maintaining-memory

maintaining-memory is a Memory stores & recall skill for AI agents, published by davidlee in the spec-driver repository on GitHub. Skillspace rates maintaining-memory D (57/100) and it passed the safety scan; the rating is based on static analysis only.

Invoke this skill whenever you observe memory drift or when your actions would invalidate existing memories. Mandatory triggers: (1) you change a workflow/command, move files, rename modules, or change invariants; (2) you discover a memory is wrong, missing provenance, or stale; (3) you see a memory record guiding behaviour that is no longer true; (4) you find duplicates or near-duplicates; (5) you are about to add a new memory that overlaps an existing one. Core rule: if you change reality, you must change memory in the same change-set (or immediately after) so future agents do not inherit incorrect guidance.

Grade
D
Quality
57 / 100
Safety
Passed
GitHub stars
26

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
80 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.