summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

2.63x

Quality

76%

Does it follow best practices?

Impact

87%

2.63x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./nanobot/skills/summarize/SKILL.md

Evaluation results

79%

44%

Podcast Episode Transcript Helper

YouTube transcript extraction

Criteria

Without context

With context

Uses summarize CLI

100%

youtube auto flag

100%

extract-only flag

100%

Default model used

100%

GEMINI_API_KEY referenced

100%

Large transcript summary first

Prompt for section/time range

40%

Transcript written to file

100%

68%

Daily Research Digest Automation

URL batch summarization pipeline

Criteria

Without context

With context

Uses summarize CLI

100%

JSON flag used

100%

Length flag used

100%

Max output tokens flag

30%

100%

OPENAI_API_KEY referenced

100%

Config file location correct

100%

Config file format correct

100%

Output collected into digest.json

100%

Iterates over urls.txt

100%

84%

52%

Competitive Intelligence Monitor

Firecrawl fallback for blocked sites

Criteria

Without context

With context

Uses summarize CLI

100%

Firecrawl always flag

100%

FIRECRAWL_API_KEY referenced

100%

ANTHROPIC_API_KEY referenced

100%

Anthropic model used

100%

Correct brew install formula

100%

Default model documented

Output written to file

100%

APIFY_API_TOKEN mentioned

Repository: HKUDS/nanobot
Commit: 04a41e3

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Podcast Episode Transcript Helper Daily Research Digest Automation Competitive Intelligence Monitor

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.