takeaways
Skill1 starsChanged 2 months agoMITView on GitHub
Extract conclusions and key takeaways from YouTube videos, Instagram Reels/posts, or long-form content, providing a fast comparison and a clear final verdict that directly answers the question or premise in the video's title. Args: <url | text>
In this repository17 other files it gives its agents.
- check-drySkill
- check-testsSkill
- create-commit-messageSkill
- create-unit-testsSkill
- deslop-proseSkill
- deslopSkill
- fanout-reviewSkill
- fix-security-auditSkill
- framework-upgrade-guideSkill
- generate-adrSkill
- learnSkill
- optimizeSkill
- pr-descriptionSkill
- resolve-merge-conflictsSkill
- security-checkSkill
- ship-itSkill
- update-claude-mdSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Check the content provided in $ARGUMENTS:
- Distinctive: line 30
If runtime browsing or fetching tools are available, attempt to retrieve page content or transcript.
- Distinctive: line 31
If external tools are unavailable, if scraping is blocked by captchas/auth, or if no captions are extractable, stop and ask the user:
- Distinctive: line 33
Empty or missing argument: stop and prompt:
- Distinctive: line 80
Do not invent facts, benchmarks, or opinions absent from the source content.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Note: $ARGUMENTS is substituted by Claude commands only. In Copilot,
the user must include their argument inline in the prompt; the skill
body sees the literal text "$ARGUMENTS" unsubstituted. -->Arguments
<url | text>
- Required. A URL to a video, social post, or article, OR raw text/transcript content.
- Examples:
/takeaways https://www.youtube.com/watch?v=example,/takeaways <pasted transcript>
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Extract Takeaways: $ARGUMENTS
Extract the core conclusions, pros, cons, and answers from long-form content, video transcripts, or social posts. Always resolve clickbait titles up front by delivering a direct, unambiguous verdict.
Step 1: Input Resolution
Check the content provided in $ARGUMENTS:
- Raw text or pasted transcript: proceed directly to Step 2.
- URL (YouTube, Instagram, article, podcast):
- If runtime browsing or fetching tools are available, attempt to retrieve page content or transcript.
- If external tools are unavailable, if scraping is blocked by captchas/auth, or if no captions are extractable, stop and ask the user:
"Could not extract transcript automatically from
<url>. Please paste the transcript, subtitles, or article text to continue."
- Empty or missing argument: stop and prompt:
"Usage:
/takeaways <url | text>. Please provide a URL or paste the content to analyze."
Step 2: Identify Core Premise and Title Question
Identify the central question, debate, or promise in the title or opening framing (for example: "Is framework X worth learning?", "Tool A vs Tool B", "Does technique Y really work?").
Step 3: Group Findings and Key Points
Synthesize the content into clear categories:
- Primary claims and evidence presented
- Concrete pros and cons
- Product, tool, or methodology comparisons
- Benchmark numbers, pricing, or measurable results
Step 4: Output Template
Render the analysis in this structured format:
# Takeaways: <Title or Subject>
**Core Premise**: <The central question or debate investigated in the content>
**Direct Verdict**: <Direct, definitive answer resolving any clickbait or open question up front>
## Key Takeaways
- **<Point 1>**: <Summary of finding with evidence or rationale>
- **<Point 2>**: <Summary of finding with evidence or rationale>
- **<Point 3>**: <Summary of finding with evidence or rationale>
## Comparison / Breakdown
| Subject / Option | Advantages | Disadvantages | Verdict |
|---|---|---|---|
| <Item A> | <Key strength> | <Key weakness> | <Assessment> |
| <Item B> | <Key strength> | <Key weakness> | <Assessment> |
## Actionable Recommendation
<1-2 concise paragraphs summarizing practical advice, trade-offs, and when to choose what>Rules
- State the final verdict directly up front; do not preserve clickbait suspense.
- Do not invent facts, benchmarks, or opinions absent from the source content.
- Be concise: prioritize bullet points and tables over dense prose.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

