CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deepline-start

Interview a user to discover a concrete GTM problem or manual task, recommend the right installed Deepline skill, prebuilt Play, recipe, or tool, confirm the plan and org, then start the chosen workflow. Use only when the user explicitly invokes deepline-start.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-engineered orchestration skill: every phase has concrete commands and explicit validation gates, especially around org verification and consent. The main costs are repeated approval-rule statements and a long single-file body that could shed some content to references.

Suggestions

Consolidate the plan-and-org approval rules, which are currently restated across 'Route first' and 'Confirm and hand off', into a single authoritative statement to cut repetition.

Move the emerging-need routing table or the interview question examples into a references/ file so SKILL.md stays a lean overview.

Trim overlapping guidance between 'Route first' and 'Select the workflow' about when a specialist versus deepline-gtm should lead.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes Claude's competence with no concept explanations, but the plan-and-org approval rules are restated multiple times across 'Route first' and 'Confirm and hand off' and could be consolidated.

4 / 5

Actionability

Fully actionable for an instruction-only skill: exact CLI commands ('deepline --maintenance off org status', 'deepline org set'), a quoted confirmation-question template, a routing table with per-row verification items, and four ordered handoff steps including the Skill-loader call with the brief as arguments.

5 / 5

Workflow Clarity

The route → interview → select → confirm → handoff sequence is explicit and gated by validation checkpoints: org-ID comparison blocks mismatched handoffs, explicit user acceptance of the org is required ('"The plan is confirmed"… is not org approval'), and plan changes trigger revise-and-reconfirm feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, and the single body is well-sectioned and easy to navigate, but at roughly 190 lines it exceeds the simple-skill allowance and keeps the routing table and interview material fully inline; moving some material to a references file would sharpen the overview.

4 / 5

Total

18

/

20

Passed

Description

92%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.

A strong description: concrete action sequence, explicit invocation-only trigger, third-person voice, and no padding. The only weakness is modest synonym coverage for GTM terminology, which slightly limits natural-trigger recall.

DimensionReasoningScore

Specificity

The description lists a complete lifecycle of concrete actions — 'Interview a user to discover a concrete GTM problem', 'recommend the right installed Deepline skill, prebuilt Play, recipe, or tool', 'confirm the plan and org', 'then start the chosen workflow' — with no vague filler and full coverage of the skill's job.

5 / 5

Completeness

Both questions are answered explicitly and concretely: the 'what' is the interview-recommend-confirm-start lifecycle, and the 'when' is the explicit trigger phrase 'Use only when the user explicitly invokes deepline-start'.

5 / 5

Trigger Term Quality

Natural terms like 'GTM problem', 'manual task', 'workflow', 'Play', 'recipe', and the invocation name 'deepline-start' are present, but common user phrasings such as 'go-to-market' or 'go to market strategy' are missing.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear entry-point niche for the Deepline skill family and gates triggering on the exact invocation name 'deepline-start', which resolves overlap with the sibling deepline-* skills; conflict risk is minimal.

5 / 5

Total

19

/

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-start/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.