Documentation synchronization using Mem0 for tracking relationships between specs, architecture, ADRs, and roadmap
/plugin marketplace add vanman2024/dev-lifecycle-marketplace/plugin install planning@dev-lifecycle-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
AGENT-INTEGRATION.mdrequirements.txtscripts/bulk-register-worktrees.pyscripts/full-registry.pyscripts/query-docs.pyscripts/register-worktree.pyscripts/serve-viewer.pyscripts/sync-to-mem0.pyscripts/update-relationships.pyscripts/view-docs.shThis skill provides tools and scripts for intelligently synchronizing documentation across the dev-lifecycle-marketplace using Mem0 for relationship tracking.
Purpose: Keep specs, architecture docs, ADRs, and roadmap interconnected and updated when dependencies change.
specs/{number}-{name}/spec.md) - Feature specifications derived from architecturedocs/architecture/*.md) - System design and component specificationsdocs/adr/*.md) - Architecture Decision Recordsdocs/ROADMAP.md) - Project timeline and milestonesUses Mem0 OSS (in-memory Qdrant) to store natural language relationships:
# Example memory
"Specification 001 (user-authentication) is derived from
architecture/security.md sections #authentication and #jwt-tokens,
and references ADR-0008 OAuth decision"
scripts/sync-to-mem0.pyScans documentation and populates Mem0 with relationships.
Usage:
python scripts/sync-to-mem0.py
What it does:
specs/*/spec.md files@docs/architecture/file.md#sectiondependencies: [001, 002]scripts/query-relationships.pyQuery Mem0 for documentation relationships.
Usage:
# Find specs that depend on a doc
python scripts/query-relationships.py "What specs depend on architecture/security.md?"
# Find all references to an ADR
python scripts/query-relationships.py "Which specs reference ADR-0008?"
# Get spec dependencies
python scripts/query-relationships.py "What does spec 001 depend on?"
scripts/validate-docs.pyValidate documentation consistency using Mem0.
Usage:
python scripts/validate-docs.py
Checks:
Spec Memory:
Specification {number} ({name}) is derived from architecture/{file}.md
sections {sections}, references ADR-{numbers}, and depends on specs {deps}.
Status: {status}. Last updated: {date}
Architecture Memory:
Architecture document {file}.md has sections: {sections}.
Section {section} is referenced by specs {spec_numbers}
Derivation Chain:
When architecture/{file}.md #{section} changes, these specs need review:
{spec_list}
# Navigate to project root
cd /path/to/dev-lifecycle-marketplace
# Run sync to populate Mem0
python plugins/planning/skills/doc-sync/scripts/sync-to-mem0.py
# Output:
# ✅ Scanned 15 specs
# ✅ Found 42 architecture references
# ✅ Created 57 memories in Mem0
# 📊 Project: dev-lifecycle-marketplace
# Check what's affected by changing security.md
python plugins/planning/skills/doc-sync/scripts/query-relationships.py \
"What specs are derived from architecture/security.md?"
# Output:
# Specs affected by architecture/security.md:
# - 001-user-authentication (sections: #authentication, #jwt-tokens)
# - 005-admin-panel (sections: #rls-policies)
# - 012-sso-integration (sections: #oauth)
# Check documentation consistency
python plugins/planning/skills/doc-sync/scripts/validate-docs.py
# Output:
# ✅ All architecture references valid
# ⚠️ Spec 003 references missing ADR-0015
# ⚠️ Circular dependency: 007 → 008 → 007
# ❌ Broken reference: @docs/architecture/deleted.md
The scripts use Mem0 OSS with in-memory Qdrant (no external dependencies):
config = {
"vector_store": {
"provider": "qdrant",
"config": {
"collection_name": "documentation",
"host": "memory", # in-memory mode
}
}
}
Uses user_id for multi-project support:
# Add memory for specific project
m.add(memory_text, user_id="dev-lifecycle-marketplace")
# Query specific project
m.search(query, user_id="dev-lifecycle-marketplace")
This skill powers these planning commands:
/planning:doc-sync - Populate Mem0 with current documentation/planning:impact-analysis <doc-path> - Show what's affected by changes/planning:validate-docs - Check documentation consistency/planning:update-docs - Interactive sync with user approvalRun sync after major changes:
# After updating architecture or ADRs
python scripts/sync-to-mem0.py
Check impact before modifying shared docs:
# Before editing architecture/security.md
python scripts/query-relationships.py "specs depending on security.md"
Validate before commits:
# Add to pre-commit hook
python scripts/validate-docs.py || exit 1
Use natural language queries:
# Install in virtual environment
python -m venv venv
source venv/bin/activate # or venv\Scripts\activate on Windows
pip install mem0ai
Ensure you're in the virtual environment where Mem0 is installed:
source /tmp/mem0-env/bin/activate
python scripts/sync-to-mem0.py
Run the sync script first to populate Mem0:
python scripts/sync-to-mem0.py
plugins/planning/README.mdplugins/planning/skills/spec-management/plugins/planning/skills/architecture-patterns/This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.