clay-to-deepline

Convert a Clay table configuration into local Deepline scripts. Handles extraction (MCP or script), documentation, action mapping, script generation, and parity validation against Clay ground truth.

Quality

58%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/clay-to-deepline/SKILL.md

Quality

Content

50%

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

This skill is essentially a thin routing shim that delegates all real work to a meta-skill and a recipe file. While it's concise and well-structured as a delegation pattern, it provides virtually no actionable content on its own—no concrete steps for the Clay-to-Deepline migration, no examples, no validation steps. Its value depends entirely on the referenced files which are not provided in the bundle.

Suggestions

Add at least a brief summary of what the clay-to-deepline recipe does (e.g., key phases like extraction, mapping, script generation) so Claude has context before loading external files.

Include a concrete example of expected input (e.g., a Clay table config snippet) and expected output (e.g., a Deepline script snippet) to make the skill actionable even in isolation.

Add a validation or parity-check step in the workflow (the description mentions 'parity validation against Clay ground truth' but the content never addresses this).

Provide the bundle files (deepline-gtm skill, clay-to-deepline recipe) or at minimum verify the relative path is correct and document what Claude should expect to find in each referenced file.

Dimension	Reasoning	Score
Conciseness	The content is very lean—just a few lines explaining the delegation pattern. Every sentence serves a purpose: clarifying that this is a shortcut, establishing execution order, and pointing to the governing meta-skill. No unnecessary explanation.	3 / 3
Actionability	The skill provides no concrete code, commands, or executable guidance. It entirely delegates to other skills/recipes without giving any direct actionable steps Claude can follow from this file alone. There are no examples, no scripts, no commands—just references to other documents.	1 / 3
Workflow Clarity	There is a numbered 3-step sequence, but it lacks any validation checkpoints or feedback loops. The steps are essentially 'invoke another skill, follow its instructions, and also read a recipe'—which is a delegation pattern rather than a clear workflow with verifiable milestones.	2 / 3
Progressive Disclosure	It references external files (deepline-gtm meta-skill and clay-to-deepline recipe) with a relative path, but no bundle files are provided to verify these references exist. The structure is one level deep, which is good, but the skill is almost entirely a pointer with minimal standalone value, and the reference to 'every sub-doc the meta-skill tells you to' is vague.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 in specificity and distinctiveness, clearly naming a niche workflow (Clay-to-Deepline conversion) with multiple concrete steps. However, it lacks an explicit 'Use when...' clause, and the trigger terms are heavily technical jargon that may not match how users naturally phrase requests. Adding explicit trigger guidance and more natural language variations would improve skill selection accuracy.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user wants to migrate or convert a Clay table configuration to local Deepline scripts, or mentions Clay-to-Deepline migration.'

Include natural language trigger variations such as 'migrate Clay', 'replicate Clay workflow locally', or 'Clay replacement' to improve matching with how users might phrase their requests.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: extraction (MCP or script), documentation, action mapping, script generation, and parity validation against Clay ground truth. These are distinct, concrete steps in a workflow.	3 / 3
Completeness	Clearly answers 'what does this do' with the list of actions (extraction, documentation, action mapping, script generation, parity validation), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes domain-specific terms like 'Clay table', 'Deepline scripts', 'MCP', 'parity validation', and 'ground truth', but these are fairly technical. Missing natural user phrases like 'migrate Clay', 'convert Clay to Deepline', or file extensions that users might naturally say.	2 / 3
Distinctiveness Conflict Risk	Very specific niche: converting Clay table configurations to Deepline scripts. The combination of 'Clay' and 'Deepline' creates a highly distinctive trigger that is unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: getaero-io/gtm-eng-skills
Commit: 449bc08

Reviewed: 1 day 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.