agentleFS
nthnclrknthnclrk/enablement-skills/skills/discovery-and-demo-structure/SKILL.md

discovery-and-demo-structure

Skill14 starsChanged 8 months agoMITView on GitHub

Design an adaptive discovery guide and outcome-led demo flow for a defined buyer, segment, stage, and meeting type. Use to create or improve question paths, stakeholder coverage, demo sequencing, and next-step structure. Use discovery-rubric-auditor to score completed discovery, call-review-coach to coach one recorded call, and talk-track-builder for a standalone pitch or spoken message.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    If there is no credible decision this meeting can produce, propose one before you build the path.

    line 16
  2. Distinctive:

    Ask only for what changes the flow:

    line 22
  3. Distinctive:

    Do not invent buyer commitments, metrics, or product claims.

    line 29
  4. Distinctive:

    Read references/discovery-demo-framework.md for topic patterns, demo-gating rules, and meeting modes.

    line 33
  5. Distinctive:

    Every question and demo block serves the named decision.

    line 68
  6. Distinctive:

    No invented capability, proof, or commitment.

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Discovery and demo structure

Design a conversation that helps the seller understand the buyer's problem and demonstrate only what the buyer needs to evaluate.

This skill designs the meeting architecture. For spoken lines inside an existing structure, use talk-track-builder.

Gated. "You said late handoffs hit the Friday ship. If I show the missed-window alert and the owner assignment, does that test the thing you would actually need to believe?"

Dump. "Let me start with the platform overview, then walk you through all six modules."

If there is no credible decision this meeting can produce, propose one before you build the path.

Inputs

Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.

Ask only for what changes the flow:

  1. Meeting type: discovery, demo, or combined
  2. Who is in the room, time available, and the decision this meeting is for
  3. What is already known versus hypothesized
  4. Approved capabilities, proof, and demo-environment limits

Do not invent buyer commitments, metrics, or product claims.

Supporting material

Read references/discovery-demo-framework.md for topic patterns, demo-gating rules, and meeting modes. Skip it if you are only tightening an existing guide.

Procedure

  1. Name the decision. What the buyer should be able to decide next, and what the seller must learn or prove. Done when that sentence is specific.
  2. Separate knowns from hypotheses. Each consequential unknown becomes a question, not a fact in the script.
  3. Build an adaptive path. For each topic: why it matters, an opening, what to listen for, if/then branches. Prioritize. This is not a list that must be completed in order.
  4. Plan stakeholder coverage. What each role can confirm, what needs someone else, where views may conflict.
  5. Gate the demo. Map each block to a confirmed outcome, criterion, or risk. For an exploratory buyer who cannot yet articulate the problem, offer a short, clearly framed example to test relevance, then return to discovery. Use verified capabilities and specify when to stop or change direction.
  6. Write the transition. Restate what you heard. Ask permission to show the matching path.
  7. Design the close. Recap confirmed outcomes and open questions. Ask for a next step. Do not write a proposed action as if the buyer already agreed.
  8. Name the few fields to capture after the call.

For scoring completed discovery use discovery-rubric-auditor. For one recorded call use call-review-coach.

What to return

  • Meeting frame: type, audience, knowns, hypotheses, decision, time
  • Discovery path with listen-fors and branches
  • Stakeholder coverage
  • Demo map with the buyer statement that unlocks each block
  • Close plan
  • Capture plan that preserves unknowns as unknown

Discovery-only, demo-only, or combined. Do not ship all three unless asked.

Quality bar

  • Every question and demo block serves the named decision.
  • Each demo block has a reason to show it, a question to test relevance, and a stop or transition condition.
  • Hypotheses stay labeled until the buyer confirms them.
  • The guide is usable live, not a 40-question checklist.
  • No invented capability, proof, or commitment.

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.