customerio-common-errors
Diagnose and fix Customer.io common errors. Use when troubleshooting API errors, delivery failures, campaign issues, or SDK exceptions. Trigger: "customer.io error", "customer.io not working", "debug customer.io", "customer.io 401", "customer.io 429".
80
77%
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-common-errors/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 and completeness. It clearly identifies the platform (Customer.io), provides explicit 'Use when' guidance, and includes specific trigger phrases. The main weakness is that the capability description could be more specific about what concrete diagnostic or fix actions the skill performs beyond the general 'diagnose and fix'.
Suggestions
Add more specific concrete actions beyond 'diagnose and fix', such as 'check API key configuration, resolve rate limiting (429), debug webhook delivery, troubleshoot segment filtering, and fix SDK initialization errors'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Customer.io) and mentions categories of issues (API errors, delivery failures, campaign issues, SDK exceptions), but doesn't list specific concrete actions like 'check API key validity', 'inspect webhook logs', or 'resolve rate limiting'. The actions are 'diagnose and fix' which are somewhat generic. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix Customer.io common errors) and 'when' (explicit 'Use when' clause with trigger scenarios, plus a dedicated 'Trigger' section with specific phrases). Both components are explicitly stated. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including specific error codes ('customer.io 401', 'customer.io 429'), common user phrases ('not working', 'debug'), and domain-specific terms ('API errors', 'delivery failures', 'campaign issues', 'SDK exceptions'). These closely match what users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform focus on Customer.io. The trigger terms are platform-specific and unlikely to conflict with other skills unless there's another Customer.io skill. The combination of the platform name with error-specific terms creates a clear niche. | 3 / 3 |
Total | 11 / 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, highly actionable troubleshooting guide with excellent concrete code examples showing both wrong and correct patterns. Its main weaknesses are the lack of an overarching diagnostic workflow (no 'start here' triage flow) and the length — some content could be offloaded to supplementary files. Adding verification steps after each fix would strengthen the workflow clarity.
Suggestions
Add a triage flowchart or decision tree at the top: 'Getting a status code? → See HTTP table. Events not firing? → See Error 3. User not receiving email? → See Error 7.' This gives an overarching diagnostic workflow.
Add explicit verification steps after each fix (e.g., 'After fixing credentials, run the diagnostic curl command from the Diagnostic Commands section to confirm 200 response').
Consider splitting the detailed per-error code examples into a separate ERRORS_REFERENCE.md, keeping SKILL.md as a concise lookup with one-line fixes and links to details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code examples, but includes some unnecessary content like the Prerequisites section (Claude knows it needs API credentials), the 200 status code row, and some comments that over-explain. The 'Overview' section restates what the skill title already conveys. | 2 / 3 |
Actionability | Excellent actionable content throughout — executable TypeScript code examples with clear WRONG/CORRECT patterns, copy-paste ready curl commands for diagnostics, a complete backoff implementation, and specific checklists for non-code debugging steps. | 3 / 3 |
Workflow Clarity | Each error is well-structured with clear fix steps, and the diagnostic checklists are helpful. However, there's no overarching diagnostic workflow (e.g., 'start here, then check X, then Y') and no explicit validation/verification steps after applying fixes — the user is told what to fix but not how to confirm the fix worked. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and a reference table, and links to external docs are provided. However, at ~150 lines this is getting long for a SKILL.md — the detailed code examples for each error could be split into a separate reference file, with the main skill providing a concise lookup table pointing to detailed fixes. | 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 | |
- Commit
3e83543
- 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.