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

67%

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/AI-Agents-Safe-Coding-Skills-claude/skills/vector-index-tuning/SKILL.md

The canonical home for this skill is vector-index-tuning in rmyndharis/antigravity-skills

Quality

Content

56%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 body is well-structured and lean with a clear workflow and sensible safety guidance, but it lacks executable specificity (no code, parameters, or commands) and its single external reference is a broken path. It reads as an outline rather than an actionable guide.

Suggestions

Add concrete executable detail to the Instructions: example parameter sweeps (e.g. ef_construction/ef_search/M ranges), a benchmark command or code snippet, and the libraries/tools to use for measuring recall and latency.

Fix the broken reference: either create resources/implementation-playbook.md with the promised patterns, checklists, and templates, or remove the dangling references from both the Instructions and Resources sections (and de-duplicate the mention).

Inline the critical validation checkpoint into the workflow step where it applies (e.g. 'Validate on staging and confirm recall >= baseline before rolling out') instead of relegating it only to the separate Safety section.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept-padding and well-organized bullet/numbered lists, but the intro line restates the description and the implementation-playbook reference is duplicated in both the Instructions and Resources sections, leaving a minor trim opportunity.	4 / 5
Actionability	The instructions are high-level directives (choose an index type, benchmark parameter sweeps) with no code, commands, parameter names/values, or tool/library names, so they describe the process rather than give executable guidance.	2 / 5
Workflow Clarity	A clear 4-step sequence (gather targets, baseline, sweep, staging validate) is present with validation/revert checkpoints in the Safety section, though those checkpoints are split from the workflow and leave the recall-regression measurement somewhat implicit.	4 / 5
Progressive Disclosure	The body is well-sectioned and points one level deep to resources/implementation-playbook.md, but that referenced file does not exist on disk, so the promised detailed patterns/checklists/templates are a dead end rather than a real navigable bundle.	3 / 5
	Total	13 / 20 Passed

Description

78%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.

A strong, well-scoped description that names a clear niche, concrete metrics, and explicit 'Use when' triggers. It is just short of top marks because the capability framing is outcome-oriented rather than a comprehensive action enumeration and a few common synonyms are absent.

Dimension	Reasoning	Score
Specificity	Lists several concrete action areas (tuning HNSW parameters, selecting quantization strategies, scaling vector search) tied to concrete metrics (latency, recall, memory), with only minor coverage gaps versus the comprehensive 5 anchor.	4 / 5
Completeness	Both what (optimize vector index performance for latency, recall, memory) and when (explicit 'Use when' clause with concrete triggers) are present, but the 'what' is outcome-framed rather than a crisp enumeration of actions, just below the 5 anchor.	4 / 5
Trigger Term Quality	Natural domain terms a user would say (HNSW parameters, quantization, vector search, latency, recall) are present with good coverage, though a few common synonyms (e.g. ANN, approximate nearest neighbor) are missing.	4 / 5
Distinctiveness Conflict Risk	The vector index / HNSW / quantization niche is clearly distinct with specific triggers and minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/vector-index-tuning/SKILL.md
Commit: 57c135b

Reviewed: 7 days 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.