far.
How do I install Chat History Analyzer?
Run "/install chat-history-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Chat History Analyzer free?
Yes, Chat History Analyzer is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Chat History Analyzer support?
Chat History Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Chat History Analyzer?
It is built and maintained by austindixson (@austindixson); the current version is v1.0.5.
More Skills