embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
76
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 74%
↑ 1.60xAgent success when using this skill
Validation for skill structure
Evaluation results
52%
1%Developer Documentation Search System
Semantic search initialization and querying
Init command used
58%
83%
SQLite backend specified
100%
100%
Embed or batch command used
25%
0%
Search command used
91%
16%
Search uses --query flag
100%
60%
Search uses --top-k flag
0%
0%
HNSW indexing mentioned
0%
100%
Normalization mentioned
0%
0%
Correct CLI tool
77%
88%
Without context: $0.6297 · 4m 36s · 35 turns · 74 in / 6,049 out tokens
With context: $0.9970 · 5m 42s · 53 turns · 52 in / 10,606 out tokens
70%
Architecture Pattern Knowledge Store
Memory integration with embeddings
Memory store command used
100%
100%
Store uses --embed flag
0%
0%
Store uses --key flag
100%
100%
Store uses --value flag
100%
100%
Memory search command used
100%
100%
Search uses --semantic flag
0%
0%
Search uses --query flag
100%
100%
Correct CLI tool
100%
100%
Without context: $0.7674 · 5m 57s · 41 turns · 46 in / 8,670 out tokens
With context: $0.5248 · 4m 11s · 35 turns · 67 in / 5,870 out tokens
100%
83%Memory-Efficient Document Embedding Pipeline for Edge Deployment
Batch embedding with quantization
Init with sqlite backend
0%
100%
Batch command used
0%
100%
Batch uses --file flag
0%
100%
Quantization applied
46%
100%
Quantization justified
60%
100%
Hyperbolic embedding chosen
0%
100%
Search command used
0%
100%
Does not use per-item embed loop
50%
100%
Correct CLI tool
0%
100%
Without context: $0.6554 · 4m 11s · 25 turns · 1,316 in / 12,550 out tokens
With context: $0.2632 · 1m 15s · 16 turns · 262 in / 3,652 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.