CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-eventhub-ts

High-throughput event streaming and real-time data ingestion.

44

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-eventhub-ts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 reference-style skill for Azure Event Hubs with good executable code examples covering the main use cases. Its main weaknesses are the lack of validation/verification steps in workflows (especially around checkpointing and batch operations), some unnecessary sections (Key Types, tautological 'When to Use'), and a monolithic structure that would benefit from splitting advanced topics into separate files.

Suggestions

Add validation checkpoints: verify batch.tryAdd() return value, confirm events were sent successfully, and add a step to verify checkpoint state after processing.

Remove the 'Key Types' import listing and the 'When to Use' section — both waste tokens without adding actionable value.

Split advanced topics (checkpointing setup, error handling patterns, partition management) into separate referenced files to improve progressive disclosure.

Check the tryAdd() boolean return value in batch sending examples and show how to handle a full batch (create new batch and retry).

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but includes some unnecessary verbosity. The 'Key Types' section is just a list of imports Claude already knows how to find. The 'When to Use' section is a meaningless tautology. The best practices list includes some obvious advice (e.g., 'Close clients'). However, most code examples are lean and purposeful.

3 / 5

Actionability

The skill provides concrete, executable TypeScript code for all major operations (send, receive, checkpoint, error handling). Code examples are copy-paste ready with realistic payloads. Minor gap: `tryAdd` return value (boolean) is never checked, which could silently drop events when batches are full — a practical gap for production use.

4 / 5

Workflow Clarity

The skill presents a clear progression from sending to receiving to checkpointing, but lacks explicit validation steps. For a streaming/data ingestion skill involving batch operations and checkpointing, there are no verification steps (e.g., confirming events were sent, verifying checkpoint state, validating consumer group assignment). The error handling section shows a retry pattern but no explicit feedback loop for recovery.

3 / 5

Progressive Disclosure

The content is well-sectioned with clear headers, but it's a long monolithic file (~200 lines of code examples) with no references to external files. Advanced topics like checkpointing, partition management, and error handling patterns could be split into separate files. For a skill of this size, the lack of any bundle files or cross-references is a missed opportunity.

3 / 5

Total

13

/

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.

This description is too terse and abstract, reading more like a marketing tagline than a functional skill description. It lacks concrete actions, specific technologies, and any 'when to use' guidance, making it difficult for Claude to reliably select this skill from a pool of related data-processing skills.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user mentions Kafka, event streams, message queues, pub/sub, or real-time data pipelines.'

List specific concrete actions such as 'Configure Kafka topics, produce and consume messages, set up stream processors, monitor consumer lag, design event schemas.'

Include natural synonyms and technology names users would mention, such as 'Kafka', 'Pulsar', 'Kinesis', 'message broker', 'pub/sub', 'stream processing', '.avro', '.parquet'.

DimensionReasoningScore

Specificity

Names the domain (event streaming, data ingestion) but provides no concrete actions. 'High-throughput' and 'real-time' are descriptive adjectives rather than specific capabilities like 'configure topics', 'produce/consume messages', or 'set up pipelines'.

2 / 5

Completeness

Provides only a vague 'what' (event streaming and data ingestion) with no 'when' clause at all. 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 to 2.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'event streaming' and 'data ingestion' that users might use, but misses common natural terms like 'Kafka', 'message queue', 'pub/sub', 'stream processing', 'consumer groups', or specific technology names users would mention.

3 / 5

Distinctiveness Conflict Risk

Somewhat specific to the streaming/ingestion domain, but 'real-time data' and 'event streaming' could overlap with skills related to data pipelines, message queues, ETL, or general data processing. Without naming specific technologies or use cases, overlap risk remains moderate.

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.