vector-index-tuning
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
77
71%
Does it follow best practices?
Impact
84%
1.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/llm-application-dev/skills/vector-index-tuning/SKILL.mdQuality
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 defines a specific technical niche. It provides concrete actions, includes natural trigger terms that practitioners would use, and has an explicit 'Use when' clause with well-defined scenarios. The description is concise, uses third person voice, and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: optimizing vector index performance across three dimensions (latency, recall, memory), tuning HNSW parameters, selecting quantization strategies, and scaling vector search infrastructure. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize vector index performance for latency, recall, and memory) and 'when' (explicit 'Use when' clause covering tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'vector index', 'HNSW', 'quantization', 'vector search', 'latency', 'recall', 'memory'. These are terms practitioners naturally use when dealing with vector search optimization. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting vector index optimization specifically. Terms like 'HNSW parameters', 'quantization strategies', and 'vector search infrastructure' are very specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides genuinely useful, executable code for vector index tuning across multiple libraries and strategies. However, it is far too verbose for a SKILL.md—most of the code templates are standard patterns Claude could generate from concise specifications. The content would benefit enormously from extracting templates to separate files and replacing them with a concise decision framework and clear tuning workflow with validation steps.
Suggestions
Extract the four code templates into separate files (e.g., templates/hnsw_benchmark.py, templates/quantization.py) and replace them in SKILL.md with brief descriptions and links.
Add an explicit tuning workflow with validation checkpoints: 1) Profile current performance → 2) Select index type from decision table → 3) Benchmark parameter combinations → 4) Validate recall meets target → 5) Deploy and monitor.
Reduce the reference tables and best practices to the core content (~50-80 lines total) since Claude can generate standard benchmarking and quantization code from brief specifications.
Add a validation step that explicitly checks recall against a threshold before recommending deployment of any configuration change.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with massive code templates that Claude could generate on its own. The quantization class, monitoring code, and benchmarking functions are standard patterns that don't need to be spelled out in full. The reference tables (index selection, HNSW parameters, quantization types) are valuable, but they're buried in excessive boilerplate code. | 1 / 3 |
Actionability | The code templates are fully executable with real libraries (hnswlib, qdrant_client, sklearn), include concrete parameter values, and cover the full workflow from benchmarking to production configuration. The Qdrant configuration template with preset optimization profiles is immediately usable. | 3 / 3 |
Workflow Clarity | While individual templates are clear, there's no overarching workflow connecting them (e.g., 'benchmark first, then choose quantization, then configure production'). There are no validation checkpoints—for instance, no step to verify recall meets targets before deploying a configuration, or to validate that quantization hasn't degraded quality below acceptable thresholds. | 2 / 3 |
Progressive Disclosure | Everything is inlined in a single monolithic file with no references to external files. The four large code templates should be split into separate files, with the SKILL.md providing a concise overview, the decision tables, and links to detailed templates. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (518 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
27a7ed9
- Reviewed
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.