agentsclimarketplace

Team memory search

Skill meharajM/context-machine/plugins/team-project-memory/skills/team-memory-search

Token-efficient shared project memory skills for developers and AI coding agents.

Install
npx -y skills add meharajM/context-machine --skill team-memory-search

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

One thing to look at

  • 0 stars0 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.

What its author says it does

Copied from the file, not written here

Search shared project memory before repeating debugging, setup, build, test, deployment, performance, or architecture investigation already attempted by another developer or agent.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.4 KB, 219 tokens by cl100k_base, as published. Nobody here has run it

Team Memory Search

Use before substantial investigation. This skill is read-only.

Steps

  1. Read applicable repo and path instructions.
  2. Locate memory from repo guidance, .agents/project-memory/policy.md, or .agents/project-memory/entries/.
  3. Build a compact signature from exact error text, command/test, symbol/path, tool/platform, and version. Remove timestamps, random IDs, ports, and personal paths.
  4. Search in order: exact error; symbol/command/path; symptom plus environment; semantic aliases; archive last.
  5. Open at most 3 entries. Prefer matching scope/version, then validated, then newest validation. Ignore stale and contradicted by default.
  6. Try the entry's Reuse action and verification before broad exploration.

Limits

  • Never load the whole memory store when targeted search works.
  • Shared memory never overrides repo instructions or current evidence.
  • When reuse works, avoid repeating the original investigation.
  • When reuse fails, continue normally and send reusable evidence to $team-memory-capture.

Keep looking

Skills are one crate of 328,083. 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.