websets-sourcing

Use when users ask to create, preview, inspect, enrich, import, refresh, monitor, export, or reuse persistent Exa Websets for GTM sourcing.

Jump to install

Repository: julep-ai/mem-plugins
Last source activity: May 11, 2026 at 04:03
Detected SKILL.md language: English
Stars: 1
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/julep-ai/mem-plugins --skill websets-sourcing

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

Websets Sourcing

Use Exa Websets as the persistent sourcing and enrichment layer for GTM Agent. Production Websets sourcing requires a configured Exa API key; if auth is missing, stop and output setup steps plus the Webset spec.

Loop

Start with Memory Store checkin; use selected canonical brief context if provided by the main GTM agent, otherwise call list-briefs and select 0-3 relevant briefs; then recall campaign, ICP, exclusions, seed accounts, suppressions, and prior Webset IDs.

Use Websets when a list should persist, refresh, enrich, export, import, or be reused across campaigns.

Preview before broad creation when available.

Separate criteria from enrichments: criteria filter inclusion; enrichments add action fields.

Pick entity type: company, person, article, research_paper, or custom.

Use imports for seed accounts, customers, competitors, suppressions, or CSV scope.

Add only enrichments that improve GTM action: buyer/persona, person name, title, work email or email status, LinkedIn/profile URL, identity confidence, high-intent signal, source URL, customer-story/persona pattern, offer angle, proof path, next action, learning intent, channel identity, confidence, and exclusion risk.

Track async IDs and status; return any brief-impact candidate to the main GTM agent. Record approved Webset/search/enrichment/import IDs to Memory Store only when this skill is the main agent for the task.

Websets MCP is separate from Exa Monitors. For monitors, use ../gtm-agent/references/monitors.md and record returned monitor IDs after approval.

Output

Return: webset read, spec, status, quality notes, Memory Store mapping, and next action.

Rules

Do not create broad reusable Websets without approval. Do not commit secrets. Do not delete Websets unless explicitly asked. Do not mark rows draft-ready without complete planner fields or high-intent signal evidence. Do not create briefs for Webset rows, previews, enrichments, or async events; use Webset IDs, campaign artifacts, records, and a main-agent brief delta only when repeated results change future operating policy.