mahmoudimus/memories-learn
skills/memories-learn/SKILL.md
Extract learnings from session transcripts and store in semantic memory database
$ install --global
skillsauthnpx skillsauth add mahmoudimus/simba memories-learnInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 3, 2026, 4:27 AM76.3s1 file scanned
SKILL.md
- name:
- memories-learn
- description:
- Extract learnings from session transcripts and store in semantic memory database
- allowed-tools:
- Task, Bash(simba *)
Check the dispatch mode:
simba config get hooks.learn_async
Then read ~/.claude/transcripts/latest.json to get the transcript path, session ID, and project path.
Build this Task prompt:
Read the transcript at <TRANSCRIPT_PATH> and extract learnings to store in the semantic memory database.
For each learning found, store it by running:
simba memory store --type <TYPE> --content "<LEARNING>" --context "<CONTEXT>" --confidence <SCORE> --session-source "<SESSION_ID>" --project-path "<PROJECT_PATH>"
LEARNING TYPES:
- WORKING_SOLUTION: Commands, code, or approaches that worked
- GOTCHA: Traps, counterintuitive behaviors, "watch out for this"
- PATTERN: Recurring architectural decisions or workflows
- DECISION: Explicit design choices with reasoning
- FAILURE: What didn't work and why
- PREFERENCE: User's stated preferences
RULES:
- Be specific - include actual commands, paths, error messages
- Confidence 0.95+ for explicitly confirmed, 0.85+ for strong evidence
- Skip generic programming knowledge Claude already knows
- Focus on user-specific infrastructure, preferences, workflows
- Keep content under 200 characters, use context field for details
- Preserve proper nouns, file paths, and identifiers verbatim — never replace them with generic words
- Preserve numeric precision: keep exact values exact; never weaken an exact number to a range or approximation
- Resolve relative dates to absolute ones (e.g. "yesterday" -> the actual date)
Extract 5-15 quality learnings.
Dispatch using the Task tool with subagent_type=memory-extractor:
- If hooks.learn_async is "true": set run_in_background=true (fire and forget)
- Otherwise: dispatch normally and wait for completion
Related Skills
mahmoudimus/turbo-index
development
VerifiedTrustedCommunity
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.
4SKILL.mdUpdated Jun 5, 2026
mahmoudimus/token-stats
tools
VerifiedTrustedCommunity
Show token economics comparing usage with turbo-search vs without. Demonstrates actual savings from search-first approach.
4SKILL.mdUpdated Jun 5, 2026
mahmoudimus/simba-codex-lifecycle
development
VerifiedTrustedCommunity
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.
4SKILL.mdUpdated Jun 5, 2026
mahmoudimus/remember
tools
VerifiedTrustedCommunity
Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.
4SKILL.mdUpdated Jun 5, 2026