Memory Analyzer

Analyzes conversation history, extracts user preferences and feedback, updates memory files automatically.

Security Scan

The skill's code, instructions, and requirements are internally consistent with a memory/analyzer tool, but it automatically reads conversation history and writes memory files (including examples containing phone numbers and IDs), so you should consider privacy and file-access controls before installing.

Purpose & Capability

The name/description (analyze conversation history and update memory files) match the SKILL.md and the included analyzer.py. Required resources (none) are proportionate to the stated purpose; no unrelated credentials, binaries, or external services are requested.

Instruction Scope

SKILL.md explicitly instructs the agent to read conversation history from sessions/ and to automatically update memory files (MEMORY.md, USER.md, AGENTS.md, IDENTITY.md, SOUL.md). That behavior is coherent for the stated purpose but broad: it grants the skill access to all stored session transcripts and gives it autonomy to modify persistent memory files. No sanitization, consent, or retention policy is described.

Install Mechanism

There is no install spec (instruction-only), and the shipped analyzer.py is a small local script with no downloads or external install steps. This is low-risk from an install/network-execution perspective.

Credentials

The skill requires no environment variables, credentials, or config paths. That is proportionate. Note: the included memory_analyzer_output.json contains personal identifiers (E.164 phone number and a Telegram id) drawn from example data — the presence of PII in outputs is a privacy concern but not an inconsistency with the skill's purpose.

Persistence & Privilege

The skill is not always-enabled and can be invoked by the user (default autonomy is allowed). It will write updates to memory files automatically when run, which is normal for a memory-updating tool but increases the risk of persistent storage of sensitive content. It does not request elevated system-wide privileges or modify other skills' configs.

Assessment

This skill appears to do what it says: read session transcripts and update memory files. Before installing, consider the privacy implications — memory files can contain sensitive data (phone numbers, account IDs, etc.). Recommended precautions: 1) Inspect and sanitize existing sessions/ transcripts to remove PII you don't want persisted, 2) run the analyzer in a safe environment first and review its proposed changes before allowing automatic writes, 3) restrict filesystem permissions on MEMORY.md / USER.md / other memory files, 4) add explicit prompting or a review step to the SKILL.md (or modify analyzer.py) so updates require human approval, and 5) audit any memory files the skill creates for accidental secrets (API keys, tokens). If you need help adapting the skill to require manual approval or to redact PII automatically, I can suggest code changes.

Memory Analyzer Skill

Analyzes conversation history and updates memory files automatically.

Usage

Default: Google Gemini 3 Flash Preview

Run memory-analyzer skill with Google model

Or manually:

Run /home/ubuntu/.openclaw/workspace/skills/memory-analyzer/analyzer.py with google/gemini-3-flash-preview model

What It Does

1. Reads conversation history from sessions/
2. Extracts user preferences, feedback patterns
3. Updates memory files:
   • MEMORY.md (long-term memory)
   • AGENTS.md (agent rules)
   • USER.md (user preferences)
   • IDENTITY.md (identity notes)
   • SOUL.md (personality updates)

Trigger

When Tevfik says things like:

• "Sen bu konuda böyle yap"
• "Ben şöyle çalışmayı tercih ediyorum"
• "Bu formatı beğendim/beğenmedim"
• Any direct feedback or preference

Output

Automatically updates relevant memory files with new insights.

Default Model

google/gemini-3-flash-preview (Configured by Tevfik)