azure-cosmosdb

Azure Cosmos DB partition keys, consistency levels, change feed, SDK patterns

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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 complete executable code across multiple languages, but it is a long monolithic reference that duplicates CRUD in two languages and lacks file-based progressive disclosure or a unified validation-gated workflow.

Suggestions

Split the Python SDK, indexing policy, and CLI quick-reference sections into separate reference files (e.g., references/python-sdk.md, references/indexing.md) and link them from a concise overview to improve progressive disclosure.

Collapse the dual TypeScript/Python CRUD duplication by keeping one canonical example inline and moving the alternate language to a reference file, reducing token cost.

Add an explicit retry/backoff code pattern for 429 throttling and a validation checkpoint around batch/bulk operations so database workflows include complete feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is ~700 lines with full CRUD duplicated in both TypeScript and Python; while mostly lean code rather than fluff, the dual-language duplication and inline reference material could be tightened, so it is not the lean score-3 case.	2 / 3
Actionability	It provides fully executable, copy-paste-ready TypeScript and Python code, CLI commands, and JSON indexing policies with imports and env vars, matching the score-3 anchor for concrete executable guidance.	3 / 3
Workflow Clarity	This is a reference catalog of individual patterns rather than a sequenced workflow; error handling is partial (404/412 shown) and 429 retry is only mentioned in anti-patterns without implementation, so database operations lack complete feedback loops and workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The skill is a single ~700-line monolithic file with no bundle files; sections are well-organized (avoiding score 1) but large blocks like the full Python SDK, indexing policy, and CLI reference are inline and could be split into separate reference files, so it does not reach score 3.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 Cosmos DB feature areas a user would mention, but it lacks an explicit 'when to use' trigger clause and is a topic list rather than a list of concrete actions.

Suggestions

Add a 'Use when...' clause to the description (e.g., 'Use when working with Azure Cosmos DB partition keys, consistency levels, change feed, or SDK patterns') so it explicitly states when to invoke the skill.

Reframe the topic list as concrete actions (e.g., 'Design partition keys, tune consistency levels, process change feed, implement SDK CRUD patterns') to lift specificity from 2 to 3.

Dimension	Reasoning	Score
Specificity	The description names concrete sub-domains ('partition keys, consistency levels, change feed, SDK patterns') but uses no action verbs, so it lists topics rather than concrete actions like the score-3 anchor ('Extract text and tables... fill forms, merge documents').	2 / 3
Completeness	It answers 'what' (the topics covered) but the description field contains no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	'Azure Cosmos DB' plus feature names ('partition keys', 'consistency levels', 'change feed') are exactly the natural terms a developer working with this service would say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	'Azure Cosmos DB' is a highly specific product niche with distinct triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (714 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Commit: 9dacc46

Reviewed: about 7 hours ago

Table of Contents

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.