deepline-engine

Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

73%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 strong, highly actionable engine-building skill with exceptional workflow validation and feedback loops for destructive/paid operations. Its main weakness is length and duplication between the Workflow and Automatic publication sections.

Suggestions

Collapse the overlap between Workflow steps 10-11 and the "Automatic publication and verification" section into a single sequenced procedure to cut tokens and remove drift risk.

Move the detailed paid-pilot cap/verification choreography into a reference file (e.g., references/paid-pilot.md) and keep SKILL.md as the overview, improving both conciseness and progressive disclosure.

Add one complete minimal orchestrator .play.ts example (state routing + ctx.runPlay + idempotent persistence) so Play authoring is copy-paste ready, not just signature-level.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the "Automatic publication and verification" section substantially duplicates Workflow steps 10-11 and the pilot detail, so it could be tightened; not a 4.	3 / 5
Actionability	Provides concrete, executable commands (deepline plays search/describe/get/versions, billing.maxCreditsPerRun) and real API signatures (definePlay, ctx.runPlay), but orchestrator authoring is shown via signatures rather than a full copy-paste example, leaving minor gaps.	4 / 5
Workflow Clarity	An 11-step Workflow plus an 11-step publication/verification sequence with explicit validation checkpoints ("Validate every edge", "Stop on failure"), feedback loops (fix and re-validate), and a checklist for the destructive/paid pilot — matching the top anchor.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one well-signaled one-level-deep reference ([references/state-machine-contract.md]) whose purpose is stated; not a 5 because the inline duplicated pilot/publication detail could itself be offloaded to a reference.	4 / 5
	Total	16 / 20 Passed

Description

80%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 clearly and explicitly covers both what the skill does and when to invoke it, anchored in a distinct, well-scoped niche. Its main weakness is limited trigger-term variation around the single phrase "build an engine."

Suggestions

Add natural trigger synonyms or variations (e.g., "orchestrator", "state-machine Play", "replay-safe workflow") so the description matches more phrasings a user might actually say.

Consider naming a file extension or concrete artifact type in the trigger clause to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("Build, publish, and verify") tied to a specific domain ("Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot"); verbs are slightly generic, keeping it just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Build, publish, and verify a Deepline Play as a durable state machine...") and when ("Invoke this skill explicitly when the user asks to build an engine") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Provides one natural trigger phrase ("when the user asks to build an engine") but lacks synonyms or variations a user might actually say, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The Deepline Play / durable state machine / Customer DB niche is highly specific with a distinct trigger, giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 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-engine/SKILL.md
Commit: 3bb8968

Reviewed: 3 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.