Promote Memory — Development skill for Claude Code
Promote one or more learnings from the active project's working.md into either a domain file (cross-project) or the project's memory.md (engagement-specific).
How to install Promote Memory
Installs to ~/.claude/skills/seyio91-ai-memory-system-promote-memory/SKILL.md
mkdir -p ~/.claude/skills/seyio91-ai-memory-system-promote-memory && curl -fsSL https://raw.githubusercontent.com/seyio91/ai-memory-system/HEAD/commands/promote-memory.md -o ~/.claude/skills/seyio91-ai-memory-system-promote-memory/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Promote Memory does
Promote one or more learnings from the active project's `working.md` into either a domain file (cross-project) or the project's `memory.md` (engagement-specific). Multi-select: the agent generates candidates, the user picks which to keep.
Checkpoint archival is separate: use `/checkpoint-archive` to roll the `## Checkpoints` section independently.
Use today's actual date (from `` injection context) for all entries — do not invent.
Step 1 — resolve the active project from the
Alternatives in Development
- Harness Improvement — Update Kandev harness files from session learnings or explicit cross-platform harness requests 697 ★
- Claude Cognitive — Working memory for Claude Code - persistent context and multi-instance coordination 440 ★
- Engage.Memory — Cross-engagement pattern memory — recall prior techniques, record confirmed findings, housekeeping 348 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ad Scope
Define and record the scope of an authorized Active Directory engagement (domain(s), DC IP, initial credential
Harvest Memory
Promote durable learnings from the machine-local per-project memory store into the version-controlled repo mem
Recall Promote
Promote a recall finding (correction/preference/domain fact) into project auto-memory so it survives without n
Active PAGE 3 Native Crossplatform
Active Skills — Page 3: Native, Cross-Platform & Personal Domain
Multi Perspective
Cross-domain expert analysis with cognitive harmonics optimization
Flux Explore
Autonomous multi-round semantic exploration — agents from progressively distant knowledge domains, synthesize
Related Agents
Pentest Commander
Pentest engagement lead. Owns research, planning, multi-domain grow-agent dispatch, cross-target synthesis, an
Melee Coach Analyst
Use this agent when working on MAGI project code that involves Melee game knowledge, replay analysis logic, co
AI Platform Architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-