How do I install the Memory Workflow skill?

Run npx skillmds add majiayu000/memory-workflow 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 Memory Workflow safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Memory Workflow?

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 Memory Workflow free to use?

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

Who published Memory Workflow?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Memory Workflow by majiayu000 — Agent Skill

Name: Memory Workflow
Rating: 4.2 (5 reviews)
Author: majiayu000

Memory Workflow

Data workflow, memory system separation, and observation rules for git-review. Defines which memory system to use for what, and how to avoid duplication. Use when saving decisions, recording observations, or managing cross-session state.

majiayu000 ede1585 2 files · 3.6 KB Updated Sep 9, 2026 567 repo stars

File contents

Memory & Data Workflow

Data Workflow (ENFORCED)

Linear = single source of truth for requirements, status, and acceptance criteria
claude-mem = cross-session decision memory (supplements Linear, never duplicates)
Local plan files = ONLY the planner agent writes these (plans/<feature>-plan.md), for code-level implementation detail too granular for Linear. All other agents write to Linear comments.
Requirements, specs, critiques, and review results go to Linear comments, not local files

Memory System Separation

System	Purpose	What to Store
claude-mem	Human-driven	User preferences, architectural decisions, debugging insights, cross-session learnings
Claude-Flow	Agent-driven	Agent coordination patterns, code optimization history, model performance data
Serena	Code-driven	Project code structure, conventions, build commands (auto-discovered via onboarding)
Linear	Project management	Ticket requirements, acceptance criteria, status tracking

No overlap: Each memory system serves a distinct purpose; never duplicate content across systems.

claude-mem 3-Layer Workflow

search(query) — Get compact index with IDs (~50-100 tokens/result)
timeline(anchor=ID) — Get chronological context around interesting results
get_observations([IDs]) — Fetch full details ONLY for filtered IDs

NEVER skip to get_observations without filtering first (saves ~10x tokens).

When to Save (claude-mem)

User states a preference or working style
An architectural or design decision is made
You discover a non-obvious project convention or pattern
A debugging session yields a reusable insight
A mistake is made that others (or future you) should avoid

When NOT to Save

Transient debugging context (one-off stack traces, temp workarounds)
Information already in CLAUDE.md, README, or docs
Obvious facts derivable from reading the code

Observation Rules

Memory observer agents are DEPRECATED — use /checkpoint skill instead
If observers must be used: only record what was actually observed. Never fabricate details.
If a session has minimal activity, record that limitation explicitly rather than padding with assumptions

MCP Server Usage

claude-mem: Cross-session memory only. Save decisions/patterns (brief). NEVER duplicate Linear content.
Linear: Source of truth for requirements, status, and acceptance criteria. ALL tickets tracked there.

---name: memory-workflowdescription: Data workflow, memory system separation, and observation rules for git-review. Defines which memory system to use for what, and how to avoid duplication. Use when saving decisions, recording observations, or managing cross-session state.--- # Memory & Data Workflow ## Data Workflow (ENFORCED) - **Linear** = single source of truth for requirements, status, and acceptance criteria - **claude-mem** = cross-session decision memory (supplements Linear, never duplicates) - **Local plan files** = ONLY the planner agent writes these (`plans/<feature>-plan.md`), for code-level implementation detail too granular for Linear. All other agents write to Linear comments. - Requirements, specs, critiques, and review results go to **Linear comments**, not local files ## Memory System Separation | System | Purpose | What to Store | |--------|---------|---------------| | claude-mem | Human-driven | User preferences, architectural decisions, debugging insights, cross-session learnings | | Claude-Flow | Agent-driven | Agent coordination patterns, code optimization history, model performance data | | Serena | Code-driven | Project code structure, conventions, build commands (auto-discovered via onboarding) | | Linear | Project management | Ticket requirements, acceptance criteria, status tracking | **No overlap:** Each memory system serves a distinct purpose; never duplicate content across systems. ## claude-mem 3-Layer Workflow 1. **`search(query)`** — Get compact index with IDs (~50-100 tokens/result) 2. **`timeline(anchor=ID)`** — Get chronological context around interesting results 3. **`get_observations([IDs])`** — Fetch full details ONLY for filtered IDs NEVER skip to `get_observations` without filtering first (saves ~10x tokens). ## When to Save (claude-mem) - User states a preference or working style - An architectural or design decision is made - You discover a non-obvious project convention or pattern - A debugging session yields a reusable insight - A mistake is made that others (or future you) should avoid ## When NOT to Save - Transient debugging context (one-off stack traces, temp workarounds) - Information already in CLAUDE.md, README, or docs - Obvious facts derivable from reading the code ## Observation Rules - Memory observer agents are DEPRECATED — use `/checkpoint` skill instead - If observers must be used: only record what was actually observed. Never fabricate details. - If a session has minimal activity, record that limitation explicitly rather than padding with assumptions ## MCP Server Usage - **claude-mem:** Cross-session memory only. Save decisions/patterns (brief). NEVER duplicate Linear content. - **Linear:** Source of truth for requirements, status, and acceptance criteria. ALL tickets tracked there.

Frequently asked questions