OpenParable
Skip to content
← Back to skills

Sync Ssot From Memory

Productivity
sync-ssot-from-memory

Sync Ssot From Memory is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Promotes important observations from memory systems (Claude-mem, Serena) to SSOT (decisions.md, patterns.md). Use when user mentions SSOT promotion, sync memory, save learnings, or before Plans.md cleanup. Do NOT load for: ad-hoc notes, implementation work, or reviews.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/context-management/sync-ssot-from-memory/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/sync-ssot-from-memory, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Sync SSOT from Memory

Promote important observations recorded in memory systems (Claude-mem or Serena) to the project's SSOT: .claude/memory/decisions.md and .claude/memory/patterns.md.

Quick Reference

  • "Save what we learned for next time" → this skill
  • "Promote important decisions to SSOT" → this skill
  • "Organize decisions (why) and methods (how) separately" → Reflect in decisions/patterns separately

Supported Memory Systems

SystemDetectionHow to Get Observations
Claude-mem~/.claude-mem/settings.jsonmcp__plugin_claude-mem_mcp-search__search
Serena.serena/memories/mcp__serena__read_memory

Auto-detected at execution, using available system.

Execution Flow

Step 0: Detect Memory System

# Claude-mem check
if [ -f "$HOME/.claude-mem/settings.json" ]; then
  MEMORY_SYSTEM="claude-mem"
fi

# Serena check
if [ -d ".serena/memories" ]; then
  MEMORY_SYSTEM="serena"
fi

Step 1: Extract SSOT Promotion Candidates

For Claude-mem:

  • Search for type:decision
  • Search for type:discovery concepts:pattern
  • Search for type:bugfix concepts:gotcha

For Serena:

  • List and read relevant memories

Step 2: Filter by Promotion Criteria

Decisions Candidates (Why) → decisions.md:

  • Technology selection reasons
  • Guardrail reasons
  • User requirements/constraints

Patterns Candidates (How) → patterns.md:

  • Recurrence prevention (bugfixes)
  • Reusable solutions
  • Implementation patterns

Exclusions:

  • Work-in-progress rough notes
  • Personal/confidential information
  • One-time tasks (not reusable)

Step 3: Reflect to SSOT

Add entries to decisions.md and patterns.md with:

  • Unique ID (D{N} or P{N})
  • Date, Tags, Observation ID
  • Structured content (Conclusion, Background, Options, etc.)

Step 4: Output Summary

## SSOT Promotion Results

### Added/Updated
| File | Item | Observation ID |
|------|------|----------------|
| decisions.md | D{N}: {Title} | #{id} |
| patterns.md | P{N}: {Title} | #{id} |

### Excluded
- Work-in-progress: N items
- Duplicates: N items

Fallback on Failure

If memory system is inaccessible, ask user to paste observation content manually.