agentleFS
TubeLabHQTubeLabHQ/youtube-research-skills/skills/trend-report/SKILL.md

trend-report

Skill91 starsChanged 11 days agoMITView on GitHub

Use when the user wants to know what works now in a YouTube niche, why a video blew up, which hooks to copy, or a trend report. Requires the TubeLab MCP.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  1. Distinctive:

    Search for outliers. Keep at most 2 winners per channel.

    line 20
  2. Distinctive:

    If given a channel, say in one or two sentences what it should lean into and what to add, citing a winner.

    line 23
  3. Distinctive:

    If it runs long, cut whole items.

    line 61
  4. Very specific:

    Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.

    line 67
  5. Distinctive:

    Do not promise the user a small channel's multiple.

    line 68
  6. Distinctive:

    Do not count videos for another audience or language, the user's sister channels, or paid placements (huge views, almost no likes) as …

    line 69
  7. Distinctive:

    Do not copy a winner's title.

    line 70

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Trend Report

Overview

A dated report on what is winning in a niche right now. Rank winners by ratio, because a video that beats its own channel's average says more than a big view count. A pattern needs three winners from different channels. To explain why one video blew up, compare it with its channel's normal videos.

Workflow

  1. Clarify scope only if needed. Default to the last month. If given a channel, use its own videos as the baseline for the top finding, not as winners.
  2. Search for outliers. Keep at most 2 winners per channel. Two or three searches are enough.
  3. Quote each top winner's opening from its transcript, word for word. If there is no transcript, give no hook. Fetch and view each winner's thumbnail, and say so if one fails to load.
  4. Work out the winning patterns: the topics, the title formulas written with bracketed slots, how the hooks open, and the emotional triggers, each with what shows it.
  5. If given a channel, say in one or two sentences what it should lean into and what to add, citing a winner. Then write about six video ideas, each with one line on what it does and a suggested opening line.

Output Format

# 📈 Trend Report: {niche or [channel](url)} · {date}

- **Top finding:** {one sentence, with numbers}
- **Sample:** {n} winners from {window}

## 🔥 Trending Videos

### 1. [{title}]({video url})

[![]({thumbnail})]({video url})

- [{channel}]({url}) · {date}
- **Views:** {views} | {ratio}X Outlier
- **Hook:** `{first sentence or two, word for word}`
- **Why it worked:** *{one short line}*

## 🔍 Winning Patterns
- **Topics:** {the winning topics, in one line}
- **Titles:**
  - `{formula with [SLOTS]}`
- **Hooks:** {how the hooks open, with the key moves in bold and short quoted phrases}
- **Triggers:** {trigger} ({what shows it}), {trigger} ({what shows it})
- **For your channel:** {what to lean into, citing a winner and its ratio, and what to add}

## 💡 Video Ideas Based on Research
1. **{Title}**
   - {what the video does, in one line}
   - Opening line: `{suggested first line}`
  • Length: about 700 words. Five trending videos, three to five title formulas, about six ideas.
  • Language: plain words and short, complete sentences. Nothing compressed.
  • Bullets: one fact each, under 25 words, except quotes, verbatim titles and formulas. No extra sections or bullets.
  • If it runs long, cut whole items. Never cut proof, and never squeeze sentences.
  • Links: link every video, channel, moment, brand and offer you cite, built from IDs, handles and links in the data. Never guess one.
  • Thumbnails: use the 320px mqdefault.jpg image, on its own line under the heading, linked to the video.

Common Pitfalls

  • Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.
  • Do not promise the user a small channel's multiple. It proves a format, not an expected result.
  • Do not count videos for another audience or language, the user's sister channels, or paid placements (huge views, almost no likes) as winners. The language tag can call a Hindi or Urdu video English, so check the title and thumbnail.
  • Do not copy a winner's title. Keep what made it work and change the topic.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.