Systems Lab

Agent skill

qualification

Write AI qualification prompt variables for prospect evaluation.

activeSelf-containedInstructions only610 words

Filed under Calls, demos and discovery.

From Ken-Technology/cold-email-skills · 10 skills · 3 · pushed 2026-08-28

What it does when it runs

Write AI qualification prompt variables for prospect evaluation. Creates audience_description, disqualification_criteria, and optional qualification_criteria. Use when setting up AI qualification for a campaign. Triggers on "write qualification", "qualification prompt", or when dispatched by campaign-planning.

Read from 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 qualification

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/Ken-Technology/cold-email-skills.git /tmp/cold-email-skills
git -C /tmp/cold-email-skills sparse-checkout set "qualification"
mkdir -p ~/.claude/skills/qualification
cp -R "/tmp/cold-email-skills/qualification/." ~/.claude/skills/qualification/

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 Ken-Technology/cold-email-skills/blob/d670f1cbcbe0bda703b630425b013e38309fae4b/qualification/SKILL.md, which is licensed MIT (repository). 610 words, 16 headings.

Qualification Skill

Write the structured variables for AI prospect qualification. These variables feed any qualification step that scores or filters individual prospects against an ICP.

Output Contract

qualification.md must follow a fixed structure so downstream campaign tooling can parse it reliably. Hard rules this skill must honor:

  • Exactly three H2 headings (case-insensitive match): ## Audience Description, ## Qualification Criteria, ## Disqualification Criteria.
  • At least 2 of 3 sections must be populated (non-empty). Fewer is a hard parser error.
  • No other H2 headings in the file - they'd be silently ignored.

Required Context

  1. Read plan.md from the plan folder - Broad ICP definition
  2. Read search-strategy.md from the plan folder - Search filters already applied. Never restate any of these dimensions in the prompt.
  3. Read {workspace}/research.md - Client overview, detailed ICP info, competitors ({workspace} = the client campaign workspace, default ./cold-email/{slug}/ under the current directory)

Core Principles

  • Write short, trust the AI - The qualification AI is smart. Give it a brief, plain-language brief and let it reason. A few high-signal lines beat an exhaustive rulebook. No long enumerations of titles, industries, or product names.
  • Never repeat the search filters - search-strategy.md already bounds the list (headcount, geography, titles, seniority, industries). Do NOT restate any of it - not in the audience description, not as a criterion. If the filter sets a headcount range, the prompt says nothing about headcount. Qualification only catches what the filters can't see.
  • Don't over-qualify - Keep it loose. Qualification is a safety net, not a precision filter. When data is incomplete or ambiguous, qualify.
  • Disqualification over qualification - Prefer audience_description + a few disqualification_criteria only. Add qualification_criteria only when there's a real positive signal worth confirming.
  • Always exclude competitors - The one disqualifier that's always worth including.

See references/qualification-guide.md for detailed guidelines and examples.

Workflow

Step 1: Load Context

  • Read plan.md for the broad ICP
  • Read search-strategy.md for what's already filtered
  • Read client context and research for competitor info and ICP nuances
  • Read references/qualification-guide.md

Step 2: Write Qualification Variables

Keep the whole thing short. A sentence or two per section is plenty - the AI fills in the judgment.

Audience Description (always required):

  • One plain sentence on who we're targeting. 5-20 words.
  • No headcount, geography, title lists, or industries - those live in the filters.

Disqualification Criteria (strongly preferred):

  • A few binary deal-breakers the filters can't see (e.g. competitor, wrong business model).
  • 2-4 lines. Always include competitor exclusion. Don't pad the list.

Qualification Criteria (optional - usually skip):

  • Add only when there's a genuine positive signal worth confirming. Most campaigns don't need it.

Step 3: Write qualification.md

Keep it lean - short lines, no filter dimensions restated:

# Qualification Prompt

## Audience Description
[One plain sentence on who we're targeting. No headcount, geography, titles, or industries.]

## Disqualification Criteria
- [Competitor exclusion]
- [One or two more deal-breakers the filters can't catch, e.g. B2C model, agency/consultancy]

## Qualification Criteria
(Optional - usually skip. Only add a real positive signal worth confirming.)

Output Handling

Workflow mode (plan folder provided):

  1. Write qualification.md to the plan folder root
  2. Confirm: "Qualification prompt saved to {plan_folder}/qualification.md"

Standalone mode:

  1. Return the output inline to the user

Variable Definitions

The three structured fields used for qualification:

  • audience_description - short description of who the target audience is
  • disqualification_criteria - conditions that disqualify a prospect (bullet points)
  • qualification_criteria - optional conditions that qualify a prospect (bullet points)

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 qualification 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.