deepline-plays-quickstart

Run a quick Deepline demo recipe on the V2 CLI using prebuilt plays.

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/deepline-plays-quickstart/SKILL.md

Quality

Content

77%

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

This is a strong, actionable skill with clear executable commands, well-sequenced workflows, and practical fallback chains. Its main weakness is moderate verbosity in the fallback/last-resort sections and the lack of progressive disclosure through supporting files. The recipes are concrete and immediately usable, which is the skill's greatest strength.

Suggestions

Tighten the fallback and last-resort sections in Recipe 1—consider condensing the inline fallback commands into a referenced file or a more compact format to reduce token usage.

Consider extracting the V2 command notes and execution flow pattern into a separate reference file, keeping SKILL.md focused on the recipes themselves.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining basic concepts, but some sections are somewhat verbose—particularly the fallback instructions in Recipe 1 and the repeated narration guidance. The 'Last resort' and 'Fallback' sections add bulk that could be tightened.	2 / 3
Actionability	The skill provides fully executable, copy-paste-ready CLI commands with concrete JSON payloads, specific flag usage (--watch --json), exact column names to display, and clear substitution guidance. The fallback path also includes concrete commands.	3 / 3
Workflow Clarity	Each recipe follows a clearly numbered sequence (run → export → wrap up) with explicit validation via --watch for streaming completion, --full --json for billing verification, and a well-structured fallback chain (primary → fallback → last resort) that serves as error recovery.	3 / 3
Progressive Disclosure	The content is reasonably well-structured with separate recipes and an execution flow overview, but everything is inline in a single file. The fallback section for Recipe 1 is dense and could benefit from being separated. There are references to /deepline-plays but no structured navigation to supporting files.	2 / 3
	Total	10 / 12 Passed

Description

40%

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 identifies a clear, narrow niche (Deepline V2 CLI demo recipes) which makes it distinctive, but it is incomplete due to the absence of a 'Use when...' clause and only describes a single action. It would benefit from explicit trigger guidance and additional detail about what the skill actually does beyond running a demo.

Suggestions

Add a 'Use when...' clause specifying trigger conditions, e.g., 'Use when the user asks to run a Deepline demo, try out a prebuilt play, or get started with the V2 CLI.'

Expand the description with more concrete actions, e.g., 'Runs a quick Deepline demo recipe on the V2 CLI using prebuilt plays, lists available demo recipes, and displays output results.'

Include natural user-facing trigger terms such as 'quick start', 'example', 'try Deepline', or 'demo run' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	It names a specific domain ('Deepline demo recipe', 'V2 CLI', 'prebuilt plays') and a single action ('Run'), but does not list multiple concrete actions or elaborate on what running a demo recipe entails.	2 / 3
Completeness	It describes what the skill does ('Run a quick Deepline demo recipe') but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when' clause caps completeness at 2, and since the 'what' is also thin, this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'Deepline', 'demo', 'V2 CLI', and 'prebuilt plays', but these are fairly niche/technical terms. It misses common variations or natural phrases a user might say (e.g., 'quick start', 'example recipe', 'demo run').	2 / 3
Distinctiveness Conflict Risk	The description is highly specific to 'Deepline demo recipe on the V2 CLI using prebuilt plays', which is a very narrow niche unlikely to conflict with other skills.	3 / 3
	Total	8 / 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.