CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-search-documents-ts

Build search applications with vector, hybrid, and semantic search capabilities.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-search-documents-ts/SKILL.md

The canonical home for this skill is azure-search-documents-ts in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

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 an actionable, code-dense tutorial that covers the core Azure AI Search workflows, but it lacks validation/verification steps for batch operations and keeps all reference material inline rather than splitting it into bundle files.

Suggestions

Add validation/verification for batch and index operations — check result.results for failures and retry or report errors — to satisfy the workflow_clarity cap.

Move the bulk type/API reference and the semantic/autocomplete details into reference bundle files (e.g. references/types.md, references/advanced.md) and link to them from the body.

Tighten or remove the filler 'When to Use' line and de-duplicate repeated import boilerplate to improve conciseness.

DimensionReasoningScore

Conciseness

A code-first tutorial with minimal prose and no over-explanation of basic concepts, but repeated import boilerplate and a filler 'When to Use' line ('applicable to execute the workflow or actions described in the overview') keep it just below lean.

4 / 5

Actionability

Concrete, copy-paste-ready TypeScript covering auth, index creation, indexing, and full-text/vector/hybrid/semantic search, with only minor gaps such as the placeholder getEmbedding() function and templated env values.

4 / 5

Workflow Clarity

Sections are logically sequenced (install → env → auth → index → query variants), but batch and index operations include no validation or result-failure verification, so the rubric's batch/destructive cap holds this at 3.

3 / 5

Progressive Disclosure

No bundle files exist and all content (full type reference, semantic config, autocomplete, batch) is inlined in a single 270-line file with section headers; structure is present but content that belongs in separate references is not split out.

3 / 5

Total

14

/

20

Passed

Description

66%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 clearly states what the skill does and names specific search capability types, but it omits any "Use when..." trigger guidance, which caps its completeness and limits distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when building Azure AI Search applications, or when the user mentions vector, hybrid, or semantic search in TypeScript.'

Include synonyms and concrete actions (e.g. 'create indexes, upload documents, run vector/hybrid/semantic queries') to lift specificity and trigger-term coverage.

Reference the SDK or file type explicitly (e.g. '@azure/search-documents', Azure AI Search) to sharpen distinctiveness from generic search tooling.

DimensionReasoningScore

Specificity

Names the search domain plus three concrete capability categories ("vector, hybrid, and semantic search"), matching the anchor that lists several specific actions with minor gaps; not a 5 because these are capability categories rather than discrete concrete actions like create-index/upload-docs.

4 / 5

Completeness

Provides a clear "what" but no "Use when..." clause or equivalent trigger guidance, which per the rubric guideline caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural technical terms a user would say ("search", "vector", "hybrid", "semantic search") with good coverage, but lacks common synonyms or file-extension-style variants that would warrant a 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to Azure AI Search with specific capability types, making it mostly distinct with only minor overlap risk against generic search skills; not a 5 because explicit trigger phrases are absent.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.