deepline-quickstart

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

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/deepline-quickstart/SKILL.md

Quality

Content

68%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.

The body is highly actionable with executable commands and a clear fast-path-to-fallback flow, but it is held back by duplicated steps and a batch operation that deliberately skips output validation. Consolidating the redundant commands and adding a lightweight in-budget verification step would lift both conciseness and workflow clarity.

Suggestions

De-duplicate the fast path and the Step 1/2/3 section so the canonical commands appear once, with the steps cross-referencing the fast path instead of restating it.

Add a minimal verification that stays within the time budget (e.g. a one-line check that the enriched CSV has a non-empty email column) so the batch operation has a checkpoint without violating the speed goal.

Consider moving the fallback payloads and the normalization Python into a scripts/ file referenced from SKILL.md to reduce inline length while keeping the fast path prominent.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the fast-path block duplicates the same dropleads_search and enrich commands shown again in Step 1/2/3, and fallback variants repeat payloads; these could be consolidated.	3 / 5
Actionability	Fully executable, copy-paste-ready bash with exact tool names, JSON payloads, hyphenated prebuilt ids, and concrete CSV paths covering the common case and fallbacks.	5 / 5
Workflow Clarity	The sequence and fallback/last-resort feedback loops are clear, but this is a batch enrichment operation that explicitly instructs not to validate the output, so the batch-without-validation cap holds it at 3.	3 / 5
Progressive Disclosure	Well-organized with clear section headers and a self-contained quickstart needing no separate reference files (no bundle files exist); minor gaps only, such as the inlined duplicated step detail.	4 / 5
	Total	15 / 20 Passed

Description

48%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.

The description conveys a clear purpose but lacks an explicit 'when to use' trigger and relies on generic, imperative-voice language with product-internal jargon. Adding a third-person 'Use when...' clause with natural user phrasing would meaningfully raise its score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants a quick Deepline demo or asks how Deepline works.'

Rewrite in third person ('Runs a quick Deepline demo...') to avoid the second-person/imperative voice penalty and list 1-2 more concrete actions.

Include natural user-facing terms and synonyms (e.g. 'Deepline quickstart', 'demo Deepline', 'try Deepline') alongside the product name.

Dimension	Reasoning	Score
Specificity	Names the domain (Deepline) and one concrete action ('Run a quick Deepline demo recipe'), but the action is generic and there is only one; the imperative 'Run...' voice triggers the second-person penalty, dropping an otherwise-3 to 2.	2 / 5
Completeness	There is a clear 'what' (run a quick demo recipe to show how Deepline works) but no 'Use when...' trigger clause, so per the missing-trigger cap it cannot exceed 3.	3 / 5
Trigger Term Quality	Includes the product name and 'demo'/'quick', but 'demo recipe' is Deepline-internal jargon and common natural variations or synonyms a user would actually say are missing.	3 / 5
Distinctiveness Conflict Risk	The specific product name 'Deepline' carves a clear niche with only minor overlap risk against other skills, though the absence of explicit triggers keeps it just below a 5.	4 / 5
	Total	12 / 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/deepline-quickstart/SKILL.md
Commit: 869569c

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.