deepline-quickstart

Run a quick Deepline demo recipe to show the user how Deepline works.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The skill is highly actionable with concrete, executable commands and clear error-recovery branches, but it is held back by command duplication across the fast path and step sections, an explicitly omitted verification step on a batch operation, and a monolithic single-file structure.

Suggestions

De-duplicate the fast path and the Step 1/Step 2 sections so the search and enrich commands appear once, with the detailed steps referenced only as the fallback path.

Add a lightweight post-enrich verification step (e.g. confirm the enriched CSV has non-empty email rows) or explicitly justify its omission in a dedicated note rather than burying it in the fast-path instruction.

Move the detailed per-step breakdowns and fallback payloads into a reference file (e.g. references/recipes.md) and keep SKILL.md as a concise overview pointing to it, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and avoids explaining concepts Claude already knows, but the fast-path block and the subsequent Step 1/Step 2 sections duplicate the same Dropleads search and enrich commands, adding redundancy that could be tightened, matching the level-2 "mostly efficient but includes some unnecessary explanation or could be tightened".	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash with exact JSON payloads, a real Python normalization script, and a specific `deepline enrich` invocation with `--name` and `--with` arguments, matching the level-3 anchor of complete executable code.	3 / 3
Workflow Clarity	Sequencing and error-recovery branches are clear (fast path, "Only use the detailed steps below if the fast path fails", Fallback, Last resort), but the batch/paid enrichment step explicitly omits verification, which the rubric notes caps workflow clarity at 2 for batch operations.	2 / 3
Progressive Disclosure	No bundle files exist, so the entire skill is a single ~120-line SKILL.md with all detail inline (full recipe, step breakdowns, fallback payloads) that could be split into reference files; it has section structure but content that should be separate is inline, matching level-2.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 concrete and clearly scoped to Deepline, but it states only one action and lacks an explicit trigger clause, leaving both specificity and completeness at the mid level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to see a Deepline demo, try Deepline, or understand what Deepline can do."

Expand the action list to name the concrete capabilities demonstrated (e.g. "searches Dropleads for leads and waterfall-enriches emails via LinkedIn-to-email").

Dimension	Reasoning	Score
Specificity	It names a concrete domain and action ("Run a quick Deepline demo recipe") plus purpose ("show the user how Deepline works"), but lists only one action rather than multiple specific capabilities, matching the level-2 anchor and falling short of the level-3 "lists multiple specific concrete actions".	2 / 3
Completeness	It answers "what" (run a demo recipe) but only implies "when" via purpose; there is no explicit "Use when..." trigger clause, which the guidelines say caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	"Deepline demo recipe" and "show the user how Deepline works" capture a user's likely phrasing, but "demo recipe" is product jargon and common variations ("try Deepline", "Deepline walkthrough", "sample run") are absent, so it is not level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	The proper noun "Deepline" gives it a clear, distinct niche unlikely to trigger for unrelated skills, satisfying the level-3 anchor of a clear niche with distinct triggers.	3 / 3
	Total	9 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getaero-io/gtm-eng-skills
Commit: 25492ee

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.