agentsclimarketplace

Local file memory

Skill wchen02/cursor-agent-learning/.cursor/skills/local-file-memory

Use a Markdown file in the repo as persisted agent memory across chats. Use when the user wants session-spanning context, a decision log, or to resume work without re-pasting history.From its SKILL.md

Install
npx -y skills add wchen02/cursor-agent-learning --skill local-file-memory

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 352 tokens by cl100k_base, as published. Nobody here has run it

Local file memory

Teach and apply the local file pattern for agent memory: read before work, update after.

Steps

  1. Resolve path — Default: .cursor/agent-memory/MEMORY.md. If missing, copy the starter from examples/agent-frameworks/local-file-memory-template/MEMORY.md and create the directory.

  2. Read first — Open the memory file and summarize Current focus, Decisions, and Open questions in chat (or use them silently if the user only asked for edits).

  3. Do the task — Follow the user’s request; align with Do not forget and past Decisions.

  4. Update memory — After substantive work, edit the file: refresh Current focus, append dated lines under Decisions, check off or add Open questions, extend Do not forget if new constraints appeared. Optionally add a line under Session log.

  5. Stay safe — Do not store secrets (keys, tokens) in memory files. See local-file-memory.md.

Reference

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.