CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

90

1.60x
Quality

Does it follow best practices?

Impact

74%

1.60x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is concise, actionable, and well-organized into navigable sections. Its main weakness is workflow clarity: it reads as a command reference rather than a sequenced process, and batch operations lack validation checkpoints.

Suggestions

Turn the Commands section into a sequenced workflow (init -> embed/batch -> search) with an explicit verification step, e.g. confirming indexes were built before searching.

Add a validation checkpoint for batch operations, such as checking row counts or running a sample search after 'embeddings batch' before declaring success.

Trim marketing-style speed claims ('75x faster', '150x-12,500x faster') or move them to a notes section, since they add tokens without actionable guidance.

DimensionReasoningScore

Conciseness

The body is lean and table-driven, assumes competence, and avoids explaining concepts Claude already knows; the only softness is marketing-style speed claims ('75x faster', '150x-12,500x faster') that could be trimmed, but it does not reach the verbosity of the level-2 anchor.

3 / 3

Actionability

Concrete, copy-paste-ready commands are provided throughout (e.g. 'npx claude-flow embeddings init --backend sqlite' and 'npx claude-flow embeddings search --query ... --top-k 5'), matching the fully-executable anchor.

3 / 3

Workflow Clarity

Commands are listed as a reference rather than sequenced into a workflow, and batch operations ('embeddings batch') and search have no validation or verification checkpoints, which caps workflow clarity at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is under 50 lines with clear sections (Purpose, Features, Commands, Memory Integration, Best Practices), qualifying for the simple-skill exception where well-organized sections score 3 without external references.

3 / 3

Total

11

/

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 strong: it states concrete capabilities, provides natural trigger terms, answers both what and when, and carves out a distinct niche with skip guidance. Minor over-claim buzzwords ('75x faster') do not undermine the structural quality.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ('HNSW indexing, sql.js persistence, and hyperbolic support' plus 'semantic search, pattern matching, similarity queries, knowledge retrieval') rather than vague language, matching the highest anchor.

3 / 3

Completeness

Explicitly answers both what ('Vector embeddings with HNSW indexing...') and when ('Use when: semantic search...'), plus a 'Skip when' clause, matching the both-answered anchor.

3 / 3

Trigger Term Quality

Trigger terms like 'semantic search', 'pattern matching', 'similarity queries', and 'knowledge retrieval' are natural phrases a user would actually say, giving good coverage.

3 / 3

Distinctiveness Conflict Risk

The vector-embeddings/semantic-search niche with explicit 'Use when'/'Skip when' triggers is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.