deepline-quickstart

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

Quality

72%

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

81%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 a complete, executable fast path and robust error-recovery workflows. Its main weakness is redundancy: the same search payload and normalization logic are repeated across the fast path and detailed steps, inflating token cost without adding information.

Suggestions

State the dropleads_search_people payload once (e.g., in the fast path) and have Step 1 and the Fallback reference it, or move the detailed Step 1–3 content into a references/ file.

Drop Step 2's "normalize those columns locally" instructions since the fast-path Python heredoc already performs that normalization.

Merge the overlapping CLI guidance in "Quick Start" and "CLI surface" (e.g., the repeated --help / auth-status instructions) into one section.

Dimension	Reasoning	Score
Conciseness	The dropleads_search_people JSON payload appears three times nearly verbatim (fast path, Step 1, and Fallback), and Step 2's instruction to "normalize those columns locally" duplicates logic already implemented in the inline Python heredoc. The content is mostly operational instruction rather than concept padding, but the triplicated payload is noticeable tightening debt, placing it between anchors 2 and 3.	3 / 5
Actionability	The fast path is a fully executable, copy-paste-ready bash block: set -e, the exact search payload, a complete Python normalization heredoc, and a concrete enrich command with a specific --name and --with configuration. Fallback and last-resort commands are equally concrete, covering the common cases.	5 / 5
Workflow Clarity	The three-step execution flow has explicit completion checkpoints ("complete only when deepline enrich exits and writes the CSV", "tell the user the results only after the CSV exists"), embedded validation (raise SystemExit on empty leads), and clear feedback loops for error recovery (Fallback section with an alternate query, Last resort escalation to /deepline-gtm).	5 / 5
Progressive Disclosure	A single well-organized file with clear sections (Quick Start, CLI resolution, Execution flow, Recipe 1) and no buried or nested references; navigation is easy. Not a 5: the ~50 lines of duplicated detailed steps (Step 1–3) could live in a separate reference file, leaving the SKILL.md as a lean fast-path overview.	4 / 5
	Total	17 / 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 is short and anchored to a distinctive product name, but it describes only a generic action with no explicit 'when to use' guidance and few natural trigger terms. It reads more like a title than a discoverability description.

Suggestions

Add an explicit 'Use when...' clause (e.g., "Use when the user wants to try Deepline, see a quick demo, or asks what Deepline can do").

Name the concrete capabilities: e.g., "Find CTOs at NY startups with verified emails via Dropleads search and waterfall email enrichment" instead of the generic "demo recipe".

Include natural trigger phrases and synonyms users would say — "quickstart", "try Deepline", "Deepline demo" — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Run a quick Deepline demo recipe to show the user how Deepline works" names the domain (Deepline demo) but the action is minimal and generic — no concrete capability such as which recipes exist or what they produce. It names the domain without concrete actions, matching anchor 2 rather than 3.	2 / 5
Completeness	A 'what' is present but weak ("run a demo recipe to show how Deepline works") and the 'when' is entirely missing — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Keywords like "Deepline", "demo recipe", and "quick" are relevant, but the description misses the natural phrases a user would actually say (e.g. "quickstart", "try Deepline", "find leads with Deepline"), so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	"Deepline" is a distinctive product name giving a clear niche with minimal conflict risk, but the absence of explicit trigger phrases means distinctiveness rests solely on the product name rather than distinct trigger wording.	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: 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.