deepline-plays

Use for Deepline GTM work that searches, enriches, scores, collects signals, or automates a workflow: find companies or people, enrich a CSV, find emails or LinkedIn, compare providers, build a waterfall, create a webhook or cron, or write a Play. For live information work, run a small heterogeneous experiment, exploit the observed winner, and reopen misses. Skip pure copywriting and non-GTM research.

Quality

92%

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

Quality

Content

92%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.

An information-dense, highly actionable body with strong sequencing and validation checkpoints. Its main weakness is progressive disclosure: the routing table points to five doc files that are not present in the bundle.

Suggestions

Ship the referenced jobs/*.md (finding, enriching, researching, automating) and shared/authoring.md files, or remove the routing table entries that point to them, so navigation resolves.

Either reference references/api-reference.md from the body or drop it from the bundle, so the present-but-unreferenced file does not confuse discovery.

Confirm the <skill-root> placeholder used in the script paths resolves at runtime, since the bundle relies on it for every scaffold/run/cost command.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse imperatives ("Marginal, never amortized.", "One shape.") with no over-explanation of concepts; every line encodes product-specific operational knowledge or a concrete failure mode.	5 / 5
Actionability	It provides copy-paste-ready commands with concrete flags and arguments across install, auth, preflight, catalog, scaffold, run, export, cost-receipt, and feedback — covering the common cases fully.	5 / 5
Workflow Clarity	An explicit contract pipeline ("contract → compare → exploit → recover → export → price"), a completion-receipt checkpoint ("{ok: true, runId, output} is the completion receipt"), the COST RECEIPT, receipt-label feedback loops (CUT CANDIDATE / NEVER REACHED / cached calls), and a deliverable checklist give clear sequencing with validation for the batch operations.	5 / 5
Progressive Disclosure	Signaling and one-level-deep routing are excellent, but scored against the actual bundle the navigation is broken: jobs/finding.md, jobs/enriching.md, jobs/researching.md, jobs/automating.md and shared/authoring.md are referenced yet absent, while references/api-reference.md exists but is never referenced — more than a minor organization gap.	3 / 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, third-person description with an explicit "Use for" trigger, comprehensive concrete actions, and clear exclusions. It is slightly light on synonyms and file extensions, otherwise excellent.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — "find companies or people, enrich a CSV, find emails or LinkedIn, compare providers, build a waterfall, create a webhook or cron, or write a Play" plus "run a small heterogeneous experiment, exploit the observed winner, and reopen misses" — giving comprehensive coverage that exceeds the score-5 anchor.	5 / 5
Completeness	It explicitly answers both "what" (the enumerated search/enrich/score/automate actions) and "when" ("Use for Deepline GTM work…" with the explicit exclusion "Skip pure copywriting and non-GTM research"), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural GTM phrases a user would say are well covered ("find companies", "enrich a CSV", "find emails", "LinkedIn", "compare providers", "webhook", "cron"), but it offers few synonyms and only "CSV" as a file-extension-ish term, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	It is niched to Deepline GTM with distinct triggers (Play, waterfall, enrich CSV, find emails/LinkedIn) and an explicit boundary ("Skip pure copywriting and non-GTM research"), giving minimal conflict risk.	5 / 5
	Total	19 / 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-plays/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.