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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%Weight 40%Scale 1-5

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

A tight router-style skill: fully concrete setup commands and an unambiguous execution order that correctly defers to the governing meta-skill. The only real weaknesses are minor repetition of the 'meta-skill governs' caution and the total absence of any conversion-task substance in this file, which is by design but leaves nothing actionable if the external recipe is unreachable.

Suggestions

Collapse the three restatements of 'the meta-skill governs the session' (lines 19, 24, and 27) into a single bolded note to save tokens without losing the warning.

Add one line of fallback guidance for when the referenced recipe path ../deepline-gtm/recipes/clay-to-deepline.md does not resolve (e.g., locate the deepline-gtm skill directory) so the routing does not dead-end.

Dimension	Reasoning	Score
Conciseness	The body is lean with executable commands and no explanations of concepts Claude already knows, but the caution 'the deepline-gtm governs the entire session' is restated three times across the shortcut note, step 2 ('Do not skip docs just because a recipe is pre-selected'), and the closing line ('The recipe only covers one part of the task. The meta-skill handles everything else').	4 / 5
Actionability	Quick Start gives copy-paste-ready bash commands (npm install, auth register/wait/status) and Execution Order names the exact tool ('Invoke deepline-gtm using the Skill tool') and the exact relative recipe path. It falls short of 5 because the core conversion task itself (extraction, action mapping, parity validation) is never demonstrated or specified here — everything is delegated to an external file.	4 / 5
Workflow Clarity	The Execution Order is a clear, numbered 3-step sequence with a conditional gate ('only when that gate routes you to it') and inline status checks ('deepline auth status', 'auth wait... no-op if already connected'). No destructive or batch operation appears in this body, so no validation cap applies, but there are no explicit error-recovery checkpoints for the delegated recipe execution.	4 / 5
Progressive Disclosure	The body is under 50 lines, split into clear 'Quick Start' and 'Execution order' sections, with a single one-level-deep reference ('../deepline-gtm/recipes/clay-to-deepline.md (relative to this file)') that is clearly signaled and conditionally gated. No bundle files exist to organize, and nothing that belongs in a separate file is inlined.	5 / 5
	Total	17 / 20 Passed

Description

75%Weight 40%Scale 1-5

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 specific, third-person description that clearly states what the skill does with a comprehensive action list and minimal conflict risk. Its one clear defect is the complete absence of an explicit 'when to use' trigger clause, which both caps completeness and leaves triggering to inference from the proper nouns.

Suggestions

Append an explicit trigger clause, e.g. 'Use when migrating a Clay table, Clay workflow, or Clay integration to Deepline, or when the user mentions Clay or Deepline.'

Add one or two natural synonyms ('migrate', 'port') alongside 'Convert' so the description matches the phrasings users actually type.

Dimension	Reasoning	Score
Specificity	'Handles extraction (MCP or script), documentation, action mapping, script generation, and parity validation against Clay ground truth' enumerates five concrete, distinct actions with the expected source and target named — comprehensive for a migration skill. It is not a 4 because no meaningful action in the pipeline is missing.	5 / 5
Completeness	The 'what' is fully and concretely answered (convert Clay table configuration into local Deepline scripts, with the enumerated pipeline), but there is no 'Use when...' clause or any equivalent trigger guidance — when to invoke it is left entirely implicit. Per the rubric guideline, a missing explicit 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	'Clay table configuration', 'Deepline scripts', 'Convert', and 'parity validation' are the natural terms a user of these tools would say, giving good keyword coverage. It misses natural synonyms and variations a user might utter ('migrate', 'port', 'Clay table', 'Clay to Deepline'), keeping it below the 5 anchor's synonym-level coverage.	4 / 5
Distinctiveness Conflict Risk	The description is anchored by two proper nouns ('Clay', 'Deepline') forming a clear niche with distinct triggers, so it is unlikely to fire for any other skill. It is not a 4 because no overlap risk with a neighboring skill is identifiable from the text.	5 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getaero-io/gtm-eng-skills
Path: skills/clay-to-deepline/SKILL.md
Commit: a9b9731

Reviewed: 6 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.