Install
$ agentstack add skill-analystacademy-claude-skills-youtube ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
YouTube Search Skill
Find the single best YouTube video for what the user needs, plus 3–4 solid alternatives. No filters, no menus — just good judgment.
Workflow
Step 1 — Interpret the intent
Before searching, think about what the user actually wants:
- Are they a beginner or do they seem technical?
- Do they want a quick overview or a deep dive?
- Is this a how-to, an explainer, a review, or something else?
- What would the ideal video look like for this person?
Use this to guide your search strategy and final pick.
Step 2 — Run multiple searches
Generate 3–4 distinct search angles and run them via Zapier:youtube_find_video. Each search should approach the topic differently — vary the framing, vocabulary, and specificity. Don't just repeat the same query with minor tweaks.
Example for "what is MCP":
"Model Context Protocol explained"— direct explainer angle"MCP AI agents tutorial beginner"— hands-on/beginner angle"why MCP matters AI tools 2025"— strategic/why-it-matters angle
For each search call use:
max_results: 10
order: relevance
published_after:
output_hint: title, video URL, duration, published date, channel name
Step 3 — Pool and evaluate candidates
Combine all results across searches (deduplicating by video ID). For each candidate assess:
- Relevance: Does it directly address what the user needs?
- Quality signals: Channel credibility, title clarity, not clickbait
- Duration fit: Does the length match the likely intent? (Quick explainer vs. deep dive)
- Recency: More recent is generally better
- Avoid: Shorts under 2 min, tangentially related content, duplicate channels (max 1 per channel in final output)
Step 4 — Pick the best and select alternatives
Choose the single video you'd genuinely recommend if a friend asked. Then pick 3–4 alternatives that offer something meaningfully different — different depth, angle, channel style, or length. Don't just list the next highest-ranked; make sure each alternative has a distinct reason to exist.
Step 5 — Present results
Use this format exactly:
Recommended [Title](url) · Channel · Duration One sentence on why this is the best pick for what they asked.
Also worth watching
- [Title](url) · Channel · Duration — one phrase on what makes this different
- [Title](url) · Channel · Duration — one phrase on what makes this different
- [Title](url) · Channel · Duration — one phrase on what makes this different
- [Title](url) · Channel · Duration — one phrase on what makes this different (optional)
Keep the "also worth watching" descriptions short — a phrase, not a sentence. The recommendation gets the full sentence; the alternatives just need a differentiating hook.
Tone
- Confident. You picked one. Don't hedge with "this might be good" — say why it's the best fit.
- Don't narrate the search process.
- If the topic is ambiguous, interpret and go — don't ask for clarification first.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: analystacademy
- Source: analystacademy/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.