g14wxz/pgvector-hnsw-index-selection
Enforces HNSW index selection over IVFFlat and correct distance operator usage for pgvector.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly communicates specific capabilities (pgvector HNSW index configuration, distance operator selection), includes rich trigger terms spanning both user-friendly concepts (vector search, semantic search) and technical specifics (HNSW, IVFFlat, inner product, cosine distance), and provides an explicit 'Use when' clause. It occupies a well-defined niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: configures pgvector HNSW indexes, enforces inner product operator for normalized embeddings instead of cosine distance, and references choosing between HNSW and IVFFlat index types. | 3 / 3 |
Completeness | Clearly answers both 'what' (configures pgvector HNSW indexes with correct distance operators, enforces inner product for normalized embeddings) and 'when' (explicit 'Use when' clause covering vector search setup, embedding indexes, semantic search, and index type selection). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'vector search', 'embedding indexes', 'semantic search', 'HNSW', 'IVFFlat', 'pgvector', 'cosine distance', 'inner product'. These cover both high-level concepts and specific technical terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: pgvector HNSW index configuration with specific distance operator guidance. The combination of pgvector, HNSW, IVFFlat, and embedding-specific operator choices makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, tightly-written skill that provides precise, actionable guidance for configuring pgvector HNSW indexes. It respects Claude's intelligence by jumping straight into decision criteria and executable SQL, includes strong validation checkpoints with explicit HALT conditions, and maintains a clear phased workflow. The operator selection rules are unambiguous and well-justified.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what pgvector is or how HNSW works conceptually. The operator class mapping table and SQL template are exactly what's needed without padding. | 3 / 3 |
Actionability | Provides executable SQL for index creation, specific operator class mappings, a concrete diagnostic query (`SELECT vector_norm(embedding)...`), and exact verification commands (`EXPLAIN ANALYZE`, `\di+`). Copy-paste ready with clear parameterization. | 3 / 3 |
Workflow Clarity | Four clearly sequenced phases with explicit HALT conditions (Phase 1 and Phase 4), validation checkpoints (verify index exists, confirm query plan uses index scan), and clear decision logic for operator selection. The feedback loop of checking the query plan and halting on failure is well-defined. | 3 / 3 |
Progressive Disclosure | For a focused, single-purpose skill under 50 lines, the content is well-organized into logical phases with clear headers. No need for external file references given the scope, and the structure supports easy scanning. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents