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

86%

Does it follow best practices?

Impact

74%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

72%

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 highly actionable with concrete executable commands, but it pads token budget with marketing speed claims and omits validation checkpoints for its batch operation. Adding a verification step and trimming the speed figures would lift the two score-2 dimensions.

Suggestions

Add an explicit validation/verification step after batch embedding (e.g., confirm row count or run a sample search) to raise workflow_clarity to 3.

Remove or relocate the marketing-style speed claims ('75x faster', '150x-12,500x faster') to tighten conciseness and avoid unsupported over-claims.

Provide a brief end-to-end usage sequence (init -> embed -> search) so the discrete commands form a clear ordered workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with terse command blocks and tables, but repeated speed-marketing figures ('75x faster', '150x-12,500x faster') are unnecessary filler that could be tightened, landing at score-2 rather than a clean 3.	2 / 3
Actionability	Commands like 'npx claude-flow embeddings search --query "..." --top-k 5' are fully executable, specific, and copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Commands are individually clear but lack a sequenced end-to-end workflow, and the batch 'embeddings batch --file' operation has no validation/verification checkpoint, which caps this at 2 per the rubric guideline.	2 / 3
Progressive Disclosure	A single self-contained file (~60 lines) with well-organized sections and no nested references qualifies for score-3 under the guideline allowing it for short, single-purpose skills.	3 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, uses third-person voice, and provides explicit Use/Skip triggers covering both what the skill does and when to invoke it. Its only weakness is marketing-flavored speed claims ('75x faster') that verge on over-claiming without context.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities ('HNSW indexing, sql.js persistence, and hyperbolic support'), matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2.	3 / 3
Completeness	Explicitly answers both what (embeddings with HNSW/sql.js/hyperbolic) and when via 'Use when:'/'Skip when:' triggers, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	'semantic search, pattern matching, similarity queries, knowledge retrieval' are natural terms a user would say, giving good coverage above the score-2 'some relevant keywords' bar.	3 / 3
Distinctiveness Conflict Risk	A clear vector-embeddings niche with distinct semantic-search triggers makes it unlikely to fire for unrelated skills; the '75x faster' over-claim does not raise conflict risk.	3 / 3
	Total	12 / 12 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/claude-flow
Path: .agents/skills/embeddings/SKILL.md
Commit: 26c35b5

Reviewed: about 4 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.