Skill

AI conversation efficiency analyzer. Analyze Claude/ChatGPT/Cursor conversation history for KPI stats, cost tracking, topic distribution, and efficiency insi...

This skill appears to do what it says: it reads conversation JSONL files from your home directory and computes local usage/cost statistics. Before installing or running it, consider: 1) These conversation files can contain sensitive data or secrets — review them or run the script in a controlled environment. 2) The SKILL.md gives a run path (~/memory-forge/skill/scripts/analyze.py) that may not match where the skill is unpacked; ensure you run the correct script file (bundled as scripts/analyze.py) or use the --base-dir flag. 3) The script itself does not perform network calls, but the README recommends an optional external pip package (memory-forge) which would download and run additional code if you choose to install it. 4) If you want extra caution, inspect the bundled scripts locally before running and run them with a restricted account or sandbox. If you want me to, I can produce the exact command to run the bundled script from its current location or check the script for specific patterns you are worried about.

Type: OpenClaw Skill Name: memory-forge Version: 1.0.1 The 'memory-forge' skill bundle is a utility designed to provide local statistics and cost analysis for AI conversation histories (Claude, ChatGPT, and Cursor). The primary script, `scripts/analyze.py`, parses local JSONL files from standard project directories and aggregates usage data (tokens, costs, and session counts) entirely on the local machine. There is no evidence of data exfiltration, unauthorized network access, or malicious intent in the code or the instructions provided in `SKILL.md`.