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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is exceptionally concise and well-structured with appropriate progressive disclosure to a real reference file, but the body lacks an executable worked example and a sequenced tuning workflow with validation/benchmark-checkpoint steps.

Suggestions

Add a short, sequenced 'Tuning workflow' section in the body (select index type → set HNSW params → apply quantization → benchmark on real queries → verify recall target met) with explicit validation checkpoints, since tuning is inherently multi-step.

Include at least one small inline executable snippet or concrete command in the body (e.g. a minimal hnswlib or qdrant config snippet) so the skill is actionable without first opening references/details.md.

Surface a one-line validation step in the Do's list tying benchmark results to an explicit pass/fail recall+latency threshold before declaring tuning complete.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized: tables, compact ASCII diagrams, and terse Do/Don't bullets with no padding or explanation of concepts Claude already knows, matching the 'every token earns its place' anchor.	5 / 5
Actionability	The body itself gives parameter defaults and decision tables but no executable code or commands inline — the concrete, copy-paste-ready code is deferred entirely to references/details.md, leaving the body at the 'some concrete guidance but incomplete' level.	3 / 5
Workflow Clarity	Tuning is a multi-step process (select index type, set HNSW params, choose quantization, benchmark, verify recall) but the body presents these as parallel concept sections rather than a sequenced workflow with validation checkpoints, capping it at 3.	3 / 5
Progressive Disclosure	A clear overview in SKILL.md with a single well-signaled one-level-deep reference ('references/details.md') that genuinely exists in the bundle and holds the detailed templates, matching the top anchor.	5 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with concrete domain-specific trigger phrases. It is highly specific and distinct from neighboring skills.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete tuning actions ('tuning HNSW parameters', 'selecting quantization strategies', 'scaling vector search infrastructure') with only minor coverage gaps, matching the 'lists several specific actions' anchor.	4 / 5
Completeness	Explicitly states what it does ('Optimize vector index performance for latency, recall, and memory') and when to use it via a clear 'Use when...' clause listing concrete triggers, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user-facing terms like 'HNSW parameters', 'quantization strategies', and 'vector search infrastructure'; a few common synonyms or system names (e.g. FAISS, .index) are missing, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (vector index tuning) with distinct triggers (HNSW, quantization) and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md
Commit: d6837ae

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.