CtrlK
BlogDocsLog inGet started
Tessl Logo

customerio-sdk-patterns

Apply production-ready Customer.io SDK patterns. Use when implementing typed clients, retry logic, event batching, or singleton management for customerio-node. Trigger: "customer.io best practices", "customer.io patterns", "production customer.io", "customer.io architecture", "customer.io singleton".

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-3

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

A strong, actionable patterns catalog with executable code and concise prose, weakened by a monolithic structure that fails to leverage its reference file and by missing validation/feedback in the batch flush workflow.

Suggestions

Add a validation/feedback step to the batch flush (e.g., inspect Promise.allSettled rejections, log or retry failures) so the batch workflow includes an explicit checkpoint.

Move detailed pattern implementations to references/implementation-guide.md and have the body reference it (e.g., 'Full implementation: [implementation-guide.md](references/implementation-guide.md)'), keeping only the overview and one quick-start example inline to avoid duplication.

Reduce duplication between the body and the reference guide so the two files are clearly one level deep rather than restating the same patterns.

DimensionReasoningScore

Conciseness

The body is code-first and lean: minimal framing prose (brief Overview/Prerequisites) with four complete TypeScript blocks and two compact tables, avoiding explanation of concepts Claude already knows.

3 / 3

Actionability

All four patterns provide complete, executable TypeScript with real imports, constructor usage, and concrete usage examples — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Patterns are sequenced with a helpful Pattern Summary table, but batch operations (Pattern 3 flush) discard Promise.allSettled results with no validation/checkpoint and no feedback loop for failures, capping this dimension per the batch-operations guideline.

2 / 3

Progressive Disclosure

The body is near-monolithic (~300 lines inline) and never signals the existing references/implementation-guide.md, which itself duplicates much of the body — content that should be offloaded is inline and the one reference is not clearly navigated to.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, well-structured description that clearly answers what and when, with explicit trigger phrases and concrete capability listing. It uses an imperative command voice rather than first/second person, incurring no voice penalty.

DimensionReasoningScore

Specificity

The description names multiple concrete actions — "typed clients, retry logic, event batching, or singleton management" — matching the rubric's top anchor of listing several specific actions.

3 / 3

Completeness

It states both what it does ("Apply production-ready Customer.io SDK patterns") and when to use it ("Use when implementing typed clients, retry logic..."), with explicit trigger guidance — the top anchor.

3 / 3

Trigger Term Quality

It provides good natural-phrase coverage via the explicit Trigger clause ("customer.io best practices", "customer.io patterns", "production customer.io", "customer.io architecture", "customer.io singleton"), terms a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

The Customer.io SDK niche is narrow and the triggers are domain-specific, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-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.