What is dym-nuwa-skill-helper-scripts-cli?

A collection of terminal scripts for downloading and cleaning YouTube subtitles, building research summary tables, and producing pass/fail reports. The scripts use Python and standard shell tools, with yt-dlp for subtitle downloads.

Use it to obtain subtitle transcripts, prepare a research table, and run six stated checks that produce machine-readable results and exit codes.

It turns source material and research notes into repeatable files and checks. The pass/fail output can be used in continuous integration, which automatically checks changes in a project.

dym-nuwa-skill-helper-scripts-cli — Skill for Claude Code by Rheinmir

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 Rheinmir/setup --skill dym-nuwa-skill-helper-scripts-cli

Clone the repo

git clone --depth 1 https://github.com/Rheinmir/setup

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli)

Your own site

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-helper-scripts-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,502 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.

Model	Per session	Once invoked
Fable 5.1	$0.00074	$0.02502
Opus 5.5	$0.00030	$0.01001
Sonnet 5.5	$0.00015	$0.00500
Haiku 4.5	$0.00007	$0.00250

Measured yesterday against content hash 73be0ce6c6bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-nuwa-skill-helper-scripts-cli 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 yesterday.

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.

.overstack/doyourmagic/nuwa-skill/skills/dym-nuwa-skill-helper-scripts-cli/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-nuwa-skill-helper-scripts-cli — Bốn script phụ trợ chạy trong terminal

Vì sao dùng: đây là phần duy nhất của repo chạy được ngoài chat — tải/làm sạch phụ đề để nạp tư liệu gốc, tổng hợp bảng khảo cứu cho chốt 1.5, và tự chấm 6 tiêu chí Phase 4. Sinh ra cái gì: file transcript sạch, bảng tóm tắt khảo cứu, báo cáo pass/fail có mã thoát dùng được trong CI.

⚠️ Toàn bộ file này là lệnh SHELL. Lệnh chat nằm ở 02, 03, 04.

Ký hiệu $NUWA dưới đây = thư mục cài skill, ví dụ ~/.claude/skills/nuwa-skill:

export NUWA=~/.claude/skills/nuwa-skill

Phụ thuộc: Python 3 (dùng type hint list[str]/tuple[bool, str] → cần 3.9+, chuẩn nhất là 3.10+), và yt-dlp cho script tải phụ đề. Không có requirements.txt; cả bốn script chỉ dùng thư viện chuẩn (sys, re, pathlib).

`download_subtitles.sh` — tải phụ đề YouTube

bash $NUWA/scripts/download_subtitles.sh <YouTube_URL> [thư_mục_ra]

Thứ tự thử: phụ đề người làm tiếng Trung (zh-Hans,zh-Hant,zh,zh-CN,zh-TW) → phụ đề người làm tiếng Anh (en,en-US,en-GB) → phụ đề tự động (zh-Hans,zh,en). Định dạng SRT, --skip-download nên không tải video.

Mã thoát: 0 khi tìm được phụ đề, 1 khi không có URL hoặc không tìm thấy phụ đề nào (đã kiểm chứng: gọi không tham số → exit 1 kèm dòng hướng dẫn dùng).

Kiểm tra yt-dlp trước:

command -v yt-dlp || brew install yt-dlp   # macOS; hoặc: pipx install yt-dlp

Lỗi đã kiểm chứng trong nhánh 1: nhánh phụ đề tiếng Trung dò file mới bằng find ... -newer /tmp/.ytdlp_marker, mà /tmp/.ytdlp_marker không bao giờ được tạo ra ở bất kỳ đâu trong repo. find lỗi, stderr bị nuốt, biến FOUND rỗng → script luôn rơi xuống nhánh 2 và chạy thêm một lượt yt-dlp tiếng Anh, rồi báo thành công ở nhánh 2 (nhánh này dùng -mmin -1 nên vẫn thấy đúng file .srt tiếng Trung vừa tải). Hệ quả thực tế: file vẫn đúng, chỉ tốn thêm một lần gọi mạng và dòng thông báo sai ngôn ngữ. Kiểm lại bằng chính tên file:

Read the full file on GitHub · 146 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.

yesterday First seen · 146 lines · 74 tokens per session scan A 73be0ce6c6bc

Subscribe to this mod's changes

dym-nuwa-skill-helper-scripts-cli is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 74 tokens to every session and 2,502 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.

Research Testing

dym-nuwa-skill-helper-scripts-cli next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dym-nuwa-skill-helper-scripts-cliRheinmir/setup	Skill	11	20d ago	MIT	A	74	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code