AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Gtm Lead Segmentation

skill-eliasstravik-gtmskills-gtm-lead-segmentation · by eliasstravik

Triggers when a user asks to classify, segment, route, bucket, or qualify individual leads or contacts against personas in a connected GTM context. Not for scoring already-labeled leads, researching people, defining personas, segmenting companies, or managing the context repository.

No reviews yet
0 installs
25 views
0.0% view→install

Install

$ agentstack add skill-eliasstravik-gtmskills-gtm-lead-segmentation

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-eliasstravik-gtmskills-gtm-lead-segmentation)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Gtm Lead Segmentation? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Segment Leads

Recipe

  1. Resolve the GTM context repo and target organization node.
  2. State Using GTM context: — personas visible.
  3. Report a missing prerequisite without classification when that node has no personas.
  4. Normalize only supplied lead facts without enrichment.
  5. Compare each lead with the target node's own freeform persona prose.
  6. Assign exactly one qualified persona label or no-match with cited language and losing alternatives.
  7. Render compact item fields and bulk counts when applicable.
  8. Close No files, git history, or external systems changed.

Details

  • Treat leads as people being classified; never reinterpret a lead as the user, operator, or account.
  • Proceed with zero questions or approval gates when repo, node, lead facts, and visible personas are resolved.
  • Weight responsibilities, authority, and scope over title; use title only as supporting or conflicting evidence.
  • Apply qualification and disqualification statements wherever they appear in a persona; do not expect fixed headings or fields.
  • Use a bare slug for a root persona and / for a suborg persona; omit physical suborgs/ segments.
  • Render the literal item fields Lead, Label, Reasoning, Confidence, Needs review, and Open questions.
  • Restrict Confidence to high, medium, or low; set Needs review to true or false.
  • Base confidence and review only on gaps or conflicts in supplied lead evidence, not on persona maintenance quality.
  • Quote decisive persona wording in Reasoning; name every plausible losing visible label and why it lost.
  • Say no other visible persona alternative exists when there is no plausible loser.
  • For no-match, explain why every plausible visible alternative fails and cite any applicable disqualifier.
  • Open bulk output with Counts by label, Low-confidence count, and Review-needed count; include every lead once.
  • Preserve supplied uncertainty in Open questions without asking the user during a complete run.
  • Never enrich, infer missing employment or authority facts, open supplied links, or silently join facts across leads.
  • Make no repo, filesystem, Git-history, CRM, or external-system change.

Calls

  • Read [references/context.md](references/context.md) before segmentation to resolve the repo and node, enforce node-local visibility, state context, and handle ambiguity or an empty visible set. If unavailable, report that the GTM context contract could not be loaded and stop without classification.
  • Read [references/output.md](references/output.md) before rendering to qualify labels and apply the exact one-off or bulk shape. If unavailable, render the six literal item fields from Details and the required close.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.