CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-cosmos-db-py

Build production-grade Azure Cosmos DB NoSQL services following clean code, security best practices, and TDD principles.

46

Quality

48%

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 ./skills/azure-cosmos-db-py/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%Scale 1-5

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

This is a solid, well-structured skill that provides concrete patterns for Cosmos DB service implementation with good progressive disclosure to reference files. Its main weaknesses are the lack of validation checkpoints in the workflow (important for database operations), some verbosity in sections like NFRs and the architecture diagram that don't add actionable value, and a few minor code inconsistencies.

Suggestions

Add explicit validation/verification steps to the Quick Start workflow, e.g., 'Verify connection: run `python -c "from db.cosmos import get_container; ..."` and confirm no errors' after client setup.

Remove or significantly trim the 'Quality Attributes (NFRs)' section—these are design principles Claude already understands and they don't provide actionable guidance.

Fix the sync/async mismatch in the service layer example where `_use_cosmos` calls `get_container()` synchronously but `get_container` is defined as async.

Replace the 'When to Use' section with something meaningful or remove it entirely—the current tautological sentence adds no value.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary sections like the ASCII architecture diagram, the 'Quality Attributes (NFRs)' section which largely restates things Claude already knows (retry logic, connection pooling, dependency injection benefits), and the final 'When to Use' sentence is a meaningless tautology. The core code examples and patterns are reasonably efficient, but there's noticeable padding.

3 / 5

Actionability

Provides concrete, executable code for client setup, model hierarchy, service layer, and testing patterns. The code examples are copy-paste ready with realistic patterns. Minor gaps exist—the `get_document` helper and `settings` object are referenced but not defined inline, and the service layer example's `_use_cosmos` method has a sync/async mismatch (calls async `get_container()` without await).

4 / 5

Workflow Clarity

The Quick Start provides a numbered sequence (client → models → service), but there are no validation checkpoints. For a skill involving database operations and document manipulation, there's no explicit verify/validate step after setup, no error recovery flow, and no feedback loop for common failures like connection issues or misconfigured partition keys.

3 / 5

Progressive Disclosure

Good structure with clear overview content inline and well-organized reference tables pointing to deeper files (references/client-setup.md, references/service-layer.md, etc.) plus template assets. References are one level deep and clearly signaled. However, since no bundle files were provided, we cannot verify the referenced files exist, and the inline content is somewhat long—some sections like NFRs could be moved to a reference file.

4 / 5

Total

14

/

20

Passed

Description

36%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 identifies a specific technology (Azure Cosmos DB NoSQL) but relies on vague, aspirational language ('production-grade', 'clean code', 'best practices') rather than concrete actions. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others. The buzzword-heavy phrasing adds little discriminative value.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Cosmos DB', 'CosmosDB', 'document database', 'NoSQL queries', 'partition key', or 'Azure database'.

Replace vague qualifiers ('production-grade', 'clean code', 'best practices') with concrete actions such as 'configure partition keys, write SQL queries, set up indexing policies, implement change feed processors, manage throughput/RUs'.

Include file extensions or SDK references users might mention, such as '.NET SDK', 'Python SDK', or 'connection string' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (Azure Cosmos DB NoSQL) but the actions are vague and generic — 'build production-grade services' and 'following clean code, security best practices, and TDD principles' are abstract qualities rather than concrete actions like 'configure partitioning, write queries, set up indexing policies.'

2 / 5

Completeness

Has a vague 'what' (build Cosmos DB NoSQL services) but completely lacks a 'when' clause. There is no explicit guidance on when Claude should select this skill, which per the rubric should cap completeness at 3, and the weak 'what' brings it down to 2.

2 / 5

Trigger Term Quality

Includes relevant keywords like 'Azure Cosmos DB', 'NoSQL', and 'TDD', which users might naturally mention. However, it misses common variations and synonyms such as 'CosmosDB', 'document database', 'partition key', 'RU', 'container', or SDK-specific terms users would say.

3 / 5

Distinctiveness Conflict Risk

The mention of 'Azure Cosmos DB NoSQL' provides some specificity, but the broad framing around 'clean code, security best practices, and TDD principles' could overlap with any Azure service skill or general coding best practices skill.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

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.