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 solid skill description with excellent trigger term coverage and clear 'what/when' guidance. Its main weakness is that the capability descriptions are somewhat high-level—terms like 'advanced debugging' and 'incident response' could be more concrete with specific actions (e.g., 'check webhook logs', 'trace segment event flow', 'audit liquid template errors'). Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'trace webhook delivery logs, audit liquid template rendering, check segment membership, review API call failures' instead of the general 'advanced debugging and incident response'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Customer.io) and some actions (debugging, incident response, diagnosing delivery issues, investigating campaign failures, running incident playbooks), but the actions are somewhat general and could be more concrete—e.g., specifying what debugging steps, what logs to check, or what specific outputs are produced. | 2 / 3 |
Completeness | Clearly answers both 'what' (advanced debugging and incident response for Customer.io) and 'when' (diagnosing complex delivery issues, investigating campaign failures, running incident playbooks) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Includes an explicit list of natural trigger phrases like 'debug customer.io', 'customer.io troubleshoot', 'customer.io not delivering', and 'customer.io incident', which closely match what users would naturally say. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform (Customer.io) and the focus on advanced debugging/incident response. The explicit trigger terms further reduce conflict risk 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 executable code, clear incident runbooks, and systematic investigation workflows. Its main weakness is length — the inline code blocks make it token-heavy, and some content (like the full DebugCioClient class) could be referenced rather than embedded. The troubleshooting framework and incident priority levels provide excellent structure for complex debugging scenarios.
Suggestions
Extract the DebugCioClient class and bash scripts into referenced files (e.g., 'See [lib/customerio-debug.ts](lib/customerio-debug.ts)') to reduce inline token usage while keeping the SKILL.md as an overview.
Consolidate the repetitive error-handling patterns in DebugCioClient (debugIdentify and debugTrack share ~80% of their code) into a single wrapper method to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some verbosity — the DebugCioClient class has repetitive error-handling patterns that could be DRYed up, and the console.log-heavy debug output is somewhat padded. The troubleshooting framework's five questions are useful but border on generic advice Claude already knows. | 2 / 3 |
Actionability | Provides fully executable TypeScript classes, bash scripts with proper error handling (set -euo pipefail), concrete curl commands, and specific dashboard navigation paths. The code is copy-paste ready with real API endpoints and proper environment variable handling. | 3 / 3 |
Workflow Clarity | The incident response runbooks are clearly sequenced with escalation paths (P1-P4), the campaign debugging function has explicit blockers and sequential validation steps, and the investigation script provides a clear checklist. Feedback loops are present (e.g., 'If errors: fix and re-validate', 'escalate to P1 if not recovering'). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's quite long (~200+ lines of inline code) that could benefit from splitting scripts into referenced files. The 'Next Steps' reference to customerio-reliability-patterns is good, but the diagnostic scripts and debug client could be external references rather than inline. | 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
70e9fa4
- 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.