Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mardab96/b2b-lead-generation-claude-skills --skill discovery-call-gap-analysisgit clone --depth 1 https://github.com/mardab96/b2b-lead-generation-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/discovery-call-gap-analysis)<a href="https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/discovery-call-gap-analysis"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/discovery-call-gap-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/discovery-call-gap-analysis"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/discovery-call-gap-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01235 |
| Opus 5 | $0.00028 | $0.00617 |
| Sonnet 5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
discovery-call-gap-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Write the questions that are still open, in the order they should be asked next.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 91 lines · 0 tokens per session scan A c1de67079816
discovery-call-gap-analysis is a skill published in the GitHub repository mardab96/b2b-lead-generation-claude-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,235 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…