Borrowing it
Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-web-YoutubeSummarizer/SKILL.mdgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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/gabrielondelphi/claude-tools-for-delphi/light-web-youtubesummarizer)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-web-youtubesummarizer"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-youtubesummarizer/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/gabrielondelphi/claude-tools-for-delphi/light-web-youtubesummarizer"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-youtubesummarizer.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 | $0.00134 | $0.01828 |
| Opus 5 | $0.00067 | $0.00914 |
| Sonnet 5 | $0.00027 | $0.00366 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
light-web-YoutubeSummarizer 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-web-YoutubeSummarizer — Video → the short version
Thin launcher. Resolve the transcript path(s), ask where to save, launch the light-web-YoutubeSummarizer agent once per file, relay what comes back. You never clean or summarize yourself.
Step 0 — URL → transcript
If $args holds a YouTube link (youtube.com/watch?v=, youtu.be/, /shorts/) or a bare 11-char id, get a transcript first:
python "c:\Users\<you>\.claude\skills\light-web-YoutubeSummarizer\scripts\extract_transcript.py" "<URL-or-id>" ["<output dir>"]
- Last stdout line = the transcript path. Fallback: glob the output dir for the newest
*(transcript).txt. - Default output dir is
C:\AI\Claude Code\Transcripts\. ffmpeg is not used and not needed. Non-zero exit prints a specific reason on stderr — no English captions, or yt-dlp itself failed. Relay that reason and stop; do not retry blindly. - Filenames may hold full-width
？｜(yt-dlp sanitises?/|). Read/Write/Agent handle them; only a picky PowerShell step needs an ASCII copy.
.url shortcuts count as links. A browser-saved .url is an INI file whose URL= line holds the address. Read it, take that value, extract into the folder the .url lives in — that is where he expects the transcript and summary, not the default folder.
Never re-download. Before extracting, check the target folder for an existing *(transcript).txt and use it. Re-extract only if he asks for a fresh one.
Several URLs → run once per URL, collect the paths.
Step 1 — Resolve the input
Build the transcript list from $args (extracted paths count as explicit inputs):
- Explicit
.txtpath(s) → use as-is. - A folder → Glob
*.txtand*.url; each.urlgoes back through Step 0. A folder holding only a.urlis the normal case after saving a link from the browser — it is not empty, don't report it as such. Skip files ending in(summary). If bothX.txtandX (cleaned).txtexist, keep only the cleaned one. - A folder holding subfolders — the normal shape of
c:\AI\Claude Code\Transcripts\, one folder per video. Glob*/*.txtand*/*.urlas well, one level down. A subfolder that already holds a*(summary).mdis done: leave it out unless he named it. Never report the parent as empty because its top level has no.txt. - Nothing → ask for the path, defaulting to
c:\AI\Claude Code\Transcripts\. If exactly one un-summarized video turns up there (top level or one level down), offer it.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +25 lines · +25 tokens per session 2ce16c80c2f1
- 7d ago Changed · +2 lines b1f723383a43
- 11d ago First seen · 66 lines · 109 tokens per session scan A c43ae794c2ba
light-web-YoutubeSummarizer is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 4d ago), licensed MPL-2.0. It adds 134 tokens to every session and 1,828 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.