Name: embeddings
Rating: 86.8 (1 reviews)
Author: ruvnet

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

1.60x

Quality

87%

Does it follow best practices?

Impact

74%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is embeddings in ruvnet/claude-flow

Quality

Content

87%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 concise and highly actionable with ready-to-run commands and tidy tables, and it is well-structured for a simple self-contained skill. Its main weakness is the absence of a sequenced workflow with validation checkpoints for batch operations.

Suggestions

Add a short ordered workflow (init -> embed/batch -> search) with an explicit verification step (e.g., checking index size or query results) before relying on stored embeddings.

For batch embed and memory store commands, include a validation/retry note so failures are caught and handled rather than silently persisted.

Dimension	Reasoning	Score
Conciseness	The body uses lean tables and short executable command blocks with no over-explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Provides copy-paste-ready `npx claude-flow embeddings ...` commands covering init, embed, batch, search, and memory integration, plus concrete quantization and best-practice tables.	5 / 5
Workflow Clarity	Commands are presented as independent sections rather than a sequenced workflow, and batch operations (batch embed, memory store) lack validation or verification checkpoints, which caps this score at 3 per the rubric.	3 / 5
Progressive Disclosure	A single self-contained file under ~60 lines with well-organized sections (Purpose, Features, Commands, Memory Integration, Quantization, Best Practices) and no bundle files, satisfying the simple-skill exception.	5 / 5
	Total	18 / 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.

A strong, well-structured description that clearly communicates capabilities, natural triggers, and exclusions. It is concise yet specific, with only minor gaps in action breadth and synonym/extension coverage.

Suggestions

Add a concrete action verb list (e.g., "index, search, persist, and retrieve embeddings") to push specificity toward comprehensive coverage.

Include common synonyms or file/format cues (e.g., "semantic search over text or JSON documents") to broaden natural trigger matching.

Dimension	Reasoning	Score
Specificity	Names several concrete capabilities ("HNSW indexing, sql.js persistence, and hyperbolic support", "agentic-flow integration") but stops short of listing the full action set, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states both what it does (vector embeddings with named backends/features) and when to use it via a clear "Use when:" clause plus a "Skip when:" exclusion list.	5 / 5
Trigger Term Quality	Provides natural, user-sayable triggers ("semantic search, pattern matching, similarity queries, knowledge retrieval") with good coverage, though it omits common file extensions and a few synonyms.	4 / 5
Distinctiveness Conflict Risk	The embeddings/HNSW/hyperbolic niche with its specific trigger phrasing is clearly distinct from other skills with minimal overlap risk.	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: ruvnet/ruflo
Path: .agents/skills/embeddings/SKILL.md
Commit: fa13ee4

Reviewed: about 5 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.