CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deepline-quickstart

Run a quick Deepline demo with a maintained Play.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/deepline-quickstart/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 a lean, fully executable quickstart covering both single-record and CSV batch flows, with explicit cost-confirmation and pilot-review checkpoints baked into each workflow. Its only notable gap is the absence of an error-recovery loop for failed or misaligned batch runs.

DimensionReasoningScore

Conciseness

Every line is a command or a directive ("npm install -g deepline", "head -n 4 leads.csv > \"$WORKDIR/leads-pilot.csv\"") with zero concept explanations and no padding — it fully assumes Claude's competence. Not a 4 because there is no over-explanation left to trim; the one-line purpose statement is a legitimate summary, not filler.

5 / 5

Actionability

Commands are fully executable with a concrete example input ('{"linkedin_url":"https://www.linkedin.com/in/example/"}'), a timestamped --csv-out, and coverage of both single-record and CSV batch cases. Not a 4 because no key details are missing — the <play-from-search> placeholders reflect genuinely dynamic search output, not pseudocode.

5 / 5

Workflow Clarity

Sequences are clearly ordered with explicit checkpoints ("Show the --dry-run price, confirm the user wants to spend credits", "Review row alignment and results before asking whether to process the rest of the file"), so the batch-operation cap at 3 does not apply. Not a 5 because there is no error-recovery feedback loop (e.g., what to do when a pilot's row alignment or results look wrong); not a 3 because verification steps are explicitly present, not merely implied.

4 / 5

Progressive Disclosure

The ~55-line body is well organized into Quick Start / Single record / CSV sections and is self-contained — no bundle files exist and none are needed for a quickstart, so the simple-skill exception applies. Not a 4 because no content is misplaced (nothing belongs in a separate file) and navigation across sections is trivial.

5 / 5

Total

19

/

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 names the Deepline domain and one action but omits the skill's core capabilities (Play search, dry-run pricing, single-record and CSV batch enrichment) and any 'when to use' trigger guidance. It is distinctive thanks to the product name yet under-represents what the skill actually does.

Suggestions

Enumerate the concrete capabilities in the description, e.g. 'Search maintained Plays, run single-record and CSV batch enrichments, and check costs with --dry-run before spending credits.'

Add an explicit trigger clause, e.g. 'Use when the user wants to enrich records or leads, or mentions Deepline, Plays, or data enrichment.'

Include natural synonyms users would say (enrich, enrichment, leads, CSV, data) to broaden trigger-term coverage beyond 'Deepline' and 'demo'.

DimensionReasoningScore

Specificity

The description names the domain ("Deepline") and a single minimal action ("Run a quick Deepline demo"), while the skill's actual capabilities — searching Plays, dry-run cost checks, single-record and CSV batch enrichment — are entirely absent. This matches the anchor 'Names the domain but actions are minimal or generic' rather than the 3-anchor, which expects 1-2 concrete actions; it is not a 1 because a concrete action and domain are stated.

2 / 5

Completeness

It has a clear 'what' ("Run a quick Deepline demo with a maintained Play") but no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 4 because the 'when' is entirely absent rather than merely imprecise, and not a 2 because the 'what' is clear and specific.

3 / 5

Trigger Term Quality

"Deepline", "demo", and "Play" are relevant keywords a user of this tool would naturally say, but common variations and synonyms (enrich, enrichment, leads, CSV, data) are missing. This fits 'Some relevant keywords but missing common variations or synonyms' — not a 4 because natural-term coverage is thin, not a 2 because the core product-name trigger is present rather than generic-only language.

3 / 5

Distinctiveness Conflict Risk

"Deepline" is a distinct product name giving this a clear niche with only minor overlap risk against generic data-processing skills. Not a 5 because the thin description offers few distinct trigger phrases and "Run a quick demo" alone is generic; not a 3 because the unique product name prevents meaningful collision with similar skills.

4 / 5

Total

12

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.