testland/vector-search-recall-tests
Use when HNSW or IVF parameters are being tuned, an embedding model is swapped, or vector search recall was never measured. Builds brute-force ground truth, measures recall@k against latency and detects embedding drift for Qdrant, Weaviate, pgvector, Pinecone, Elasticsearch k-NN and Milvus.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The referenced GitHub repository is cloned and run as setup/runtime operational guidance to fetch code and benchmarks, representing a common/reputable unofficial operational dependency.
Where we found it
erikbern/ann-benchmarks
dependency · 1 site
The plugin instructs the user to clone and run the erikbern/ann-benchmarks GitHub repository as part of Step 6 for cross-engine baseline testing, making it an unverifiable external runtime dependency.
references/ann-benchmarks.md
10
git clone https://github.com/erikbern/ann-benchmarks.git
- Audited
- Security analysis