mcpField
G
gtm-qualify-prospects

gtm-qualify-prospects

github.com/eliasstravikMarketing & growth22326 installsUpdated 2w ago
Repository

About gtm-qualify-prospects

gtm-qualify-prospects is a skill for assessing supplied people against personas and companies against ICPs. It returns evidence-based fit scores without writing results to the workspace.

Key features

  1. 01Score people against personas
  2. 02Score companies against ICPs
  3. 03Use evidence and confidence bands
  4. 04Keep fit checks separate by entity type
  5. 05Write no files or workspace data

Use cases

  1. 01Assess whether a person matches a target persona
  2. 02Evaluate a company against an ICP
  3. 03Compare supplied prospects using fit scores

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/eliasstravik/gtm-skills --skill gtm-qualify-prospects

After installing, type/gtm-qualify-prospectsin Claude Code to confirm it loaded.

Bundled filesreferences/interactions.md

Details

From the project README

GTM Qualify Prospects

Trigger

Apply this skill when a request asks how well supplied people or companies fit the workspace's personas or ICPs.

Scope

Fit checks only: people against personas, companies against ICPs, never blended in one score; nothing is written to the workspace or anywhere else.

Inputs

The people or companies as given; the workspace's personas/*/PERSONA.md and icps/*/ICP.md; free public pages such as a company's own site; paid data tools the host exposes, only after the gate in step 3.

Roles

The user supplies the entities and approves any paid lookup; the agent scores.

Procedure

The first gtm skill used in a conversation checks once for a newer release, as updates says. Talk by the six rules in interaction; reproduce the dialogues.

  1. Sort the entities into people and companies; pick the persona or ICP to score against, asking with options when several fit and the request names none.
  2. Gather evidence from the request and free public pages.
  3. When a paid tool would fill missing criteria, ask once: what it fills, how many calls, and the provider's published price, as options with the lookup first and "score with what I have" second.
  4. For each entity, write the reasoning first, commit to a band, then choose the score inside it: Excellent 85–100, Good 70–84, Fair 50–69, Not a fit 0–49. A matched disqualifier is Not a fit at 0. Missing evidence lowers confidence (High, Medium, Low), never the band.
  5. One entity: labelled lines Verdict, Score, Confidence, Scored against, Reasoning. Several: one table per mode (Person or Company, Verdict, Score, Confidence), then one reasoning line per entity, then the footer Fit only; recurring scoring belongs in a gtm-workflow.

Outputs

The verdicts in the reply; no files.

Exceptions

Requires the gtm-workspace skill installed alongside this one; when ../gtm-workspace/SKILL.md is missing, say: install it the same way this skill was installed, with npx skills add eliasstravik/gtm-skills -s gtm-workspace -y (add -g when this skill lives in the global skills directory), then retry. Asked to save results: say fit checks save nothing and offer a workflow. No persona or ICP exists for a mode: say so and offer to create one.

QC

  • Every person is scored only against a persona and every company only against an ICP.
  • Every score sits inside its stated band; every disqualifier match is 0.
  • No file changed.

References

interactions; from gtm-workspace: interaction, contract, company data, person data.

Comments

Markdown supported