From demarkus-memory
Saves, recalls, and queries persistent personal notes across Claude Code sessions via demarkus-memory MCP tools on a local versioned markdown store organized by project.
How this skill is triggered — by the user, by Claude, or both
Slash command
/demarkus-memory:memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill routes "remember" / "recall" intents through the `demarkus-memory` MCP server (a local demarkus-server), which provides a versioned, link-graph-aware personal memory store. The store is organized by project: top-level `/index.md` is a project list, and each project lives at `/<slug>/` with a consistent internal structure.
This skill routes "remember" / "recall" intents through the demarkus-memory MCP server (a local demarkus-server), which provides a versioned, link-graph-aware personal memory store. The store is organized by project: top-level /index.md is a project list, and each project lives at /<slug>/ with a consistent internal structure.
Trigger on phrases and intents like:
Do NOT trigger for ephemeral context ("remember that in this conversation we're using Python 3.12") — that belongs in the current session, not the persistent store.
Before reading or writing, resolve the project slug:
CLAUDE_PROJECT_DIR env var (via the Bash tool: basename "$CLAUDE_PROJECT_DIR"). Convert to a lowercase slug if needed (spaces → hyphens).CLAUDE_PROJECT_DIR is unset or the user is clearly asking about a different project, ask which project./<slug>/ subtree), create it on first write by publishing the relevant file(s) and adding a link to /index.md.Each /<project>/ subtree has a fixed layout:
/<project>/plan/tasks.md — active work, priorities, what's in flight/<project>/architecture.md — system design, module boundaries, key decisions/<project>/patterns.md — code patterns, conventions, idioms/<project>/roadmap.md — done, next, not prioritized/<project>/adr/<NNNN>-<slug>.md — Architecture Decision Records (one per decision, zero-padded 4-digit sequence)/<project>/journal/<YYYY-MM-DD>.md — dated session notes, one file per dayRead intents → start with mark_fetch:
/index.md to see the project list/<project>/ (directory listing) or a specific file under itmark_backlinks or mark_graph to surface related documents across projectsWrite intents — route to the right file for the content type:
/<project>/journal/<YYYY-MM-DD>.md. If the file does not exist yet, create it with mark_publish (expected_version: 0) and a header like # <Project> journal — <YYYY-MM-DD>, then append on subsequent calls. The /soul-journal command handles this automatically./<project>/adr/<NNNN>-<slug>.md with mark_publish (expected_version: 0). Pick the next sequence number by listing the adr/ directory. Standard ADR template: # <NNNN>. <Title>, ## Status, ## Context, ## Decision, ## Consequences./<project>/patterns.md. Fetch first if updating an existing section; otherwise mark_append with expected_version unset./<project>/architecture.md, update the relevant section, publish with the correct expected_version./<project>/plan/tasks.md./<project>/roadmap.md.Always reference what you saved by full path so the user can find it again.
When the user wants to start memory for a project that does not exist in /index.md yet:
CLAUDE_PROJECT_DIR, lowercased, spaces → hyphens)architecture.md stub) with mark_publish expected_version: 0/index.md, add a bullet - [<Project Name>](/<slug>/) under the project list, and publish with the correct expected_versionmark_fetch returns not-found, the document does not exist — say so./<project>/ subtrees except for /index.md itself.npx claudepluginhub latebit-io/demarkus --plugin demarkus-memoryLoads, saves, and applies durable project memory from MEMORY.md at repo root. Activates on 'remember this' commands, session starts with file, or mistake corrections.
PROACTIVELY query Forgetful MCP (mcp__forgetful__* tools) when starting work on any project, when user references past decisions or patterns, when implementing features that may have been solved before, or when needing context about preferences. Save important decisions, patterns, and architectural insights to memory.
Manages persistent semantic memory across sessions: store/retrieve knowledge/TODOs/issues, hybrid semantic search, hierarchy/tags organization, and maintenance tools.