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".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

77%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.

Highly actionable content with concrete prompts, code, and a clear sequenced workflow including validation. The main weaknesses are a marketing-fluffed overview and a monolithic structure that would benefit from splitting prompt templates and QA logic into reference files.

Suggestions

Remove the marketing statistic from the Overview ('30% of Clay customers... 500K+ research tasks per day') and other explanatory padding to improve token efficiency.

Move the reusable Claygent prompt templates and the QA TypeScript snippet into files under references/ (e.g. prompts.md, qa-check.ts) and link to them from SKILL.md, turning the body into a lean overview.

Convert the Step 4 QA check into an explicit feedback loop ('run qaCheck, if issues exist fix the row/column mapping and re-run until pass') so the validation narrative matches the code.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete prompts, code, and a compact error table, but the Overview pads in marketing fluff ('30% of Clay customers use Claygent daily, generating 500K+ research tasks per day') and some explanatory prose Claude does not need.	2 / 3
Actionability	Provides copy-paste-ready Claygent research prompts, a complete TypeScript QA function, a full JSON HTTP config, and specific conditional-run criteria — fully executable guidance.	3 / 3
Workflow Clarity	Steps 1–6 are clearly sequenced with an explicit QA checkpoint before campaign launch and conditional gating (ICP Score >= 70), plus an error-handling table for recovery — validation is present for this batch operation.	3 / 3
Progressive Disclosure	Sections are well-organized and external links are one level deep, but the skill is a ~180-line monolithic document with all prompt templates and code inline; no reference files exist to split detail into, and the length would benefit from offloading templates to bundle files.	2 / 3
	Total	10 / 12 Passed

Description

100%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 strong description: concrete capabilities, explicit 'Use when' guidance, natural trigger phrases, and a clearly distinct product niche. Voice is appropriately third-person imperative throughout.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Claygent AI research', 'AI-powered personalization', 'generate outreach copy from enriched data' — tied to a specific tool rather than vague language.	3 / 3
Completeness	Clearly answers both 'what' (research + personalization to generate outreach copy) and 'when' via an explicit 'Use when...' clause plus trigger phrases.	3 / 3
Trigger Term Quality	Explicit trigger phrases ('clay AI personalization', 'claygent research', 'clay outreach copy', 'clay AI column') give good coverage of natural terms a Clay user would say; 'clay secondary workflow' is slightly branded but the cluster is strong.	3 / 3
Distinctiveness Conflict Risk	The Claygent/Clay niche is highly product-specific with distinct triggers, making overlap with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/clay-pack/skills/clay-core-workflow-b/SKILL.md
Commit: c4eafaf

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.