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".
68
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/customerio-pack/skills/customerio-cost-tuning/SKILL.mdQuality
Discovery
89%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 is a well-structured skill description with strong trigger terms, clear 'Use when' guidance, and a distinctive niche around Customer.io cost optimization. The main area for improvement is adding more specific concrete actions beyond the somewhat general terms like 'cleaning inactive users' and 'right-sizing your plan.'
Suggestions
Add more specific concrete actions, e.g., 'archive profiles inactive for 90+ days', 'consolidate duplicate event names', 'compare plan tiers based on current usage metrics' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Customer.io costs) and some actions (reducing profile count, cleaning inactive users, deduplicating events, right-sizing plan), but these are somewhat high-level and could be more concrete about specific techniques or outputs. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Customer.io costs via profile cleanup, deduplication, plan right-sizing) and 'when' (explicit 'Use when' clause plus a 'Trigger' list with specific phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'customer.io cost', 'reduce customer.io spend', 'customer.io billing', 'customer.io pricing', 'customer.io cleanup'. These are realistic phrases a user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform (Customer.io) and the cost/billing focus. Very unlikely to conflict with other skills given the narrow, well-defined niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for Customer.io cost optimization with real SDK usage, but is significantly over-verbose for what it delivers. The profile audit script is mostly decorative (prints rules rather than executing them), and the pricing explanation wastes tokens on information Claude already knows. The code would benefit from being split into referenced bundle files with the SKILL.md serving as a concise overview.
Suggestions
Remove the 'How Customer.io Pricing Works' section and inline cost table — Claude knows this, and the checklist already covers review actions. This alone saves ~20% of tokens.
Make the profile audit script actually functional by using the Customer.io App API (beta) to query segments, or clearly state it's a manual dashboard process and drop the script wrapper.
Split the five TypeScript files into actual bundle files (e.g., scripts/cio-cleanup-inactive.ts) and reference them from a concise SKILL.md overview.
Add a validation step after the cleanup operation — e.g., 'Verify profile count in dashboard decreased by expected amount before proceeding to event optimization.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose at ~200+ lines. It explains how Customer.io pricing works (Claude can look this up), includes full class definitions for a UsageMonitor that just increments counters, and the profile audit script mostly just prints strings. The cost savings estimates table and pricing explanation are filler that don't add actionable value proportional to their token cost. | 1 / 3 |
Actionability | The code is mostly executable TypeScript using the real customerio-node SDK, but key parts are incomplete — the profile audit script just prints rules rather than actually querying profiles, the cleanup script requires the user to build their own target list from a commented-out query, and there's no way to actually get the list of inactive users from Customer.io's API. The sampling and dedup utilities are functional but simple. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced logically (audit → cleanup → dedup → sampling → monitoring), and the cleanup script includes a dry-run mode which is good. However, there's no explicit validation checkpoint after deletion (e.g., verify profile count decreased), no feedback loop for the overall process, and the monthly checklist is disconnected from the scripted workflow. | 2 / 3 |
Progressive Disclosure | The content is a monolithic file with no bundle files to reference. The pricing table, cost savings estimates, and full code for five separate scripts are all inline. The event dedup library, sampling library, and usage monitor could easily be separate referenced files. The reference to 'customerio-reference-architecture' at the end is a good signal but the main content is not well-split. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.