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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

72%

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

The body is highly actionable and well-structured with executable prompts, code, and an error table, but loses points for minor marketing padding and a list-numbering defect plus an implicit (rather than explicit) QA feedback loop. Progressive disclosure is clean given the self-contained, no-bundle structure.

Suggestions

Remove the marketing statistic ("30% of Clay customers use Claygent daily, generating 500K+ research tasks per day") from the Overview; it adds tokens without aiding execution.

Fix the broken ordered list in Step 1 where the "Enable Auto-run on new rows" item restarts numbering at 1 instead of continuing the sequence.

Add an explicit fix-and-retry loop after the Step 4 QA check (e.g., "If qaCheck returns issues, fix the row or prompt and re-run before exporting") to turn the implicit checkpoint into a real feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and instructional (prompts, code, an error table) rather than explaining known concepts, but includes some non-essential padding such as the marketing stat "30% of Clay customers use Claygent daily, generating 500K+ research tasks per day" that does not aid execution; this places it at the mostly-efficient-but-could-be-tighter anchor.	2 / 3
Actionability	Provides copy-paste-ready research and copywriting prompts, a complete executable TypeScript QA function, a concrete JSON HTTP API export config, and specific UI click paths — fully executable and specific, matching the top anchor.	3 / 3
Workflow Clarity	A clear 6-step sequence exists with a QA checkpoint (Step 4) and a conditional export gate, but the sequence is disrupted by a list-numbering bug in Step 1 (two separate "1." lists) and lacks an explicit fix-and-retry feedback loop after the QA check beyond flagging issues, capping it below the top anchor.	2 / 3
Progressive Disclosure	No bundle files are present (references/, scripts/, assets/ are empty), so the skill is self-contained; sections are well-organized with a one-level-deep Resources section linking to external Clay docs and a single Next Steps pointer, with no nested references, satisfying the well-organized anchor for a self-contained skill.	3 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is strong across all dimensions: it states concrete actions, includes an explicit "Use when" clause with natural trigger phrases, and occupies a clear niche. It does not score below top on any dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "generate outreach copy from enriched data", "writing personalized email openers", "running Claygent research prompts", "configuring AI columns" — matching the highest anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both "what" (generate outreach copy from enriched data via Claygent) and "when" ("Use when writing personalized email openers, running Claygent research prompts, or configuring AI columns..."), satisfying the top anchor.	3 / 3
Trigger Term Quality	Provides a good spread of natural trigger phrases a user would say in this domain ("clay AI personalization", "claygent research", "clay outreach copy", "clay secondary workflow", "clay AI column"), with third-person voice and no jargon-only language.	3 / 3
Distinctiveness Conflict Risk	Targets a clear Clay/Claygent personalization niche with distinct triggers; the "clay secondary workflow" phrase is slightly generic within Clay's ecosystem but the overall niche is distinct and unlikely to trigger for unrelated skills.	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
Commit: 3022dd3

Reviewed: 2 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.