Store and retrieve documents using Qdrant for RAG workflows. Use for persistent memory, research storage, and semantic search.
Stores information in Qdrant vector database with automatic embeddings and metadata. Claude uses this to persist research findings, documentation snippets, and code examples for later semantic retrieval in RAG workflows.
/plugin marketplace add mindmorass/reflex/plugin install reflex@mindmorass-reflexThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Use the qdrant MCP server tools for persistent vector storage and semantic retrieval.
| Tool | Purpose |
|---|---|
qdrant-store | Store information with automatic embedding |
qdrant-find | Semantic search for stored information |
The collection name is configured via environment variable:
COLLECTION_NAME - Set to ${WORKSPACE_PROFILE:-default}_memoriesThis provides workspace isolation - each profile gets its own collection.
Store information with the qdrant-store tool:
Tool: qdrant-store
Information: "GitHub REST API uses OAuth tokens for authentication. Personal access tokens (PATs) provide scoped access to repositories, issues, and other resources. Fine-grained PATs offer more granular permissions than classic tokens."
Metadata:
source: "https://docs.github.com/rest/authentication"
type: "documentation"
harvested_at: "2025-01-04"
tags: "github,api,authentication"
Always include:
source - Original URL or file pathtype - Content type (documentation, code, article, etc.)harvested_at - ISO date of collectiontags - Comma-separated searchable keywordsOptional but useful:
project - Related project namelanguage - Programming language if codeversion - API or library versionsummary - Brief content summaryFind related content by meaning:
Tool: qdrant-find
Query: "how to authenticate with OAuth"
The tool returns the most semantically similar stored information.
Before researching, query for existing content:
Tool: qdrant-find
Query: "GitHub Actions workflow syntax"
If results are relevant and recent (check metadata), use them. Otherwise, harvest fresh content.
When gathering new information:
Tool: qdrant-store
Information: "<extracted content here>"
Metadata:
source: "<url or path>"
type: "documentation"
harvested_at: "<today's date>"
tags: "<relevant,keywords>"
When answering questions or implementing features:
qdrant-findharvested_at in resultsqdrant-storeThis 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 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 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.