research-patterns | reflex | ClaudePluginHub

Skill

Community

research-patterns

0

Description

Knowledge retrieval and research patterns using Qdrant for stored knowledge

AI Summary

Automatically queries Qdrant vector database for stored knowledge before external research, then stores valuable new findings with source metadata for future retrieval.

Install

1

Add the repository(one-time)

$

/plugin marketplace add mindmorass/reflex

2

Install the plugin

$

/plugin install reflex@mindmorass-reflex

Tool Access

This skill inherits all available tools. When active, it can use any tool Claude has access to.

Skill Content

Research Patterns

Patterns for finding and synthesizing information, with Qdrant-first retrieval.

Workflow

1. Check Stored Knowledge First

Before external research, query Qdrant:

Tool: qdrant-find
Query: "your search query"

If relevant results exist, use them and cite the source metadata.

2. External Research If Needed

If stored knowledge is insufficient or outdated:

Search official documentation
Use WebSearch for current information
Cross-reference multiple sources

3. Store Valuable Findings

For information worth persisting, use qdrant-store:

Tool: qdrant-store
Information: "<content>"
Metadata:
  source: "<URL>"
  type: "documentation"
  harvested_at: "<ISO date>"

Research Checklist

Query Qdrant - Always check stored knowledge first
Assess freshness - Check harvested_at metadata
Define gaps - What's missing or outdated?
Search externally - Find additional sources if needed
Evaluate - Assess source quality and relevance
Synthesize - Combine into coherent answer
Cite - Reference sources including Qdrant metadata
Store - Save valuable new findings to Qdrant

Best Practices

Note data freshness in responses
Cross-reference multiple sources
Distinguish cached vs fresh information
Keep stored documents focused (one topic each)

Links

GitHub Stats

0 forks

Updated 5 days ago

Similar Skills

Agent Development

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.

54.1k

Command Development

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.

54.1k

Hook Development

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.

54.1k