How do I install the Six Layer Memory skill?

Run npx skillmds@latest add lord1egypt/six-layer-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Six Layer Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Six Layer Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Six Layer Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Six Layer Memory?

Lord1Egypt (@lord1egypt) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Six Layer Memory by lord1egypt — Agent Skill

Name: Six Layer Memory
Rating: 4.2 (5 reviews)
Author: Lord1Egypt

Six Layer Memory

Set up or repair a local-first six-layer memory structure for an OpenClaw/Codex workspace. Use when a user wants durable HOT/WARM/COLD/CURATED memory files, local maintenance helpers, and per-workspace memory hygiene. This public package does not include cloud sync, external API upload, secret collection, cookies, or login-state handling.

Lord1Egypt Updated Sep 8, 2026 2 repo stars

File contents

Six-Layer Memory

Use this skill when the user wants a workspace to keep memory proactively instead of relying on chat context alone.

What this skill sets up

HOT: memory/SESSION-STATE.md
WARM: local vector/index refresh when source material changes
COLD: memory/decisions/
CURATED: MEMORY.md plus daily logs
LOCAL-AUTO: optional local maintenance log and digest checks, with no external API calls

Workflow

Pick the target workspace.
Run scripts/install_workspace.sh <workspace>.
Review the created files before adding any schedule.
Add periodic execution only after the user confirms the schedule:

0 6 * * * /usr/bin/python3 <workspace>/memory/auto_memory_6layer.py --workspace <workspace> --daily --source memory-daily

Validate with memory/check_memory_layers.sh.

Bundled scripts

scripts/install_workspace.sh
scripts/auto_memory_6layer.py
scripts/memory_writer.py
scripts/check_memory_layers.sh

Notes

This skill is designed per workspace. Repeat installation for each agent workspace.
Do not overwrite HOT state with synthetic “all good” status text.
Prefer one canonical HOT file path: memory/SESSION-STATE.md.
Keep MEMORY.md for durable facts only. Put operational notes elsewhere.
Do not store API keys, access tokens, cookies, login state, or customer private data in public skill files, shared templates, or examples.
If a user wants cloud sync, treat it as a separate private extension: explain the risks, ask for explicit confirmation, and keep keys outside the published skill.

References

Local-first guide: references/local-first-guide.md

---name: six-layer-memorydescription: Set up or repair a local-first six-layer memory structure for an OpenClaw/Codex workspace. Use when a user wants durable HOT/WARM/COLD/CURATED memory files, local maintenance helpers, and per-workspace memory hygiene. This public package does not include cloud sync, external API upload, secret collection, cookies, or login-state handling.---# Six-Layer MemoryUse this skill when the user wants a workspace to keep memory proactively instead of relying on chat context alone.## What this skill sets up- HOT: `memory/SESSION-STATE.md`- WARM: local vector/index refresh when source material changes- COLD: `memory/decisions/`- CURATED: `MEMORY.md` plus daily logs- LOCAL-AUTO: optional local maintenance log and digest checks, with no external API calls## Workflow1. Pick the target workspace.2. Run `scripts/install_workspace.sh <workspace>`.3. Review the created files before adding any schedule.4. Add periodic execution only after the user confirms the schedule:```cron0 6 * * * /usr/bin/python3 <workspace>/memory/auto_memory_6layer.py --workspace <workspace> --daily --source memory-daily```5. Validate with `memory/check_memory_layers.sh`.## Bundled scripts- `scripts/install_workspace.sh`- `scripts/auto_memory_6layer.py`- `scripts/memory_writer.py`- `scripts/check_memory_layers.sh`## Notes- This skill is designed per workspace. Repeat installation for each agent workspace.- Do not overwrite HOT state with synthetic “all good” status text.- Prefer one canonical HOT file path: `memory/SESSION-STATE.md`.- Keep `MEMORY.md` for durable facts only. Put operational notes elsewhere.- Do not store API keys, access tokens, cookies, login state, or customer private data in public skill files, shared templates, or examples.- If a user wants cloud sync, treat it as a separate private extension: explain the risks, ask for explicit confirmation, and keep keys outside the published skill.## References- Local-first guide: `references/local-first-guide.md`

Frequently asked questions