Systems Lab

Agent skill

gtm-qualify-prospects

Triggers when a user asks whether a named person or company, or a pasted list of them, fits the GTM workspace's personas or ICPs, with phrasings like "is this a fit", "check quillhr.com against our ICP", "score these leads", or "qualify this list".

activeSelf-containedInstructions only398 words

Filed under Prospecting and list building.

From eliasstravik/gtm-skills · 7 skill entries · 13 · pushed 2026-09-21

What it does when it runs

Triggers when a user asks whether a named person or company, or a pasted list of them, fits the GTM workspace's personas or ICPs, with phrasings like "is this a fit", "check quillhr.com against our ICP", "score these leads", or "qualify this list". Owns in-conversation fit checks of supplied people or companies and writes nothing. Not for creating or editing ICPs or personas (gtm-icp, gtm-persona), the workspace itself (gtm-workspace), or recurring scoring of lists, which is a saved gtm-workflow.

Automated analysis of the skill and the 1 file bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about gtm-qualify-prospects

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/eliasstravik/gtm-skills.git /tmp/gtm-skills
git -C /tmp/gtm-skills sparse-checkout set "skills/gtm-qualify-prospects"
mkdir -p ~/.claude/skills/gtm-qualify-prospects
cp -R "/tmp/gtm-skills/skills/gtm-qualify-prospects/." ~/.claude/skills/gtm-qualify-prospects/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from eliasstravik/gtm-skills/blob/2f986ae36d384bded1df28ba51fee25a672fdf4d/skills/gtm-qualify-prospects/SKILL.md, which is licensed MIT (repository). 398 words, 10 headings.

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

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.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what gtm-qualify-prospects does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.