Skip to main content
affpapa.org
RU EN
skill CX Codex

memory-continue — Claude Code skill: resume work across sessions

This skill rebuilds context from the Basic Memory graph so your assistant picks up previous work instead of starting cold.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add basicmachines-co/basic-memory --skill memory-continue -a claude-code
Open on GitHub

What memory-continue does

Reach for it at the start of a session, or when you say something like “continue with the refactor” and expect the agent to know what that means. The skill reconstructs the thread from notes stored in Basic Memory.

It walks the knowledge graph with MCP tools. bm_context follows relations outward from a starting note at a chosen depth, bm_project(command="recent") surfaces what changed lately, bm_search finds candidate notes by keyword, and bm_read opens one in full or just a slice. Time windows come as plain words: "today", "3d", "2 weeks", "1 month".

None of those calls work without the Basic Memory MCP server configured, since the skill has nothing else to read from. Project names differ per user, so run bm_project(command="list") first and scope a memory:// URL with a project prefix when you keep several, as in memory://research/papers/crdt.

What it helps with

  • rebuild session context without retelling it yourself
  • locate notes on a topic when the filename is long gone
  • pull related notes around a spec or project
  • see what changed over the past few days
  • continue a task that spans several sessions

Example prompts for the agent

  • Continue work on SPEC-24 and pull the context from memory
  • Where did we leave the Postgres migration?
  • Go back to the async client refactor and show me the last week of changes

How to install memory-continue

1Skills CLI (Vercel)

npx skills add basicmachines-co/basic-memory --skill memory-continue -a claude-code

2Manually: put the files in place

~/.claude/skills/memory-continue/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/memory-continue/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about memory-continue

How do I install memory-continue in Claude Code?

Run npx skills add basicmachines-co/basic-memory --skill memory-continue -a claude-code. The skill lands at ~/.claude/skills/memory-continue/SKILL.md.

What does memory-continue do?

It gathers earlier work from the Basic Memory graph — searching notes, following their relations, listing recent changes — so the assistant resumes where you left off.

What does the skill need to run?

A configured Basic Memory MCP server. The skill calls its tools bm_context, bm_search, bm_read and bm_project, and without the server those calls fail.

Similar skills

All skills for Agent setup: memory, context, orchestration →
setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set14

memory-curate Curates your Basic Memory knowledge graph by connecting orphan notes, proposing typed relations, merging duplicates, and building hub indexes. Useful when accumulated notes become disorganized. CX Codex +1 1,300installs memory-capture Turns the current state of a working thread into one Basic Memory note. Useful mid-thread or at the end, once decisions and context are worth keeping. CX Codex +1 1,300installs memory-notes Guides coding agents on structuring markdown notes for Basic Memory knowledge graphs. It covers YAML metadata, categorized observations, and wiki-style note relations. CX Codex +1 1,300installs memory-research Researches companies, people, and tools across the web and synthesizes findings into Basic Memory notes. Useful when you need to record structured facts about an external subject. CX Codex +1 1,200installs memory-literary-analysis Turns a complete literary work into a Basic Memory knowledge graph with schemas, chapter notes, linked entities, and validation. CX Codex +1 1,200installs memory-lifecycle Automates note status transitions in Basic Memory. It archives completed work into appropriate folders and updates frontmatter without deleting records. CX Codex +1 1,200installs memory-defrag This skill tidies a Basic Memory project by splitting bloated notes, consolidating facts, and flagging contradictions for review. CX Codex +1 1,200installs memory-tasks Keeps work-in-progress as notes in the Basic Memory knowledge graph, so you can find active tasks and resume them after compaction or a restart. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor