# Discovery Call Gap Analysis > Reads a discovery call transcript and finds what was never asked: budget, authority, timing, the incumbent, and the real cost of doing nothing. Use when deals stall after good calls, or when a forecast keeps being wrong in the same direction. - **Type:** Skill - **Install:** `agentstack add skill-mardab96-b2b-lead-generation-claude-skills-discovery-call-gap-analysis` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [mardab96](https://agentstack.voostack.com/s/mardab96) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [mardab96](https://github.com/mardab96) - **Source:** https://github.com/mardab96/b2b-lead-generation-claude-skills/tree/main/discovery-call-gap-analysis ## Install ```sh agentstack add skill-mardab96-b2b-lead-generation-claude-skills-discovery-call-gap-analysis ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Discovery Call Gap Analysis ## Use this skill when Calls feel good and deals do not close. A discovery call has a small number of things it must establish, and a pleasant conversation can miss all of them while feeling productive. The gap is usually invisible in the moment and obvious in the transcript, which is why this is worth doing on calls that went well rather than only on ones that went badly. Run it on a single call to fix a deal. Run it across five calls from the same person to fix a habit. ## Required input - The transcript. Gong, Fathom, Otter, Zoom, or a rough paste. - What you sell and the typical deal size. - Where the deal is now, if the call has already happened some time ago. Useful: - who was on the call and their roles - whether this was first contact or a later conversation - what the agreed next step was - how similar deals have gone ## Analysis workflow 1. Map who spoke and for how long. A discovery call where the seller speaks most of the time did not discover much, whatever else it contained. Treat the ratio as a direction rather than a threshold: the vendors who publish research on this from large call corpora put the healthy band well below half seller talk, and their numbers are theirs, not measured here. What matters for one call is whether the buyer did most of the talking. 2. Check whether the current cost of the problem was ever established in their terms. Not whether the problem was named, but whether anyone quantified what it costs them to keep living with it. Without that, there is no case for change and no urgency later. 3. Check for a real timeline and what creates it. "Sometime this quarter" is not a timeline. Something has to force the date, and if nothing does, the deal will slip indefinitely regardless of enthusiasm. 4. Check authority without the interrogation. Look for whether anyone established how a decision like this gets made there, who else is involved, and what the approval path looks like. 5. Check the incumbent. What are they doing today, what does it cost, and what would have to happen to that arrangement. Deals are lost to the status quo far more often than to competitors. 6. Find the moment a buying signal appeared and was not followed. Transcripts almost always contain one: a question about implementation, a mention of a deadline, a reference to a colleague who cares. These are where the deal was available and the conversation moved on. 7. Check whether anyone other than the person on the call was ever mentioned as needing to be involved. A deal that lives with one contact is one holiday away from silence, and that is visible in the transcript long before it becomes a problem. 8. Write the questions that are still open, in the order they should be asked next. ## Decision rules - A seller-dominant call is a finding on its own. Do not attach a hard percentage to it here: the right band varies with call type, deal complexity and length, and a borrowed threshold applied to a demo-heavy call generates false alarms. Report the ratio, say who dominated, and let the manager judge. - An unquantified problem is the most common gap and the most expensive one. Prioritise it over the others. - Do not score the call against a framework for its own sake. The output is which questions are still open, not a grade. - If the economic buyer was absent and nobody discussed how to reach them, that is the top finding regardless of how the call felt. - Across multiple calls, look for the gap that repeats. One missed question is a call; the same missed question five times is coaching. ## Output format ### Call shape Talk ratio, call length, who was present, and what the agreed next step was. State the ratio as an observation, not a grade. ### What was established | Area | Established | Evidence from the transcript | |---|---|---| | Cost of the current problem | | | | Timeline and what forces it | | | | Decision path and who else | | | | Incumbent or current approach | | | | Success criteria | | | ### Missed signals Quote the moment, say what it opened, say what should have followed. ### Still open The questions to ask next, ordered, with the one that matters most first. ### If this is a pattern Only when several calls were supplied: the gap that repeats and what it is costing. ## Practical example A 38-minute first call. Talk ratio 71% seller. The prospect described a manual reporting process in detail and said, at minute 22, "our finance director has been asking about this for a while." Everything except the incumbent was left unestablished. Nobody asked what the manual process costs in hours or money, nobody asked what timeline the finance director has in mind, and the finance director was never mentioned again in the remaining sixteen minutes. The top finding is that the buying signal at minute 22 named the economic buyer and their motivation in one sentence, and the conversation moved past it. The next call has three open questions, and the first is about the finance director. ## Guardrails - Do not evaluate the salesperson as a person. The output is about the call, and a transcript read as a performance review will stop being shared. - Do not fabricate what was said. Quote or mark as absent. - Do not treat a framework as the goal. Deals close because the buyer has a reason and a date, not because five letters were covered. - Do not analyse a recording that was made without consent, and check the jurisdiction before assuming consent exists. - Do not draw a pattern from one call. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [mardab96](https://github.com/mardab96) - **Source:** [mardab96/b2b-lead-generation-claude-skills](https://github.com/mardab96/b2b-lead-generation-claude-skills) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-mardab96-b2b-lead-generation-claude-skills-discovery-call-gap-analysis - Seller: https://agentstack.voostack.com/s/mardab96 - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.