video-transcript-downloader

内容创作者与自媒体创作者在需要下载视频、提取视频网站字幕时，当需要获取纯文本稿或本地媒体文件请一键调用。自动清洗时间轴与杂音标记，一键下载音视频并生成干净的段落式字幕，大幅提升二创与内容处理效率。

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable SKILL.md body that delegates implementation to a real bundled script and surfaces just the command surface Claude needs. The only gap is the absence of explicit validation/checkpoint steps in the fallback flow.

Dimension	Reasoning	Score
Conciseness	Lean, command-driven body that assumes Claude's competence; no padding or explanation of concepts Claude already knows, and every note (e.g. 'Prefer MP4 container without re-encoding (remux when possible)') earns its place.	5 / 5
Actionability	Copy-paste-ready executable commands covering all common cases (transcript with --timestamps/--keep-brackets, download, audio, subs, formats) plus yt-dlp arg forwarding via '--'.	5 / 5
Workflow Clarity	The transcript fallback sequence (YouTube direct fetch via youtube-transcript-plus, else yt-dlp subtitles then clean) is clearly described, but there are no explicit validation/error-recovery checkpoints, leaving minor gaps.	4 / 5
Progressive Disclosure	Well-organized sections serve as an overview pointing to one real bundle file (./scripts/vtd.js, confirmed present) one level deep; no nested references and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, trigger-rich description that clearly states capabilities and usage conditions for a video-transcript/subtitle skill. It would score higher on specificity but for the second-person imperative, and on trigger terms but for missing synonyms/extensions.

Suggestions

Rephrase '请一键调用' into third person (e.g., '当用户需要…时调用本技能') to remove the second-person voice and recover the specificity penalty.

Add natural synonyms and file extensions (e.g., 字幕/SRT/VTT, .mp4, 逐字稿) to broaden trigger-term coverage.

Trim the marketing filler '大幅提升二创与内容处理效率' to keep the description concise and focused.

Dimension	Reasoning	Score
Specificity	Names several concrete actions (下载视频, 提取字幕, 获取纯文本稿, 清洗时间轴与杂音标记, 生成段落式字幕), but the imperative '请一键调用' is second-person voice, incurring the -1 specificity penalty from an otherwise comprehensive 5.	4 / 5
Completeness	Explicitly answers both what (download/extract/clean/generate subtitle actions) and when ('在需要下载视频、提取视频网站字幕时…当需要获取纯文本稿或本地媒体文件请一键调用'), providing concrete trigger phrases equivalent to a 'Use when' clause.	5 / 5
Trigger Term Quality	Good natural-keyword coverage for the target audience (下载视频, 提取字幕, 纯文本稿, 本地媒体文件, 音视频), but omits synonyms and file extensions (.mp4, .srt), leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (video transcript/subtitle downloading for content creators) with distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anbeime/skill
Path: skills/video-transcript-downloader/video-transcript-downloader/SKILL.md
Commit: d9e888d

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.