deepline-plays

Use this skill for any GTM Engineering work in Deepline — prospecting, list-building, account research, contact enrichment, email/phone/LinkedIn lookup, ICP qualification, lead scoring, outreach copy, CSV-driven row work, and verifying enriched data. Triggers on phrases like 'enrich this CSV', 'find contacts at these companies', 'build a TAM list', 'waterfall emails for these leads', 'detect job changes', 'is this data accurate', 'write a sequence for', and on any request that mentions Deepline, plays, or named GTM providers (Crustdata, Hunter, Dropleads, etc.). Use this even when the user does not explicitly say 'GTM' — most CSV-with-leads tasks and most provider-driven enrichment tasks are GTM tasks. SKIP only when the request is a Clay table extraction (use clay-to-deepline) or has no Deepline / outbound / data-enrichment dimension at all.

Quality

88%

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

77%

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 clear, validated four-stage workflow and concrete executable CLI examples. Its main weaknesses are repetitive emphasis that bloats the token budget and a progressive-disclosure model whose referenced job/shared/play files are absent from the bundle.

Suggestions

Bundle the referenced files (jobs/finding.md, jobs/enriching.md, jobs/writing.md, shared/authoring.md, shared/correctness.md, shared/reranking.md, plays/route-fanout.play.ts, plays/shared/rerank.ts, plays/shared/rerank-cli.ts) or remove the dead references so the 'Choose your job' table routes to real material.

Deduplicate the coverage/cost and 'session is the product' guidance — state each once in the Laws and reference it from the lifecycle and cross-cutting sections rather than restating verbatim three or four times.

Trim rhetorical restatement in the Laws and field-notes sections to keep the body lean while preserving the concrete failure-mode examples.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and largely Deepline-specific content Claude would not already know, but it repeats the same rules across sections — 'session is the product' and the coverage/cost-as-decision point each appear in the lifecycle, Laws (2, 9), CLI mechanics, and cross-cutting rules — so it could be tightened; it is not the level-1 'explains concepts Claude knows' case.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands ('deepline tools list <category> --json', the route-fanout run invocations with real --input/--csv/--watch flags) plus a complete worked example walking every stage, matching the level-3 executable-examples anchor rather than the pseudocode level-2.	3 / 3
Workflow Clarity	The EXPLORE → SCORE → EXPLOIT → VERIFY spine is a clearly sequenced multi-step process with explicit validation checkpoints (pilot-before-scale, confirm-before-spend, the dedicated VERIFY stage) and feedback loops, satisfying the level-3 anchor including validation for batch/paid operations.	3 / 3
Progressive Disclosure	Navigation signaling is good (the 'Choose your job' router table, one-level-deep references), but the body references jobs/finding.md, jobs/enriching.md, jobs/writing.md, shared/authoring.md, shared/correctness.md, shared/reranking.md, plays/route-fanout.play.ts, and plays/shared/*.ts — none of which exist in the bundle (only references/debugging.md is present), so the disclosure model is incomplete and the long SKILL.md leans on missing materials; not the level-3 well-split case.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, highly specific description with explicit trigger phrases, named providers, and clear skip/hand-off guidance that minimizes conflict risk. It is somewhat verbose for a description field, but every clause is concrete rather than generic.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'prospecting, list-building, account research, contact enrichment, email/phone/LinkedIn lookup, ICP qualification, lead scoring, outreach copy, CSV-driven row work, and verifying enriched data' — matching the multi-action anchor; not the level-2 single-domain phrasing and far above vague level-1.	3 / 3
Completeness	Explicitly answers both what (the enumerated GTM actions) and when (the 'Triggers on phrases like…' clause plus 'Use this even when the user does not explicitly say GTM'), and adds explicit SKIP guidance, satisfying the level-3 'what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Enumerates natural trigger phrases users would actually say ('enrich this CSV', 'find contacts at these companies', 'build a TAM list', 'waterfall emails for these leads', 'detect job changes', 'is this data accurate', 'write a sequence for') plus named providers (Crustdata, Hunter, Dropleads), giving broad coverage rather than the level-2 partial set.	3 / 3
Distinctiveness Conflict Risk	Clear Deepline/GTM niche with named providers and an explicit hand-off ('SKIP only when the request is a Clay table extraction (use clay-to-deepline)'), making it unlikely to fire for the wrong skill; not the level-2 'could still overlap' case.	3 / 3
	Total	12 / 12 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: 59a5bd2

Reviewed: about 10 hours 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.