Team project memory
Skill meharajM/context-machine/packages/team-project-memory-skill/skills/team-project-memory
Token-efficient shared project memory skills for developers and AI coding agents.
npx -y skills add meharajM/context-machine --skill team-project-memoryAssembled 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
Route shared project-memory work to the smallest specialized skill. Use when configuring, using, reviewing, or improving reusable knowledge shared across developers, agents, sessions, or machines.
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
1.1 KB, 170 tokens by cl100k_base, as published. Nobody here has run it
Team Project Memory Router
Prevent repeated investigation without loading a large workflow into every task.
Route
Load only the skill needed now:
- Before recurring debugging, setup, build, test, deployment, performance, or architecture work: use
$team-memory-search. - After a non-obvious result is verified and worth reusing: use
$team-memory-capture. - For setup, duplicate cleanup, contradictions, staleness, retention, or archiving: use
$team-memory-maintenance.
Do not load all three unless the task spans all phases.
Invariants
- Repo and path instructions outrank shared memory.
- Implicit use is read-only.
- Shared memory is evidence, not source of truth.
- Never store secrets, personal/customer data, or unredacted confidential logs.
- User absence is never permission to publish.