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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

70%

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

The body is highly actionable with complete, executable code and useful summary tables, but it is verbose and monolithic, keeping detailed implementations inline instead of progressively disclosing them into the existing reference file, and it omits validation checkpoints for its batch operations.

Suggestions

Move the full code implementations into references/implementation-guide.md and link to it from the body, keeping only minimal signature/example snippets in SKILL.md to improve progressive disclosure and conciseness.

Add explicit validation/feedback steps for the batching pattern (e.g., log rejected events from Promise.allSettled, retry failed events) and the singleton teardown to lift workflow clarity.

Tighten the retry and batch sections by removing redundant usage wrappers and consolidating env-var wiring into a single shared setup note.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code per pattern and minimal concept explanation, but four full inline code blocks plus repeated usage snippets and env-var wiring add length that could be trimmed or pushed to the reference file.	2 / 3
Actionability	Provides complete, copy-paste-ready TypeScript implementations for each pattern with concrete types, parameters, and usage examples rather than pseudocode.	3 / 3
Workflow Clarity	Patterns are clearly grouped and a decision table and error-handling table aid selection, but batch/destructive operations (the flush queue, singleton teardown) lack explicit validation checkpoints and feedback loops, capping clarity at 2.	2 / 3
Progressive Disclosure	The body is largely monolithic with all four full implementations inline; a references/implementation-guide.md exists but is not linked or signaled from the body, so content that could be split out remains undivided.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, concise, and clearly signals both capability and trigger conditions using third-person voice. It names concrete actions and natural trigger phrases with strong distinctiveness.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions: 'implementing typed clients, retry logic, event batching, or singleton management', directly mapping to four distinct production patterns.	3 / 3
Completeness	Explicitly states what it does ('Apply production-ready Customer.io SDK patterns') and when to use it via a 'Use when' clause plus a dedicated 'Trigger:' list, satisfying both requirements.	3 / 3
Trigger Term Quality	Includes natural phrases a user would say such as 'customer.io best practices', 'customer.io patterns', 'production customer.io', and 'customer.io singleton', covering common variations.	3 / 3
Distinctiveness Conflict Risk	The customerio-node / SDK-patterns niche is specific and distinct, with trigger terms unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 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
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
Commit: 02d6341

Reviewed: 3 days 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.