short-video-abstract

short-video-abstract is a skill for Claude Code, Codex from Charlesmpc/by2kb. It costs 18 tokens per session (264 once invoked), scanned A, original, MIT.

A short, decision-focused summary of a video based on its transcript. It says what the video is about, what you can learn, and whether deeper notes are worth reading.

In plain words
What is it for?
Use it to turn a transcript into a concise abstract, a few concrete takeaways, and guidance about who should continue watching or studying.
Why use it?
It lets you decide quickly whether a video merits your time without reproducing the full transcript. It warns when the transcript is incomplete or poor quality.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to turn a transcript into a concise abstract, a few concrete takeaways, and guidance about who should continue watching or studying.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/charlesmpc/by2kb/short-abstract
Install

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.

Any agent
npx skills add Charlesmpc/by2kb --skill short-abstract
Clone the repo
git clone --depth 1 https://github.com/Charlesmpc/by2kb

Made for: Claude Code, Codex.

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 short-video-abstract

README.md
[![agentmods](https://agentmods.dev/badge/skills/charlesmpc/by2kb/short-abstract/github.svg)](https://agentmods.dev/skills/charlesmpc/by2kb/short-abstract)
Your own site
<a href="https://agentmods.dev/skills/charlesmpc/by2kb/short-abstract"><img src="https://agentmods.dev/badge/skills/charlesmpc/by2kb/short-abstract/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 short-video-abstract

Your own site · 80×15
<a href="https://agentmods.dev/skills/charlesmpc/by2kb/short-abstract"><img src="https://agentmods.dev/badge/skills/charlesmpc/by2kb/short-abstract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 264 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.
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 $0.00018 $0.00264
Opus 5 $0.00009 $0.00132
Sonnet 5 $0.00004 $0.00053
Haiku 4.5 $0.00002 $0.00026

Measured 10d ago against content hash 59c5cb4fcada, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

short-video-abstract 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.

by2kb/skills/builtin/short-abstract/SKILL.md · 34 lines

What it actually says

Short video abstract

Goal

Help the reader decide in under a minute whether the full study notes or source video are worth their time.

Rules

  1. Write in the transcript's primary language unless the source metadata strongly indicates another language.
  2. Stay grounded in the transcript. Do not add background facts or infer claims that the speaker did not make.
  3. Keep the entire response concise: roughly 120–200 Chinese characters or 80–140 English words.
  4. Do not reproduce the transcript or create a detailed chapter list.
  5. If the transcript is incomplete or low quality, say so in one short warning.

Output

Produce exactly these sections:

  1. # 一句话摘要 / # One-sentence abstract — the topic and central conclusion.
  2. ## 你会得到什么 / ## What you will learn — 2–4 concrete bullets.
  3. ## 是否值得深入 / ## Is it worth going deeper? — who benefits, what prior interest is assumed, and the strongest reason to continue or skip.
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. 10d ago First seen · 34 lines · 18 tokens per session scan A 59c5cb4fcada

Subscribe to this mod's changes

short-video-abstract is a skill published in the GitHub repository Charlesmpc/by2kb (6 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 264 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

obsidian-setup-consultant

Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…

SikJa/hermes-obsidian-setup-consultant · 124 tokens

solomd

Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).

zhitongblog/solomd · 69 tokens

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

youtube-fetcher

Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…

JimmySadek/youtube-fetcher-to-markdown · 74 tokens

larksnap-fetch

A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.

AmbroseX/larksnap · 111 tokens

link-memory

Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.

gowtham0992/link · 0 tokens