Reviewing Memory
- 68 installs
- 1 repo stars
- Updated August 3, 2026
- davidlee/doctrine
reviewing-memory is a Doctrine agent skill that performs structured memory corpus audits with doctrine memory validate so developers can prune and re-anchor memories before risky changes.
About
reviewing-memory is a Doctrine skill for structured memory corpus audits before high-risk changes. It pulls validation findings across the corpus, inspects high-impact entries, and records outcomes so agents do not rely on drifting facts. Run it ahead of releases or migrations or when retrieval quality drops.
- Runs doctrine memory validate corpus-wide to build an audit queue
- Targets releases, schema migrations, ADR boundary changes, or confused retrieve results
- Documents MCP memory_show shortcut when doctrine MCP server is connected
- Produces auditable per-memory outcomes after inspection
Reviewing Memory by the numbers
- 68 all-time installs (skills.sh)
- Ranked #524 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davidlee/doctrine --skill reviewing-memoryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 68 |
|---|---|
| repo stars | ★ 1 |
| Last updated | August 3, 2026 |
| Repository | davidlee/doctrine ↗ |
How do you know agent memory is still trustworthy before a release, migration, or large refactor when retrieve starts contradicting itself?
Audit Doctrine memories with doctrine memory validate before releases or migrations when retrieve returns contradictions or low confidence.
Who is it for?
Doctrine users who run CLI or MCP memory tools and need auditable memory cleanup before stability-sensitive work.
Skip if: Projects skipping Doctrine memory entirely or teams unwilling to run corpus-wide validate output review.
When should I use this skill?
You face a release, migration, ADR shift, or bad retrieve results and invoke reviewing-memory to audit the corpus.
What you get
An audit queue from validate, inspected high-impact memories, and documented corrective outcomes per entry.
Related skills
Improve Codebase ArchitectureSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.566k196k
Caveman ReviewGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.270k94.7kCodebase DesignShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.266k196kCavecrewDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.220k94.7kCode ReviewReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.201k196k
Requesting Code ReviewDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.183k264kFAQ
What command seeds the audit queue?
Skill procedure starts with doctrine memory validate corpus-wide without REF to surface dangling relations and stale verifications.
When is this skill recommended?
Skill text cites releases, schema migrations, subsystem ADR shifts, or contradictory low-confidence retrieve results.
Is there an MCP alternative to CLI show?
Skill notes memory_show via doctrine MCP when the server is connected for machine-parseable JSON.