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.
94
94%
Does it follow best practices?
Impact
Pending
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 exemplary skill description that excels across all dimensions. It provides specific technical capabilities, comprehensive natural trigger terms including casual phrases like 'tl;dw', explicit 'Use this skill whenever...' guidance, and a clearly defined niche around video summarization that distinguishes it from related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Downloads via yt-dlp', 'extracts transcript (YouTube captions or Whisper)', 'pulls scene-detected keyframes', 'produces a multimodal summary with clickable timestamped YouTube links'. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both what (summarize video via audio/visual analysis, download, transcript extraction, keyframes, multimodal summary) AND when with explicit 'Use this skill whenever...' clause containing multiple trigger scenarios and example phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'summarize a YouTube video', 'digest a talk or tutorial', 'get notes from a video', 'extract key points', 'tl;dw', 'summarize this video', 'what's in this video', 'YouTube URL'. Includes both formal and casual phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on video summarization with distinct triggers like 'YouTube video', 'tl;dw', 'YouTube URL', and specific tool mentions (yt-dlp, Whisper). Unlikely to conflict with document or audio-only 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-structured skill with excellent workflow clarity and actionability. The multi-step pipeline is clearly sequenced with explicit validation gates and parallel execution guidance. Minor verbosity in the pipeline overview and some explanatory text could be trimmed, but overall the skill effectively teaches Claude a complex video processing workflow.
Suggestions
Remove the Pipeline Overview section since it duplicates the detailed steps below, or condense it to a single-line summary
Trim explanatory phrases like 'The video URL is needed for timestamp links' that Claude can infer from context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundant explanations (e.g., explaining what scene detection does, describing YouTube deep link format that Claude knows). The pipeline overview duplicates information found in detailed steps below. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, concrete code examples for locating scripts, specific flag tables, and copy-paste ready commands for each step. The markdown output template is complete and actionable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit validation checkpoints (Step 0 dependency check with 'do NOT proceed' gate), clear sequencing, parallel execution guidance for Steps 2&3, error recovery instructions (re-run failed subagents), and conditional branching for short vs long videos. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, appropriately references external file (SUBAGENT-PROMPT.md) for detailed subagent template, and organizes content into logical sections. The standalone installation section is appropriately placed at the end. | 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