customerio-cost-tuning

Optimize Customer.io costs and usage efficiency. Use when reducing profile count, cleaning inactive users, deduplicating events, or right-sizing your plan. Trigger: "customer.io cost", "reduce customer.io spend", "customer.io billing", "customer.io pricing", "customer.io cleanup".

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.

Highly actionable with executable code and a clear step sequence, but it is verbose for a SKILL.md and underuses progressive disclosure — the provided reference files are not signaled and inline scripts duplicate content that belongs in separate files. Destructive/batch workflows also lack explicit validation checkpoints.

Suggestions

Move the inline TypeScript scripts into actual files under scripts/ (matching the paths already named in comments) and replace the inline blocks in SKILL.md with concise overviews plus links, reducing token cost and removing the redundancy with references/implementation-guide.md.

Add an explicit validation checkpoint to the destructive cleanup workflow: review the [DRY RUN] output and confirm the target count before re-running with dryRun=false, plus a retry loop for failed suppress/destroy calls.

Link the existing bundle files (references/implementation-guide.md, references/implementation.md) from a clearly signaled section so the detailed material is discoverable one level deep instead of duplicated inline.

Dimension	Reasoning	Score
Conciseness	The body embeds ~200 lines of full TypeScript scripts inline and overlaps heavily with the bundle reference files; it is mostly useful but could be tightened by moving code into scripts/ and trimming redundant inline implementations.	2 / 3
Actionability	Steps 2–5 provide fully executable code (suppress/destroy with rate limiting, SHA-256 dedup, sampling, usage monitor) that is concrete and copy-paste ready.	3 / 3
Workflow Clarity	Steps are clearly sequenced and a dryRun flag exists, but the destructive suppress/delete and batch operations lack an explicit review-then-proceed validation checkpoint and a validate→fix→retry feedback loop, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are organized, but the existing references/ files are never linked from the body and large code blocks are inline claiming script paths (e.g. scripts/cio-profile-audit.ts) that do not exist as files.	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.

A strong, third-person description that names concrete actions, provides natural trigger phrases, and explicitly answers both what the skill does and when to use it. No significant weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reducing profile count, cleaning inactive users, deduplicating events, or right-sizing your plan' — rather than vague language.	3 / 3
Completeness	Clearly states what ('Optimize Customer.io costs and usage efficiency') and when ('Use when reducing profile count...'), with an explicit Trigger clause, so both are covered.	3 / 3
Trigger Term Quality	Explicit trigger phrases ('customer.io cost', 'reduce customer.io spend', 'customer.io billing', 'customer.io pricing', 'customer.io cleanup') are natural terms a user would say.	3 / 3
Distinctiveness Conflict Risk	A clear Customer.io cost-tuning niche with distinct cost/billing triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: about 2 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.