agentspec: Skill for Claude Code

.claude/skills/meeting-analysis/SKILL.md

meeting-analysis is a skill for Claude Code from luanmorenommaciel/agentspec. It costs 172 tokens per session (1,816 once invoked), scanned A, original, MIT.

A meeting-transcript tool that produces a structured analysis and a short follow-up message for team chat. It identifies decisions, tasks, requirements, blockers, and unstated signals.

In plain words
What is it for?
It helps document meetings and prepare updates for Slack, Teams, Discord, or similar chat channels.
Why use it?
It turns a long transcript into clear outcomes that the team can review and share.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is luanmorenommaciel/agentspec's own configuration. It tells Claude Code how to work on agentspec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentspec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luanmorenommaciel/agentspec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/luanmorenommaciel/agentspec/main/.claude/skills/meeting-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

Made for: Claude Code.

Wrote 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.

agentmods badge for meeting-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/meeting-analysis/github.svg)](https://agentmods.dev/skills/luanmorenommaciel/agentspec/meeting-analysis)
Your own site
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/meeting-analysis"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/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.

agentmods 80×15 button for meeting-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/meeting-analysis"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/meeting-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00172 $0.01816
Opus 5 $0.00086 $0.00908
Sonnet 5 $0.00034 $0.00363
Haiku 4.5 $0.00017 $0.00182

Measured 8d ago against content hash cfd21e03329c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 8d 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.

.claude/skills/meeting-analysis/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Analysis

Turn a meeting transcript into two shareable artifacts:

  1. A formal analysis document, produced by the meeting-analyst agent with its 10-section extraction framework (decisions, action items, requirements, blockers, implicit signals).
  2. A short follow-up message, ready to paste into the team's chat channel.

Both artifacts are team deliverables. Hold them to that bar: formal, professional, content only — nothing about how the analysis was produced.

When to Use

  • The user provides a meeting transcript (file path or pasted text) and wants it analyzed or summarized.
  • The user asks to "analyze this meeting", "write up this meeting", or "summarize this for the team".
  • The user wants a channel-ready post announcing meeting outcomes.

Skip If

  • The user wants a daily standup message — that is the standup-report skill (this skill can feed it; see step 7).
  • The user only wants to store, file, or catalog a transcript, with no analysis requested.

Core Heuristic: TL;DR Inline, Extra Documents Only When Needed

  • The inline TL;DR (1–2 lines) always goes in the follow-up message itself. It is the at-a-glance "what you need to know", without padding.
  • A separate summary document is justified only for very long (3h+) or unusually dense meetings. For everything else, the analysis document is enough. More documents do not add more value.

Process

1. Gather Input and Context

Collect before delegating:

  • Transcript — a file path or pasted text. If pasted, save it to a file first so the analyst agent can read it.
  • Meeting purpose — what the meeting was for and, if the requester attended, what they say it resolved. This outcome lens tells the analyst where to focus.
  • Participants — ask for a roster only if attribution matters for this meeting and the transcript leaves it unclear who said what. Machine transcripts often carry unreliable speaker labels; the requester's account of who attended and who decided beats the transcript. Do not interrogate the user when attribution is irrelevant to the outcomes.
  • Working language — see step 2.

Read the full file on GitHub · 165 lines

Changes

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.

  1. 8d ago First seen · 165 lines · 172 tokens per session scan A cfd21e03329c

Subscribe to this mod's changes

meeting-analysis is a skill published in the GitHub repository luanmorenommaciel/agentspec (246 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 1,816 once invoked, about $0.0009 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 2026-09-01.

Related

Other skills, from other repositories