Implement Customer.io core features: transactional messages, API-triggered broadcasts, segments, and person merge. Trigger: "customer.io segments", "customer.io transactional", "customer.io broadcast", "customer.io merge users", "customer.io send email".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly identifies the specific Customer.io features it covers and provides explicit trigger terms. It uses proper third-person voice and is concise without being vague. The only minor improvement would be slightly expanding the 'when' guidance beyond just listing trigger keywords, but the current format is effective.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: transactional messages, API-triggered broadcasts, segments, and person merge. These are clearly defined Customer.io features. | 3 / 3 |
Completeness | Clearly answers 'what' (implement Customer.io core features: transactional messages, API-triggered broadcasts, segments, person merge) and 'when' (explicit trigger terms listed). The 'Trigger:' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'customer.io segments', 'customer.io transactional', 'customer.io broadcast', 'customer.io merge users', 'customer.io send email'. These cover the main use cases with natural phrasing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Customer.io' product name and its specific features. Very unlikely to conflict with other skills unless there are multiple Customer.io skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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, actionable skill with excellent executable TypeScript examples covering six Customer.io features. Its main weaknesses are the lack of validation/verification steps for destructive operations (merge, delete, suppress) and some verbosity that could be trimmed. The content would benefit from explicit safety checkpoints and slightly tighter organization.
Suggestions
Add explicit validation steps before destructive operations (merge, delete): e.g., verify both users exist before merging, confirm user identity before deletion, and include a pattern for logging/confirming these actions.
Reduce repetitive API client instantiation by showing it once and referencing it, rather than repeating the same 3-line initialization block across multiple features.
Consider splitting the six features into a concise overview in SKILL.md with links to per-feature detail files, given the overall length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but includes some unnecessary verbosity — e.g., the overview restates what the features section already covers, comments like 'Segments in Customer.io are data-driven' explain concepts Claude already knows, and some inline comments are redundant. The multiple similar API client instantiations could be DRYer. | 2 / 3 |
Actionability | Every feature includes fully executable TypeScript code with real imports, concrete function signatures, realistic parameters, and expected response shapes. The code is copy-paste ready with clear template IDs, data structures, and API calls. | 3 / 3 |
Workflow Clarity | Each feature is presented as a standalone code block rather than a sequenced workflow. For destructive operations like merge (permanently deletes secondary) and delete, there are no validation checkpoints or confirmation steps. The error handling table helps but doesn't integrate into the workflow as explicit verification steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headings and a resources section linking to external docs, but the skill itself is quite long (~180 lines of content) with all six features inline. Features like transactional push or suppress/delete could be referenced rather than fully inlined, and the reference to 'customerio-common-errors' for next steps is good but the main body could benefit from better splitting. | 2 / 3 |
Total | 9 / 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 | |
70e9fa4
Table of Contents
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.