customerio-advanced-troubleshooting
Apply Customer.io advanced debugging and incident response. Use when diagnosing complex delivery issues, investigating campaign failures, or running incident playbooks. Trigger: "debug customer.io", "customer.io investigation", "customer.io troubleshoot", "customer.io incident", "customer.io not delivering".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 clear 'what/when' guidance. Its main weakness is that the capability descriptions are somewhat high-level—listing specific debugging actions (e.g., checking delivery logs, analyzing bounce codes, reviewing API call failures) would make it more concrete. Overall, it effectively serves its purpose of enabling Claude to select this skill at the right time.
Suggestions
Add more specific concrete actions beyond 'diagnosing' and 'investigating', such as 'check delivery logs, analyze bounce codes, review webhook configurations, trace message routing'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Customer.io) and some actions like 'diagnosing complex delivery issues', 'investigating campaign failures', and 'running incident playbooks', but these are somewhat high-level rather than listing multiple concrete specific actions (e.g., checking webhook logs, analyzing bounce rates, reviewing segment filters). | 2 / 3 |
Completeness | Clearly answers both 'what' (advanced debugging and incident response for Customer.io) and 'when' (diagnosing delivery issues, investigating campaign failures, running incident playbooks) with explicit trigger terms listed separately. | 3 / 3 |
Trigger Term Quality | Excellent trigger term coverage with natural phrases users would actually say: 'debug customer.io', 'customer.io troubleshoot', 'customer.io not delivering', 'customer.io incident', and 'customer.io investigation'. These cover multiple natural variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform (Customer.io) combined with the specific use case (debugging/incident response). The trigger terms are all platform-specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable troubleshooting skill with excellent workflow clarity through prioritized incident runbooks and systematic diagnostic frameworks. The main weaknesses are its length — the debug client, investigation scripts, and runbooks could be split into separate files for better progressive disclosure — and some repetitive patterns in the TypeScript code that could be condensed. Overall it provides genuinely useful, executable guidance that Claude wouldn't know by default.
Suggestions
Split the incident runbooks (P1-P4), network diagnostics script, and debug client into separate referenced files to reduce the main SKILL.md size and improve progressive disclosure.
Condense the DebugCioClient class by extracting the shared error-handling/timing logic into a helper method, reducing ~15 lines of duplication.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with some redundancy — the DebugCioClient class has repetitive error-handling patterns that could be condensed, and the user investigation script includes verbose echo statements that pad the content. However, it avoids explaining basic concepts and most content is domain-specific knowledge Claude wouldn't inherently know. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript classes, bash scripts with proper shebang lines and error handling, concrete curl commands, and specific dashboard navigation paths. Code is copy-paste ready with real API endpoints and proper error handling. | 3 / 3 |
Workflow Clarity | The troubleshooting framework provides a clear 5-question diagnostic sequence, the incident runbooks are well-prioritized (P1-P4) with explicit ordered steps, and the campaign debugging flow includes validation checkpoints (e.g., 'BLOCKER: Cannot identify user. Fix auth first.'). Feedback loops are present in the incident response steps. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's quite long (~250 lines of substantive content) and could benefit from splitting the incident runbooks, network diagnostics, and debug client into separate referenced files. The reference to 'customerio-reliability-patterns' at the end is good, but the main file is monolithic. | 2 / 3 |
Total | 10 / 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.