CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/customerio-pack/skills/customerio-common-errors/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable debugging reference with strong executable examples, but it underuses its own bundle: reference files are orphaned from the body, content is duplicated across files, and the diagnostic flow lacks explicit verify-checkpoints. Tightening duplication and wiring up the references would lift the weaker dimensions.

Suggestions

Link the reference files from the body (e.g., under a '## Advanced patterns' section: 'See [implementation.md](references/implementation.md) for the error-classification map and retry wrappers') so the bundle is actually discoverable and progressive disclosure is signaled.

Remove the duplicated material between SKILL.md and the references — keep the status table and backoff/curl snippets in one place and point to the reference for the rest, reducing token cost.

Add an explicit diagnostic workflow with a verify step, e.g. '1. Reproduce with the curl probe 2. Match the HTTP code to the table 3. Apply the fix 4. Re-run the probe to confirm HTTP 200', and have the error handler surface/verify recovery instead of returning null.

DimensionReasoningScore

Conciseness

The body is lean and code-driven with no concept-explaining fluff, but the backoff function, the HTTP status table, and the curl diagnostic commands are duplicated verbatim in the reference files, so tokens are spent twice; it could be tightened by leaning on the bundle, matching anchor 2 rather than 3.

2 / 3

Actionability

Each error ships executable TypeScript, the diagnostics are concrete curl commands, and the centralized error handler is copy-paste ready, matching anchor 3 for fully executable guidance.

3 / 3

Workflow Clarity

Diagnostic checklists (Errors 3 and 7) and a 429 retry loop exist, but there is no overarching diagnose-to-fix-to-verify sequence with explicit validation checkpoints, and the main handler swallows failures with `return null` instead of verifying recovery, matching anchor 2 rather than 3.

2 / 3

Progressive Disclosure

The body is well-sectioned rather than a wall of text, but the two local reference files (implementation-guide.md, implementation.md) are never linked from the body and overlapping content is inline; references are present but not signaled, matching anchor 2 and not 1 (good organization) or 3 (references would be clearly signaled).

2 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that clearly states what the skill does, when to use it, and includes explicit, natural trigger terms with product-specific error codes. The only weakness is that the named actions ("diagnose and fix") are generic verbs rather than a richer set of concrete capabilities.

DimensionReasoningScore

Specificity

"Diagnose and fix" are only two fairly generic verbs and the listed items ("API errors, delivery failures, campaign issues, SDK exceptions") are problem categories rather than concrete actions, matching anchor 2; it does not reach anchor 3's bar of multiple specific concrete actions.

2 / 3

Completeness

"Diagnose and fix Customer.io common errors" states what, "Use when troubleshooting..." states when, and an explicit Trigger clause provides triggers, clearly answering both what and when as in anchor 3.

3 / 3

Trigger Term Quality

The explicit Trigger clause lists natural phrases a user would say ("customer.io not working", "debug customer.io", "customer.io 401", "customer.io 429"), giving good coverage matching anchor 3.

3 / 3

Distinctiveness Conflict Risk

The Customer.io-specific niche with code-level triggers (401/429) makes it clearly distinguishable and unlikely to fire for the wrong skill, matching anchor 3.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.