CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-cosmos-py

Azure Cosmos DB SDK for Python (NoSQL API). Use for document CRUD, queries, containers, and globally distributed data.

59

Quality

69%

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-cosmos-py/SKILL.md

The canonical home for this skill is azure-cosmos-py in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 content is highly actionable with copy-paste-ready code across the common Cosmos operations and is reasonably concise, but it lacks validation feedback loops around destructive database operations and advertises reference files that are not present in the bundle.

Suggestions

Add validation/verification checkpoints and a retry feedback loop for destructive and rate-limited operations (e.g., verify an item exists before delete, confirm reads after writes, retry on 429 using x-ms-retry-after-ms).

Either provide the advertised bundle files (references/partitioning.md, references/query-patterns.md, scripts/setup_cosmos_container.py) or remove the Reference Files table so navigation is not broken.

Move the deeper query-pattern and partitioning detail into the referenced files and keep SKILL.md as a lean overview to reduce inlined redundancy.

DimensionReasoningScore

Conciseness

The body is mostly executable code with brief headers and no padding about concepts Claude already knows; minor redundancy (read-all-items duplicates the basic query; two setup variants) keeps it at anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Copy-paste-ready code covers the common cases (CRUD, queries, partitioning, throughput, async, error handling), matching anchor 5; the only gap is PartitionKey being used before its import appears, but the import is shown later in the same skill.

5 / 5

Workflow Clarity

Operations are sequenced but destructive operations (delete_item) and database workflows lack validation/verification checkpoints or validate→fix→retry feedback loops, so the destructive/batch cap holds at anchor 3.

3 / 5

Progressive Disclosure

Sections are clear and a Reference Files table signals references, but the referenced files (references/partitioning.md, references/query-patterns.md, scripts/setup_cosmos_container.py) are not bundled — the directories do not exist — and detailed query/partitioning content is inlined, fitting anchor 3.

3 / 5

Total

15

/

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 is specific and distinctive, naming the exact SDK and several concrete capabilities, but its "when" guidance is a capability restatement rather than explicit trigger scenarios, capping completeness.

Suggestions

Add an explicit "Use when…" trigger clause naming scenarios, e.g. "Use when the user mentions Azure Cosmos DB, a NoSQL document database, or needs Cosmos CRUD/queries in Python."

Include natural trigger synonyms such as "Cosmos DB", "document database", and "NoSQL database" to broaden keyword coverage.

Optionally mention additional capabilities the body covers (change feed, indexing, throughput) to approach comprehensive specificity.

DimensionReasoningScore

Specificity

"document CRUD, queries, containers, and globally distributed data" lists several specific actions with minor coverage gaps, matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

A clear "what" is present ("Azure Cosmos DB SDK for Python (NoSQL API)") but "when" is only "Use for [capabilities]" restating actions rather than explicit trigger scenarios; the missing "Use when…" trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

"Azure Cosmos DB", "Python", "document CRUD", "queries", "containers", "NoSQL API" give good natural keyword coverage, though synonyms like "document database"/"NoSQL database" are missing, fitting anchor 4 not 5.

4 / 5

Distinctiveness Conflict Risk

"Azure Cosmos DB SDK for Python (NoSQL API)" names a specific, low-conflict niche, matching anchor 4; triggers are not as crisply scenario-based as the anchor 5 example.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

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.