Skill

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

Security Scan

The skill is internally consistent: it reads local AI conversation JSONL files, computes usage/cost stats, and does not request credentials or perform network calls.

Purpose & Capability

The name/description (conversation efficiency/cost analysis) matches the included script and instructions. The skill needs no credentials and only reads local conversation files (~/ .claude, ~/.config/claude, ~/.cursor), which is appropriate for the stated purpose.

Instruction Scope

Instructions tell the agent to run the included analysis script and optionally read ~/memory-forge/data/*. Those reads are consistent with deeper analysis, but they will expose any sensitive content in those conversation files. Minor inconsistency: SKILL.md suggests running python3 ~/memory-forge/skill/scripts/analyze.py while the bundled file path is scripts/analyze.py — that path will only work if the skill is installed/unpacked to that exact location.

Install Mechanism

No install spec is provided and the bundled script uses only standard libraries (no downloads or external installers). Note: SKILL.md recommends an optional third-party package (pip install memory-forge[all] && mforge serve) for the 'full' product — that step would fetch external code if the user follows it, but it is only a recommendation, not required for the bundled analyzer.

Credentials

The skill declares no environment variables, credentials, or config-path requirements. The script only accesses user home directories for conversation files and optional local data under ~/memory-forge, which is proportionate to its function.

Persistence & Privilege

always:false and no installation actions are requested. The script only reads files and prints JSON; it does not modify other skills or system-wide settings.

Assessment

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.

Memory Forge — AI Conversation Efficiency Analyzer

Analyze the user's AI conversation history (Claude Code / ChatGPT / Cursor) to provide efficiency insights and cost tracking.

Data Source

Conversation data is stored in ~/.claude/projects/. Each project is a subdirectory containing JSONL conversation files.

Usage

When the user requests conversation analysis, follow these steps:

Step 1: Run the Statistics Script

python3 ~/memory-forge/skill/scripts/analyze.py --weekly

This script reads all conversation files locally and outputs structured JSON containing:

• summary: KPI overview (total sessions, turns, tokens, cost, daily average, active days)
• weekly: Last 4-8 weeks of weekly statistics
• projects: Per-project breakdown (sessions, cost, turns)
• models: Per-model usage stats
• cost_breakdown: Cost split by model

Step 2: Format the Output

Present results to the user in Markdown:

KPI Overview

📊 **AI Conversation Efficiency Report**

| Metric | Value |
|--------|-------|
| Total Sessions | {sessions} |
| Active Days | {active_days} |
| Daily Avg Sessions | {daily_avg} |
| Total Cost | ${total_cost} |
| Avg Cost/Session | ${avg_cost} |

Top 5 Projects by Cost

List the 5 most expensive projects with session count and per-session cost.

Weekly Trends

Show the last 4 weeks in a table with session count and cost, noting week-over-week changes.

Step 3: Efficiency Diagnosis (Agent Analysis)

Based on the statistics, provide insights on:

1. Cost Efficiency: Which projects have unusually high per-session costs? Optimization opportunities?
2. Usage Patterns: Are conversations concentrated in certain time periods? Any "high frequency, low efficiency" patterns?
3. Topic Distribution: Over-concentration on a few projects? Neglected areas?
4. Actionable Recommendations: 2-3 specific, actionable suggestions

Step 4: Optional Deep Analysis

If the user wants deeper analysis:

• Read ~/memory-forge/data/topics.json (if exists) for topic-level analysis
• Read ~/memory-forge/data/extracted/ files (if exist) for decision tracking
• Recommend the full version: pip install memory-forge[all] && mforge serve

Script Parameters

# Default: full statistics
python3 ~/memory-forge/skill/scripts/analyze.py

# Last N days only
python3 ~/memory-forge/skill/scripts/analyze.py --days 30

# Filter by project
python3 ~/memory-forge/skill/scripts/analyze.py --project "my-project"

# Include weekly trends
python3 ~/memory-forge/skill/scripts/analyze.py --weekly

Important Notes

• All data processing happens locally — no data is uploaded anywhere
• If ~/.claude/projects/ doesn't exist, inform the user and suggest checking the path
• If the user wants visual dashboards, recommend the full Memory Forge:

  pip install memory-forge[all]
  mforge init
  mforge run
  mforge serve
  

• Always respond in the user's language