skills/memories-sanitize/SKILL.md
Review recent memories and remove invalid or misleading ones from the semantic memory database
npx skillsauth add mahmoudimus/simba memories-sanitizeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review memories and identify those that are invalid, misleading, or outdated. This applies to any work session - debugging, feature development, refactoring, exploration, etc.
List all memories:
simba memory list
Or filter by type:
simba memory list --type GOTCHA
Each memory shows: id, type, confidence, and content.
Review each memory and mark as INVALID if it:
For each invalid memory, delete it:
simba memory delete <MEMORY_ID>
If an invalid memory should be replaced with a correct version:
simba memory store --type WORKING_SOLUTION --content "<CORRECT_LEARNING>" --context "<CONTEXT>" --confidence 0.95
| Type | Use For |
|------|---------|
| GOTCHA | Counterintuitive behaviors, traps, "watch out for this" |
| WORKING_SOLUTION | Commands, code, or approaches that worked |
| PATTERN | Recurring architectural decisions or workflows |
| DECISION | Explicit design choices with reasoning |
| FAILURE | What didn't work and why (useful to avoid repeating) |
| PREFERENCE | User's stated preferences |
Invalid: "Reference equality vs .Equals() mismatch causes graph disconnection" Correct: "Coordinate tolerance 1e-6 too small for reprojected coords; use 0.01m for EPSG:3857"
Invalid: "Use polling for real-time updates in dashboard" Correct: "Use WebSocket for real-time updates - polling caused excessive server load"
Invalid: "ServiceLocator pattern works well for dependency injection" Correct: "Constructor injection preferred - ServiceLocator made testing difficult"
development
Index the current project for optimized search with QMD semantic search and fast file suggestions. Run this when entering a new codebase or after significant changes. Saves 60-80% tokens on exploration tasks.
tools
Show token economics comparing usage with turbo-search vs without. Demonstrates actual savings from search-first approach.
development
Enforce Simba's Codex lifecycle routine for coding tasks. Use when starting or finishing implementation work in a Simba-enabled repo to run `simba codex-status` at start, `simba codex-extract` when extraction is pending, and `simba codex-finalize` before final handoff.
tools
Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.