Lucid Dreamer

Nightly AI memory reasoning system. Lucid runs every night while you sleep — it reads your daily notes and memory files, detects stale facts, unresolved todo...

Security Scan

The skill's code, instructions, and requested capabilities are consistent with a nightly memory-review tool; nothing requested is disproportionate to its stated purpose.

Purpose & Capability

Name/description (nightly memory review, trend detection) align with the actual behavior. Requiring git (for local commits), date (for commit timestamps), and python3 (to run trend_detection.py) is reasonable. The skill reads/writes only workspace markdown files and a local state.json which is consistent with its purpose. One minor documentation inconsistency: README once claims "No Python"/"no runtime dependencies" while SKILL.md and the metadata correctly declare python3 required for trend detection.

Instruction Scope

Runtime instructions explicitly limit reads to workspace files (MEMORY.md, USER.md, last 7 daily notes) and forbid reading memory/review/*.md to avoid circular reasoning. It writes review files, state.json, and a .last-success sentinel. Auto-apply writes to MEMORY.md and commits locally; the skill explicitly states it will not push to remotes and auto-apply is opt-in/disabled by default. No instructions direct data to external endpoints or request unrelated system files/credentials.

Install Mechanism

This is an instruction-only skill with included Python script(s) but no install spec — nothing is downloaded from external URLs or installed automatically. The only runtime requirement is an interpreter (python3) already declared; executing the included script is expected and low risk. Pre-scan found no injection signals.

Credentials

No credentials or secret environment variables are requested. CLAWD_DIR is offered as an optional workspace path (not required). The set of environment/binary requirements is minimal and proportionate to reading/writing a local workspace and running the trend script.

Persistence & Privilege

always:false and auto-apply disabled by default. The skill can be scheduled (cron) per user instructions, which is expected. It writes local files and may create local git commits when auto-apply is enabled — this is documented and revertable via git. There is no attempt to modify other skills or system-wide agent configs.

Assessment

This skill appears coherent and implements what it claims, but review these before running: 1) Set CLAWD_DIR to the correct workspace so it only reads intended files. 2) Do not run it against a workspace that contains unencrypted secrets or API keys in plaintext markdown files—the skill reads all workspace markdown. 3) Auto-apply (writes + local git commits) is opt-in and disabled by default; only enable after reviewing several nightly outputs. 4) The trend detection runs a local Python script (python3 required) — inspect scripts/trend_detection.py before executing in a sensitive environment. 5) The README contains a small mismatch (it once claims "no Python"), but SKILL.md correctly documents python3 is needed. If you want extra caution, run the skill once manually in an isolated test workspace to verify behavior before scheduling it nightly.

Your AI sleeps. Lucid dreams.

Lucid keeps your AI's memory clean. Every night, it reads what happened, checks what your AI already knows, and suggests what's outdated, missing, or forgotten.

See README.md for full setup, ARCHITECTURE.md for internals, and config/ for configuration.

Quick Setup

1. Set your workspace path in the config:

   export CLAWD_DIR=/path/to/your/workspace
   

2. Create a nightly cron job using OpenClaw's cron tool — run the prompt in prompts/nightly-review.md at 3 AM.

3. Wake up to a review report in memory/review/YYYY-MM-DD.md.

4. Approve or reject suggestions — Lucid tracks state in memory/review/state.json.

Files

• prompts/nightly-review.md — the main nightly review prompt
• config/ — thresholds and behavior settings
• examples/ — sample review output and state file

Security

Files read at runtime:

• MEMORY.md — long-term agent memory summary
• USER.md — user profile and preferences
• Last 7 daily notes (memory/YYYY-MM-DD.md)

Files written at runtime:

• memory/review/YYYY-MM-DD.md — the generated review report
• memory/review/state.json — approval/rejection tracking state

What this skill is designed to avoid:

• Avoid suggesting or outputting passwords, API keys, tokens, or other credentials in generated memory updates
• Never accesses files outside the configured workspace directory
• Never pushes to remote git automatically — all commits are local only, and no git push is performed unless you explicitly run it
• Announce/notification delivery is opt-in and off by default — no messages are sent without explicit configuration

Recommendations:

• Set CLAWD_DIR explicitly in your environment to ensure the skill operates on the correct workspace
• This skill reads workspace markdown files such as MEMORY.md, USER.md, and recent daily notes. Do not run it on a workspace containing unencrypted API keys or other secrets in plain markdown files.
• Review generated reports before approving suggestions — Lucid proposes changes, but you remain in control