claude-os/templates/commands/claude-os-save.md
Bob Roberts ddf3bac39b CRITICAL FIXES: Consolidate templates + API improvements
This commit fixes several critical issues found during comprehensive review:

## CRITICAL FIX: Template Consolidation ⚠️
- Moved 6 commands from ~/.claude/commands/ to templates/commands/
- Moved 3 skills from ~/.claude/skills/ to templates/skills/
- Team sharing was BROKEN without this (symlinks pointed to empty dirs)
- Updated README with prominent consolidation step warning
- Commands: list, remember, save, search, session, triggers
- Skills: initialize-project, remember-this, memory

## HIGH PRIORITY FIXES:
- ✅ Completed selective semantic indexing (removed TODO at line 878)
- ✅ Fixed PostgreSQL references in health check (system uses SQLite)
- ✅ Created comprehensive API documentation (docs/API_REFERENCE.md)
- ✅ Added Depends import to fix authentication endpoints

## DOCUMENTATION:
- Added complete API_REFERENCE.md (60+ endpoints documented)
- Created HYBRID_INDEXING_INTEGRATION.md (5 KB architecture)
- Updated README with API docs link + consolidation warning
- Documented all hybrid indexing endpoints with examples

## IMPROVEMENTS:
- Selective semantic indexing now actually ingests files (was placeholder)
- Health check now correctly queries SQLite instead of PostgreSQL
- All authentication endpoints now functional
- Structural indexing stores as pure JSON (no embeddings)

Impact: Team sharing now works, all features documented, critical bugs fixed.
Tested: Pistn indexing (3,117 files in 3 seconds) ✅

🚀 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-31 14:23:43 -05:00

2.1 KiB

Claude OS Save Command

You are helping save important context to Claude OS knowledge bases.

User's Request

The user ran: /claude-os-save

Your Task

  1. Determine what to save:

    • Look at recent conversation context
    • If user specified content after the command, use that
    • Otherwise, ask what they want to save
  2. Ask for details (if not provided):

    • Title for the document
    • KB name (default: Pistn-project_memories)
    • Category (e.g., Architecture, Integration, Pattern, Troubleshooting, Design Decision)
  3. Format the content as markdown:

# [Title]

**Date Saved**: [YYYY-MM-DD]
**Category**: [Category]

---

## Context

[Main content here - well structured with headers, bullet points, code examples as needed]

---

*Saved to Claude OS - Your AI Memory System*
  1. Save the file:

    • Create temp file: /tmp/[sanitized_title].md
    • Upload using curl:
    curl -s -X POST \
      "http://localhost:8051/api/kb/[KB_NAME]/upload" \
      -F "file=@/tmp/[filename].md" \
      -w "\n%{http_code}"
    
  2. Confirm success:

    • ✅ Saved to Claude OS!
    • 📁 KB: [KB Name]
    • 📄 File: [filename]
    • 📦 Chunks: [number]

Available KBs

  • Pistn-project_memories - Project decisions, patterns, solutions
  • Pistn-project_profile - Architecture, standards, practices (usually don't write here)
  • Pistn-project_index - Codebase index (automated, don't write here)
  • Pistn-knowledge_docs - Documentation (usually don't write here)

Examples

Example 1: /claude-os-save Design decision for new feature

  • Ask for: Category, details about the decision
  • Save to: Pistn-project_memories

Example 2: /claude-os-save This bug fix about N+1 queries - KB: Pistn-project_memories - Category: Troubleshooting

  • Extract: title, KB, category from command
  • Ask for: the actual content/details

Important

  • Claude OS is YOUR memory system - use it liberally
  • Save decisions, patterns, solutions, insights, edge cases
  • Well-formatted markdown makes future searches better
  • Always confirm successful save with HTTP 200 response