Deepline Skills - Deepline

Deepline Skills are the packaged operating instructions for common GTM work. Start with deepline-gtm for prospecting, enrichment, research, and outreach. Use a specialized skill when the job needs a deeper method, such as research planning before paid data work or a human review loop after a pilot. Skills do not replace the Deepline CLI. The skill plans and checks the job. The CLI searches tools, enriches data, executes Plays, and exports results.

Entrypoints

Use deepline-gtm for GTM work and Play authoring. Read command contracts with deepline plays --help. deepline-plays is a deprecated compatibility alias that routes to deepline-gtm. For installation and the pilot/review workflow, see Use Deepline with an agent and Quickstart. If the CLI is missing, paste this into your agent before choosing a skill:

Install and set up the official Deepline CLI globally from npm (package: deepline) by following https://code.deepline.com/INSTALL.md.

deepline-start

Interviews you to find a concrete GTM problem, proposes the right Deepline workflow and skill, then starts it after you confirm the plan. Use it for

Find a valuable GTM task to automate
Turn a manual sales or marketing process into a workflow plan
Choose between the GTM generalist and specialist research or scoring skills

deepline-gtm

The default skill for prospecting, enrichment, research, and outreach jobs. Start here when the request begins with a CSV, a target audience, or a GTM outcome. Use it for

Clean or enrich a CSV
Build account and contact lists
Find and validate LinkedIn URLs
Research and write outreach

deepline-engine

Builds, publishes, and verifies an orchestrator Play as a durable state machine, including a small paid pilot through its real transitions. Use it for

Turn a user-defined state machine into a Deepline Play
Define input and output tables for each state
Reuse workspace Plays or prebuilts for state transformations
Publish the checked engine and verify terminal, failed, invalid, and retried transitions with a bounded paid pilot

deepline-plays-review

Reviews a play and its output with a human feedback loop. Use it after a pilot when rows need approval, corrections, or a repeatable review sheet. Use it for

Review pilot output row by row
Collect corrections in a Google Sheet
Revise checks after failures
Decide whether a play is ready to scale

deepline-research

Plans a research job before paid data work. It maps public and private sources, designs source-specific queries, finds material datasets, and recommends the Deepline route. Use it for

Research a market or buyer problem
Find public datasets and source coverage
Design queries before provider execution
Estimate research cost before approval

deepline-ads-audiences

Builds, enriches, audits, and uploads paid advertising audiences for Google, Meta, and LinkedIn. It is for audience matching, not cold outbound. Use it for

Increase customer-list match coverage
Build suppression audiences
Audit hashing and normalization
Upload and compare Google or Meta audiences

deepline-analytics

Answers governed RevOps and GTM questions from a configured warehouse or semantic layer, with Snowflake as the primary analytics surface. Use it for

Answer funnel and pipeline questions
Compare periods using governed metrics
Find the right semantic object
Use raw SQL only when the semantic layer cannot answer

deepline-scoring

Finds observable signals that distinguish closed-won from closed-lost accounts, then turns them into an evidence-backed scoring model and prospect list. Use it for

Discover ICP signals from won and lost accounts
Analyze jobs, websites, and technology evidence
Build an account scoring model
Return net-new prospects that fit the discovered pattern

deepline-crm-cleaning

Audit CRM data, prepare evidence-backed repairs, and measure unresolved work. Covers duplicates, company domains, enrichment, employment changes, and typed entity relationships. Use it for

Find duplicates and assess prevention gaps
Repair invalid company URLs and missing fields
Separate legal entities, brands, business units, and account hierarchies
Measure quality, evidence coverage, and unresolved records

Recipes included with deepline-gtm

The router loads these focused recipes when the request matches. You do not need to invoke them separately.

Recipe	Use it when
Account Org Chart Builder	Build an interactive account org chart, leadership map, buying committee, or manager/report neighborhood around a person. Use for decision makers, reporting-line candidates, stakeholder mapping, and warm intro paths. Skip standalone email lookup and unrelated cross-company prospecting.
Build a TAM List	Build a Total Addressable Market list: size the audience, source companies from ICP filters, then find contacts at those companies at scale.
Find Qualified Titles	The recipe finds people whose actual titles match a plain-English ICP across the companies in a supplied list. It starts with each company’s title roster rather than guessed keywords. The roster is free. Matching the ICP uses one small AI call per company. Any contact spend occurs only at the end.
Portfolio/VC Prospecting	Find companies backed by a specific investor or accelerator, then find contacts and build personalized outbound.
Small Business Prospecting	Use this for local SMB discovery like dentists, plumbers, med spas, agencies, or nearby storefronts.

What is not in this list

deepline-feedback is a retired skill. The CLI documents feedback and session sharing through deepline feedback send --help and deepline sessions send --help. It still ships so existing prompts and installed CLIs keep working. deepline-quickstart provides a guided demo. Deepline still includes this skill. The recommended daily workflow above does not include this skill.

​Entrypoints

​deepline-start

​deepline-gtm

​deepline-engine

​deepline-plays-review

​deepline-research

​deepline-ads-audiences

​deepline-analytics

​deepline-scoring

​deepline-crm-cleaning

​Recipes included with deepline-gtm

​What is not in this list