qredence/agentic-fleet/memory-system-guide

Claude Code and agent skill by qredence/agentic-fleet

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install qredence/agentic-fleet/memory-system-guide

SKILL.md

AgenticFleet Memory System Guide

A comprehensive guide to using the Two-Tier Memory System (Local + Chroma Cloud) for persistent agent context.

Context

When to use this skill:

  • You are a new agent or contributor starting a session.
  • You need to recall past architectural decisions or debugging solutions.
  • You want to save a new complex solution for the future.

Prerequisites:

  • Python dependencies installed: uv pip install -r .context/scripts/requirements.txt
  • Chroma Cloud configured in .context/.chroma/config.yaml.

Step-by-Step Guide

1. Initialization

At the start of a session, always hydrate the local context.

bash
uv run python .fleet/context/scripts/memory_manager.py init
2. Recalling Information (Semantic Search)

To find information stored in Chroma Cloud:

bash
uv run python .fleet/context/scripts/memory_manager.py recall "how to fix cors error"

This queries the semantic (facts) and procedural (skills) collections.

3. Learning (Saving New Skills)

When you solve a tough problem:

  1. Create a markdown file in .context/skills/ (e.g., fix-auth-bug.md).
  2. Use the SKILL_TEMPLATE.md structure.
  3. Index it into Chroma:

``bash uv run python .context/scripts/memory_manager.py learn --file .context/skills/fix-auth-bug.md ``

4. Reflection (End of Session)

Summarize your work to keep the history clean.

bash
uv run python .fleet/context/scripts/memory_manager.py reflect

Common Pitfalls

  • Not Configuring Chroma: If config.yaml is missing or has no keys, the system falls back to local-only (no search).
  • Committing Private Data: Never force-add files in core/ or skills/ unless they are generic templates.
  • Forgetting to Learn: Solving a problem without running /learn means the next agent has to solve it again.

Related Resources

  • AGENTS.md (System Instructions)
  • .fleet/context/MEMORY.md (Architecture Docs)

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
111
Repository forks
11
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/qredence/agentic-fleet/memory-system-guide/badge)](https://verified-skill.com/skills/qredence/agentic-fleet/memory-system-guide)

Something wrong with this skill or its page? Tell us.