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 Morningstar202604/awesome-skillkit --skill meeting-notesgit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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/morningstar202604/awesome-skillkit/meeting-notes)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/meeting-notes"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/meeting-notes/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/morningstar202604/awesome-skillkit/meeting-notes"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/meeting-notes.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 | $0.00089 | $0.00899 |
| Opus 5 | $0.00044 | $0.00449 |
| Sonnet 5 | $0.00018 | $0.00180 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
meeting-notes 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Notes (transcript → minutes)
Machine-first rule: never invent an owner, date, or decision. If the
transcript does not state it, mark it <未明确> and list it in open questions.
Inputs
| Input | Required | Default | Notes |
|---|---|---|---|
| transcript / raw notes | yes | — | pasted text; speaker labels help but optional |
| meeting meta | no | — | date, attendees, purpose |
| audience | no | 全体相关人 | shapes how blunt the summary is |
If the transcript is missing, ask ONCE:
请粘贴会议文字记录（语音转写稿即可）。可选告知：日期、参会人、 会议目标，以及纪要发给谁。
Workflow
Step 1: Segment before summarizing
Split the transcript chronologically into议题块 (one block per topic shift), numbering them T1…Tn with a one-line topic label each. Expected: block count matches discussion flow; merge fragments of the same topic.
Step 2: Extract decisions vs discussions
For each block classify every exchange as:
- 决议：有明确结论且无人反对（记录原话关键句作为证据）
- 讨论：有交换但无结论 → 归入 open questions
- 行动：有人说"我来/你去/下周前" → 进入 Step 3 Expected: zero unclassified exchanges; when ambiguous, quote the sentence in open questions instead of guessing intent.
Step 3: Action table (the deliverable's core)
| 行动项 | Owner | 截止 | 来源议题 | 状态 |
|---|
Rules: Owner 必须是 transcript 里点名的人，否则写 <待指派>;
deadline 缺失写 <待定>；每行必须能在 T 编号中找到出处。
Step 4: Compose minutes in fixed structure
# 会议纪要 YYYY-MM-DD <主题>
参会：<名单或<未明确>>
## 一页结论
<3–5 条最重要的决议，每条一行>
## 决议明细
<按 T 编号，决议+证据原话>
## 行动项
<Step 3 表格>
## 待明确问题
<无主/无结论事项，含需要谁来拍板>
Step 5: Consistency check before delivery
Verify: every 决议 has evidence quote; every action has owner+deadline or an explicit placeholder; total length ≤ 1/3 of transcript. Fix violations by returning to Steps 2–3, not by deleting items.
Failure handling
| Symptom | Likely cause | Action |
|---|---|---|
| speakers unlabeled in transcript | raw ASR dump | infer roles from content but mark <推断> on uncertain attributions |
| two conflicting "decisions" same topic | later reversal missed | keep both with timestamps, flag in open questions |
| transcript truncated mid-topic | input incomplete | note cutoff point Tn explicitly at the end |
| user asks to soften a decision | political editing | deliver faithful version; edits are theirs to make |
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.
- 10d ago First seen · 96 lines · 89 tokens per session scan A 14c3f89014e3
meeting-notes is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (1 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 899 once invoked, about $0.0004 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
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.