clay-known-pitfalls
Identify and avoid the top Clay anti-patterns, gotchas, and integration mistakes. Use when reviewing Clay integrations for issues, onboarding new team members, or auditing existing Clay table configurations. Trigger with phrases like "clay mistakes", "clay anti-patterns", "clay pitfalls", "clay what not to do", "clay gotchas", "clay code review".
83
81%
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 that clearly communicates its purpose and when to use it. It excels in completeness and trigger term coverage with explicit 'Use when' and 'Trigger with' clauses. The main weakness is that the capabilities described are somewhat high-level—listing specific anti-patterns or concrete review actions would strengthen specificity.
Suggestions
Add 2-3 specific examples of the anti-patterns or mistakes covered (e.g., 'Detects incorrect enrichment column mappings, flags missing error handling in webhooks, identifies rate limit violations') to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Clay anti-patterns/mistakes) and some actions (identify, avoid, review, audit), but doesn't list specific concrete anti-patterns or specific actions like 'detect missing webhook handlers' or 'flag incorrect enrichment column mappings'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | The description clearly answers both 'what' (identify and avoid top Clay anti-patterns, gotchas, and integration mistakes) and 'when' (reviewing Clay integrations for issues, onboarding new team members, auditing existing Clay table configurations), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | The description explicitly lists natural trigger phrases users would say: 'clay mistakes', 'clay anti-patterns', 'clay pitfalls', 'clay what not to do', 'clay gotchas', 'clay code review'. These are realistic terms a user would naturally use when seeking this kind of help. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Clay anti-patterns and mistakes, which is a clear niche. The trigger terms are all Clay-specific and unlikely to conflict with other skills unless there are multiple Clay-related skills, in which case the 'anti-patterns/mistakes' focus provides further distinction. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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 reference skill with excellent actionability — each pitfall provides specific symptoms, root causes, and concrete fixes with real numbers and examples. The consistent structure makes it highly scannable. Main weaknesses are minor verbosity (some explanations could be tighter) and the lack of explicit validation/verification steps after applying fixes, which would be valuable given the credit-burning consequences of these pitfalls.
Suggestions
Add brief verification steps to key pitfalls (e.g., 'Verify: Check Settings > Connections shows green checkmarks for connected API keys' or 'Verify: Run one test row and confirm only 1 action credit consumed').
Trim the Prerequisites section entirely — Claude doesn't need to be told what prior knowledge is needed, and the skill content is self-explanatory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with clear symptom/cause/fix structure, but some sections include unnecessary context (e.g., Prerequisites listing things Claude would know, some verbose explanations). The code examples for CSV normalization are somewhat trivial and the comments explain obvious things. Overall mostly tight but could be trimmed. | 2 / 3 |
Actionability | Each pitfall provides specific, concrete fixes with exact settings to toggle, code snippets, specific formulas (ISEMPTY, ICP Score thresholds), navigation paths (Settings > Connections), and quantified impacts. The Claygent bad/good prompt comparison is particularly actionable. | 3 / 3 |
Workflow Clarity | Each pitfall is clearly structured with Symptom → Root Cause → Fix, which is effective for a reference/checklist skill. However, there are no validation checkpoints or feedback loops — for instance, no way to verify webhook count, no step to confirm API keys are working, no verification that conditional run rules are properly configured. For a skill that involves potentially destructive credit-burning operations, explicit verification steps would strengthen it. | 2 / 3 |
Progressive Disclosure | Well-organized with a clear overview, individual pitfalls as scannable sections with consistent formatting, a summary checklist table for quick reference, external resource links, and a pointer to advanced troubleshooting. Content is appropriately contained in one file given its nature as a reference checklist, with one-level-deep references to related resources. | 3 / 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.