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, explicit trigger conditions via a 'Use when...' clause, and uses domain-specific terminology that makes it highly distinguishable from other skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'optimize vector index performance', 'tuning HNSW parameters', 'selecting quantization strategies', 'scaling vector search infrastructure'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize vector index performance for latency, recall, and memory) and 'when' (Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords that a user working in this domain would use: 'vector index', 'latency', 'recall', 'memory', 'HNSW parameters', 'quantization', 'vector search'. These are the terms practitioners naturally use when seeking this kind of help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focusing specifically on vector index optimization with domain-specific triggers like 'HNSW', 'quantization strategies', and 'vector search infrastructure' that are 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 reference tables (index selection, HNSW parameters, quantization types) and executable code, but is severely bloated with implementation details Claude could generate from concise specifications. The lack of a connecting workflow between the templates and the monolithic structure significantly reduce its effectiveness as a skill file.
Suggestions
Reduce the body to the decision tables, parameter recommendations, and brief code snippets; move full template implementations to separate bundle files (e.g., templates/hnsw_benchmark.py, templates/quantization.py)
Add an explicit tuning workflow: 1. Profile current performance → 2. Identify bottleneck (latency/recall/memory) → 3. Select strategy from decision table → 4. Apply template → 5. Benchmark and validate improvement → 6. Iterate if targets not met
Remove boilerplate code that Claude can generate (e.g., the full VectorQuantizer class, VectorSearchMonitor class) and replace with concise specifications of what to build and key parameter values
Add validation checkpoints such as 'verify recall meets target before deploying' and 'compare memory usage against budget before scaling'
| 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 class, and Qdrant configuration are all 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 monitoring. The recommend_hnsw_params function and Qdrant configuration templates provide copy-paste ready solutions. | 3 / 3 |
Workflow Clarity | While individual templates are clear, there's no overarching workflow connecting them (e.g., 'first benchmark → then select parameters → then configure → then monitor'). There are no validation checkpoints or feedback loops for tuning iterations — the skill presents tools but not a sequenced process for using them together. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code with no references to external files. The four large templates (HNSW tuning, quantization, Qdrant config, monitoring) should each be in separate referenced files, with SKILL.md containing only the decision tables and a brief overview. No bundle files exist to offload this content. | 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
34632bc
- 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.