agentleFS
narenaryannarenaryan/agent-skills/skills/sales/sales-discovery-qualification/SKILL.md

sales-discovery-qualification

Skill0 starsChanged 41 days agoMITView on GitHub

Use when preparing complex B2B discovery, buyer evidence is missing, or a previously qualified deal changes scope, funding authority, stakeholders, or approval requirements.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test account assumptions before pitching.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sales Discovery and Qualification

Qualification is decision-specific. Historical truth can outlive applicability.

Establish evidence

Record claim, speaker, date, artifact, scope, and status: confirmed, inferred, unknown, contradicted, or needs-revalidation. Preserve history; CRM edits are not buyer evidence.

QuestionEvidence
Why change?Incident, affected workflow, consequence, baseline
Why this solution?Buyer-owned acceptance criteria and required proof
Who decides?Authority for this expenditure, affected users, approval route
Why now?Buyer deadline, delay cost, competing priorities

Test account assumptions before pitching. Use SPIN flexibly: situation, problem, consequences, desired improvement. Quantify frequency, volume, unit cost, and period; label estimates and owners. Separate cash, capacity, and speculative revenue without double-counting. One person’s estimate is not organizational agreement.

Revalidate selectively

Compare the current decision with the evidence's scope. This matrix is synthesis, not validated scoring.

ChangeReopen affected claims
Larger spend, new business unit, tighter spending controlsFunding authority and approval conditions
Advocate changes role or leavesCurrent influence, internal advocacy, stakeholder access
New requirements or deployment scopeAcceptance criteria, proof coverage, review prerequisites
New approval step or missed milestoneDependencies, owners, achievable outcome date

Mark affected claims needs-revalidation, not automatically contradicted; retain unaffected observations. Ask the buyer owner what remains applicable and resolves the gap. Reassess dependent dates using mutual action plans.

Example: $20,000 pilot approval and passing sandbox tests do not establish authority or production clearance for a $200,000 cross-unit rollout. Preserve the pilot results; reopen funding and production-review claims. A new stakeholder alone does not invalidate every technical finding.

Recommend advance, investigate, defer, or decline. Advancement requires a useful buyer-agreed action, owner, and date; deferral requires a reopening condition. Unknowns are investigation targets, not invented win probabilities.

Primary sources, worked scenario, and limits.

Pitfalls

  • Elapsed days alone establish neither expiry nor continued validity; honor explicit approval conditions.
  • Enthusiasm and meetings do not prove buying progress; doing nothing can be rational.
  • Revalidation is not permission to bypass contacts, contact buyers, update CRM, or bind either party.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.