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 Netcracker/qubership-ai-packages --skill meeting-analysisgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/meeting-analysis)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/meeting-analysis"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/meeting-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/netcracker/qubership-ai-packages/meeting-analysis"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/meeting-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 | $0.00140 | $0.02938 |
| Opus 5 | $0.00070 | $0.01469 |
| Sonnet 5 | $0.00028 | $0.00588 |
| Haiku 4.5 | $0.00014 | $0.00294 |
Grade A, and why
meeting-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 11d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting analysis
Turn a meeting transcript into a dense, verifiable report. Not a play-by-play retelling, but a multi-axis breakdown: you pass over the text several times, each time through a single lens, and pull out only what that lens is about.
Output language
Write the entire report in the same language as the transcript. A German transcript gets a German report, a Japanese transcript a Japanese report — match the transcript, not this skill's language and not the language the request was written in. The reader works in the source language, so switching it would force them to translate back. Headings, axis names, and prose all stay in the transcript's language; quotes are verbatim regardless.
Why this, not "summarize in order"
After a conversation a person holds the whole context at once — they see the meeting from every side simultaneously. A linear summary cannot reproduce that: it follows the chronology and smears the meaning. One narrow pass per axis catches what a broad retelling blurs. An argument stretched across 40 minutes with back-and-forth collapses into one clear fork; tasks scattered through the whole conversation converge into a single list. Several targeted passes almost always beat one wide one.
Input
The skill takes either a single transcript file or a folder. If a folder holds several transcript files, it is almost always one meeting or a close span of time split into parts (several back-to-back calls, or one meeting across several files). In that case:
- Load all the files and analyze them as one large transcript under the same rules — one report, one set of axes, deduplication across the whole. Do not produce a separate breakdown per file and do not split the report by file.
- The only difference is in the verification apparatus: a timecode must point to both the source file and the minute, or the reference is ambiguous (see below). Give each file a short label and cite it by that label.
If the folder clearly holds something other than a transcript (screenshots, notes, attachments), use it as context, but the conversation stays the axis of the report.
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.
- 11d ago First seen · 267 lines · 140 tokens per session scan A 7bf4047b022c
meeting-analysis is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 140 tokens to every session and 2,938 once invoked, about $0.0007 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…