Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

embeddings

Vector embeddings configuration and semantic search

Quality

65%

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 ./src/skills/bundled/embeddings/SKILL.md

Quality

Content

65%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 a well-organized, actionable reference with lean code examples, but it functions as an inlined catalog rather than a progressive-disclosure overview and lacks validation checkpoints for its batch and cache-clearing operations.

Suggestions

Move the bulk API reference, provider/model tables, and use-case recipes into separate reference files (e.g., REFERENCE.md, PROVIDERS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Add explicit validation/verification steps around batch (embedBatch, storeBatch) and destructive cache operations (e.g., confirm collection before clearCache, verify storeBatch returned expected count).

Trim duplicated provider/model tables and inline comments to tighten token efficiency and push conciseness toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient reference material that avoids explaining what embeddings are, with only minor instances (e.g., repeated provider/model tables and some verbose comments) that could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	It provides concrete, copy-pasteable TypeScript examples and chat commands covering common cases, but a few methods (e.g., findSimilar) are shown without full self-contained context, keeping it just below fully copy-paste ready.	4 / 5
Workflow Clarity	Content is organized as a reference catalog rather than a sequenced workflow, and operations involving batch processing (embedBatch, storeBatch) and cache clearing (clearCache) lack any validation or verification checkpoints, so per the rubric workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	Sections are clearly headed, but the full API reference, provider table, and model tables are all inlined in one 245-line SKILL.md with no separate reference files and no bundle files provided, fitting the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	14 / 20 Passed

Description

50%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 clear and on-domain but generic: it states what the skill does without any explicit trigger guidance or natural synonyms. Adding a 'Use when...' clause and richer trigger terms would move it from adequate to strong.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when configuring embedding providers, building semantic search, or comparing text similarity').

Broaden trigger terms with synonyms and concrete artifacts users mention ('embeddings', 'vector search', 'semantic similarity', 'text-embedding models').

List a couple more concrete actions (e.g., 'store and query vectors', 'cache embeddings') to raise specificity beyond the 1-2 action minimum.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Vector embeddings') and two concrete actions ('configuration' and 'semantic search'), matching the anchor for naming a domain with 1-2 concrete actions but lacking comprehensive coverage.	3 / 5
Completeness	It states a clear 'what' (configuration and semantic search) but provides no 'when' / 'Use when' trigger clause, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords ('vector embeddings', 'semantic search') but misses common variations, synonyms, or file/extension terms users might naturally say, matching the anchor for partial keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The embeddings/semantic-search niche is somewhat specific but could still overlap with general search or vector-DB skills, fitting the 'somewhat specific but could overlap' anchor better than the more-distinct anchor above.	3 / 5
	Total	12 / 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: alsk1992/CloddsBot
Path: src/skills/bundled/embeddings/SKILL.md
Revision: c930628

Reviewed: 1 month ago

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.

embeddings

Table of Contents

Is this your skill?