TalonForge Memory System (EN/AR)

Automatically sets up a 3-layer memory system with long-term MEMORY.md, daily notes, and nightly fact extraction for durable AI memory management.

Security Scan

The skill's instructions mostly match its stated purpose (setting up a 3-layer memory system) but contain ambiguous, open-ended directives and a few inconsistencies (references an openclaw CLI but does not declare it, claims bilingual support not reflected in the README) and will create a recurring cron job that autonomously reviews conversations — a privacy-sensitive behavior you should review before installing.

Purpose & Capability

The stated purpose (create MEMORY.md, daily notes, and nightly extraction) aligns with the instructions. However SKILL.md invokes the 'openclaw' CLI (openclaw cron add) but the skill declares no required binaries — that's an operational inconsistency. package.json claims bilingual EN/AR, but SKILL.md is English only. These are plausible oversights but should be clarified.

Instruction Scope

The runtime instructions instruct an autonomous nightly job to 'Review today's conversations. Extract durable facts...' but do not specify which conversation sources, scope limits, retention, or redaction rules. That is broad and could cause the agent to aggregate sensitive user data into persistent files. The cron command text is open-ended and gives the agent wide latitude to read and store conversational content.

Install Mechanism

This is an instruction-only skill with no install spec and no code to be downloaded or executed, which is low risk from an install/execution perspective.

Credentials

The skill requests no environment variables or credentials (proportionate). However, it will create persistent local files (MEMORY.md and daily notes) that may contain sensitive information; the skill does not declare retention or access controls for those files.

Persistence & Privilege

The skill sets up a recurring cron job (nightly extraction) which gives it ongoing autonomous actions. While always:false, the scheduled autonomous extraction plus the open-ended instruction to review conversations increases privacy/privilege risk and should be reviewed before enabling.

What to consider before installing

This skill is coherent with its goal of creating a file-based memory system, but it contains a few things you should verify before installing: - Confirm the 'openclaw' CLI exists on your platform and that the openclaw cron add command does what you expect; SKILL.md uses that CLI but the skill does not declare it as required. - Understand what 'Review today's conversations' means in your environment: which transcripts will the cron job access? Does the agent have permission to read all conversation logs? Make sure you are comfortable with the scope and retention of data written to MEMORY.md and memory/YYYY-MM-DD.md. - The cron job runs nightly and acts autonomously — if you want tighter control, either run the extraction manually or remove/modify the scheduled job. Consider testing with dummy data first. - Check the package homepage/source (homepage points to talonforge.xyz) and confirm authorship/trustworthiness if you plan to persist real user data. - If you have sensitive data policies, add clear rules: what to exclude, how long to keep memories, and how to redact secrets. If you cannot verify these points, treat the skill as high-privacy-risk and do not enable its nightly cron or autonomous invocation until you audit its behavior.

AI Memory System Skill

Auto-setup for the 3-layer OpenClaw memory architecture

What It Does

Sets up the complete 3-layer memory system from the Zero-Human Company playbook:

• MEMORY.md (tacit knowledge and preferences)
• Daily notes (memory/YYYY-MM-DD.md)
• Nightly extraction cron job

Setup Instructions

After installing, tell your AI: "Set up the memory system."

Your AI will:

1. Create MEMORY.md with a template
2. Create the memory/ directory
3. Set up a nightly extraction cron at 11pm your timezone
4. Create today's first daily note entry

MEMORY.md Template

# MEMORY.md — Long-Term Memory

## About [User]
- Name: 
- Timezone: 
- Communication preferences: 

## Working Style
- (Observe and update)

## Key Decisions
- (Log important decisions here)

## Lessons Learned
- (Capture mistakes and insights)

## Hard Rules
- (Non-negotiable boundaries)

## Action Log
- YYYY-MM-DD — [Action taken]

Daily Note Template (memory/YYYY-MM-DD.md)

# YYYY-MM-DD

## Key Events
- HH:MM — [What happened]

## Decisions Made
- [Decision and reasoning]

## Facts Extracted
- [Durable facts worth remembering]

## Pending
- [Open items to follow up]

Nightly Extraction Cron

openclaw cron add \
  --name "nightly-extraction" \
  --cron "0 23 * * *" \
  --tz "[YOUR_TIMEZONE]" \
  --session isolated \
  --message "Review today's conversations. Extract durable facts (relationships, decisions, status changes, milestones). Skip small talk. Update memory/YYYY-MM-DD.md with timeline. Update MEMORY.md with new patterns or preferences." \
  --announce

Memory Rules

1. If it matters, WRITE IT DOWN. Mental notes don't survive sessions.
2. Never delete facts — supersede them instead.
3. Update MEMORY.md when you notice new patterns about your user.
4. Daily notes are raw logs. MEMORY.md is curated wisdom.
5. Review and clean MEMORY.md weekly.

Version

1.0 by TalonForge