clay-core-workflow-b
Use Claygent AI research and AI-powered personalization to generate outreach copy from enriched data. Use when writing personalized email openers, running Claygent research prompts, or configuring AI columns for campaign personalization at scale. Trigger with phrases like "clay AI personalization", "claygent research", "clay outreach copy", "clay secondary workflow", "clay AI column".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 that clearly identifies its niche within the Clay platform ecosystem. It provides explicit trigger guidance and a 'Use when' clause, making it easy for Claude to select appropriately. The main weakness is that the specific capabilities could be more concretely enumerated—listing more granular actions beyond 'generate outreach copy' and 'configure AI columns' would strengthen specificity.
Suggestions
Add more concrete action verbs and outputs, e.g., 'Generates personalized email openers, crafts subject lines, builds Claygent research prompts, and configures AI enrichment columns for scaled outbound campaigns.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Claygent AI research, outreach copy) and some actions (generate outreach copy, running research prompts, configuring AI columns), but the actions are not highly concrete or comprehensive—e.g., it doesn't specify what kinds of enriched data, what specific outputs are produced, or detailed steps. | 2 / 3 |
Completeness | The description clearly answers both 'what' (generate outreach copy from enriched data using Claygent AI research and AI-powered personalization) and 'when' (explicit 'Use when' clause with specific trigger scenarios and a 'Trigger with phrases' list). | 3 / 3 |
Trigger Term Quality | The description includes a dedicated trigger phrase list with natural, specific terms like 'clay AI personalization', 'claygent research', 'clay outreach copy', 'clay secondary workflow', 'clay AI column', plus contextual phrases like 'personalized email openers' and 'campaign personalization at scale'. These cover likely user phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to the Clay platform ecosystem with distinctive terms like 'Claygent', 'clay AI column', and 'clay secondary workflow', making it very unlikely to conflict with generic email or copywriting 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 well-structured, highly actionable skill with clear step-by-step workflows, concrete prompt examples, executable QA code, and a useful error handling table. Its main weaknesses are moderate verbosity (some marketing-style stats and unnecessary context) and a monolithic structure that could benefit from splitting advanced topics into separate files. Overall it serves as a strong practical guide for Clay AI personalization workflows.
Suggestions
Remove marketing statistics ('30% of Clay customers...') and obvious prerequisites ('Understanding of prompt engineering basics') to improve conciseness.
Consider extracting the QA code (Step 4) and the Navigator section (Step 6) into separate bundle files, referencing them from the main skill to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary context (e.g., '30% of Clay customers use Claygent daily, generating 500K+ research tasks per day', 'Understanding of prompt engineering basics' as a prerequisite). The overview paragraph could be tighter. However, most of the content is practical and relevant, with good prompt examples and code that earn their place. | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste-ready guidance: complete Claygent prompts with template variables, a TypeScript QA function, a full JSON API payload for export, and specific Clay UI navigation steps. Each step has executable examples rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with logical progression from research → multi-output extraction → personalization → QA validation → export → advanced use. Step 4 provides an explicit validation checkpoint with a QA function before campaign launch, and the conditional run filter in Step 5 acts as another gate. The error handling table adds recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill references `clay-core-workflow-a` and `clay-common-errors` as related skills, and includes external resource links. However, the content is fairly long and monolithic — the QA code, the error table, and the Navigator section could potentially be split into separate reference files. With no bundle files provided, there's no deeper structure to support progressive disclosure. | 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.