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 excels at completeness with explicit 'Use when' and 'Trigger with' clauses, and its platform-specific terminology makes it highly distinctive. 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 and subject lines, configures Claygent research prompts to pull company/person insights, sets up AI formula columns for dynamic copy generation.'
| 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 scenarios and a 'Trigger with phrases' section). | 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 (Claygent, Clay AI columns, Clay secondary workflow), making it very unlikely to conflict with generic email writing or other outreach 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 prompts, executable code, and good error handling. Its main weakness is length — it could be more concise by trimming marketing stats and moving the QA code and error table to referenced files. Overall it serves as a strong operational guide for Clay AI personalization workflows.
Suggestions
Remove marketing statistics ('30% of Clay customers...') and the 'Understanding of prompt engineering basics' prerequisite to improve conciseness.
Consider moving the full QA TypeScript function and error handling table to a referenced file (e.g., `clay-qa-checks.md`) to keep the SKILL.md as a leaner overview with 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 content is functional and relevant. | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste ready prompts for Claygent columns, AI columns, and API export configurations. The QA check TypeScript code is executable, the JSON payload for Instantly is complete, and the Claygent prompts include specific column references and output formatting instructions. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced from research to export, with an explicit QA validation step (Step 4) before campaign launch. The error handling table provides a feedback loop for common failures, and the conditional run filter in Step 5 acts as a gate before sending data to outreach tools. | 3 / 3 |
Progressive Disclosure | The skill references companion files (`clay-core-workflow-a`, `clay-common-errors`) and external resources, which is good. However, the content is quite long and some sections (like the full QA TypeScript function and the detailed error table) could be split into referenced files. The inline content is heavy for a SKILL.md overview. | 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.