Semantic similarity computation for content relationships and intelligent discovery
Computes semantic relationships between documents to enable intelligent content discovery and recommendations.
npx claudepluginhub a5c-ai/babysitterThis skill is limited to using the following tools:
The Semantic Similarity skill provides advanced capabilities for computing and leveraging semantic relationships between content in knowledge management systems. Using modern embedding models and vector similarity techniques, this skill enables intelligent content discovery, recommendation, and organization beyond traditional keyword matching.
This skill integrates with:
task: Generate embeddings for knowledge base content
skill: semantic-similarity
parameters:
source: knowledge-base
model: text-embedding-3-small
batch_size: 100
output: vector-store
dimensions: 1536
task: Set up semantic similarity search
skill: semantic-similarity
parameters:
vector_store: pinecone
index_name: kb-embeddings
similarity_metric: cosine
top_k: 10
hybrid_search: true
keyword_weight: 0.3
task: Identify duplicate content
skill: semantic-similarity
parameters:
threshold: 0.92
scope: all-documents
output: duplicate-report.json
action: flag_for_review
task: Generate topic model for knowledge base
skill: semantic-similarity
parameters:
method: bertopic
min_topic_size: 10
nr_topics: auto
output: topic-model
visualizations: true
Document -> Chunking -> Embedding -> Vector Store -> Query -> Results
Query -> [Keyword Search] -> Results
-> [Semantic Search] -> Results
-> [Reranking] -> Final Results
User Context -> Find Similar Content -> Filter by Metadata -> Personalize -> Recommend
Key metrics for semantic similarity systems:
| Metric | Description | Target |
|---|---|---|
| Retrieval Precision | Relevant results in top-k | > 80% |
| Search Latency | Time for similarity search | < 200ms |
| Duplicate Detection F1 | Accuracy of duplicate finding | > 90% |
| Topic Coherence | Quality of topic models | > 0.5 |
| User Satisfaction | Relevance ratings | > 4.0/5.0 |
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
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.