catalan-adobe/video-digest
Summarize any video by analyzing both audio and visuals. Downloads via yt-dlp, extracts transcript (YouTube captions or Whisper), pulls scene-detected keyframes, and produces a multimodal summary with clickable timestamped YouTube links. Use this skill whenever the user wants to summarize a YouTube video, digest a talk or tutorial, get notes from a video, extract key points from a recording, or says things like "tl;dw", "summarize this video", "what's in this video", or pastes a YouTube URL and asks for a summary. Also triggers for non-YouTube URLs that yt-dlp supports.
74
93%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific concrete actions and tools, includes a comprehensive set of natural trigger terms and user phrases, explicitly separates 'what' from 'when', and occupies a clearly distinct niche. The description is thorough without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: downloads via yt-dlp, extracts transcript (YouTube captions or Whisper), pulls scene-detected keyframes, produces multimodal summary with clickable timestamped YouTube links. | 3 / 3 |
Completeness | Clearly answers both 'what' (downloads, extracts transcript, pulls keyframes, produces multimodal summary) and 'when' with an explicit 'Use this skill whenever...' clause listing multiple trigger scenarios and exact user phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user terms: 'summarize a YouTube video', 'digest a talk or tutorial', 'get notes from a video', 'extract key points from a recording', 'tl;dw', 'summarize this video', 'what's in this video', 'pastes a YouTube URL'. These are highly natural phrases users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on video summarization with specific tools (yt-dlp, Whisper, scene-detected keyframes). The combination of video-specific triggers and toolchain makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that provides a complete, actionable pipeline for video summarization. The workflow is clearly sequenced with appropriate validation checkpoints, parallel execution guidance, and conditional logic for different video lengths. Minor verbosity in some sections (markdown template, asset preparation details) prevents a perfect conciseness score, but overall the content is well-organized and highly executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content earns its place — specific commands, concrete formats, and decision logic. However, some sections are slightly verbose (e.g., explaining what scene detection does, the contact sheet assembly details, the full markdown template could be more compact). It generally respects Claude's intelligence but could be tightened in places. | 2 / 3 |
Actionability | Highly actionable throughout: every step has concrete bash commands, specific file paths, exact output formats, and copy-paste ready code. The markdown template, YouTube deep link format, flags table, and script commands are all fully specified and executable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing, explicit validation checkpoints (Step 0 dependency check with stop-and-fix loop, re-run deps after install, check frame count and suggest threshold adjustment, re-run failed subagents), parallel execution guidance for Steps 2&3, and conditional branching for short vs long videos. Feedback loops are present for error recovery. | 3 / 3 |
Progressive Disclosure | The SKILL.md serves as a clear overview with well-structured sections. It references `references/SUBAGENT-PROMPT.md` for the subagent template and `scripts/video-digest.sh` for the helper script, keeping the main file focused on orchestration logic. The pipeline overview at the top provides quick orientation before diving into details. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents