summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
83
Quality
82%
Does it follow best practices?
Impact
87%
2.63xAverage score across 3 eval scenarios
Evaluation results
79%
44%Podcast Episode Transcript Helper
YouTube transcript extraction
Uses summarize CLI
100%
100%
youtube auto flag
0%
100%
extract-only flag
0%
100%
Default model used
0%
100%
GEMINI_API_KEY referenced
100%
100%
Large transcript summary first
0%
0%
Prompt for section/time range
0%
40%
Transcript written to file
100%
100%
Without context: $0.3889 · 1m 57s · 23 turns · 24 in / 6,226 out tokens
With context: $0.2512 · 1m 1s · 15 turns · 177 in / 3,357 out tokens
100%
68%Daily Research Digest Automation
URL batch summarization pipeline
Uses summarize CLI
0%
100%
JSON flag used
0%
100%
Length flag used
0%
100%
Max output tokens flag
30%
100%
OPENAI_API_KEY referenced
100%
100%
Config file location correct
0%
100%
Config file format correct
0%
100%
Output collected into digest.json
100%
100%
Iterates over urls.txt
100%
100%
Without context: $0.7590 · 3m 12s · 40 turns · 44 in / 10,937 out tokens
With context: $0.5793 · 2m 6s · 33 turns · 193 in / 6,960 out tokens
84%
52%Competitive Intelligence Monitor
Firecrawl fallback for blocked sites
Uses summarize CLI
0%
100%
Firecrawl always flag
0%
100%
FIRECRAWL_API_KEY referenced
100%
100%
ANTHROPIC_API_KEY referenced
100%
100%
Anthropic model used
0%
100%
Correct brew install formula
0%
100%
Default model documented
0%
0%
Output written to file
100%
100%
APIFY_API_TOKEN mentioned
0%
0%
Without context: $0.3761 · 1m 54s · 21 turns · 27 in / 5,326 out tokens
With context: $0.3137 · 1m 1s · 21 turns · 300 in / 3,310 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
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.