trend-radar
Skill19 starsChanged 30 days agoMITView on GitHub
Use when evaluating whether a trend is relevant, identifying emerging trends, or advising on trend participation timing.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Cheukcoding/claude-skillstheir own version, first seen Nov 1, 2026
- easyaitech/etsy-skillstheir own version, first seen Oct 16, 2026
- megandmartin/agent-skills-repotheir own version, first seen Jul 24, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- easyaitech/etsy-skills★ 5same name
- megandmartin/agent-skills-repo★ 3same name
- Cheukcoding/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- agent-interviewSkill
- audio-acquisitionSkill
- brand-kitSkill
- content-autopsySkill
- edit-handoffSkill
- editor-beat-syncSkill
- editor-camera-directingSkill
- editor-captionsSkill
- editor-motion-graphicsSkill
- editor-plan-and-checkSkill
- editor-sfx-sparseSkill
- editor-soundtrackSkill
- editor-versionsSkill
- hook-anatomySkill
- media-acquisitionSkill
- platform-fluencySkill
- read-the-roomSkill
- repurpose-engineSkill
- studio-setupSkill
- subject-compositingSkill
- video-formatsSkill
- video-productionSkill
- voice-matchingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Every social media trend follows a lifecycle.
- Distinctive: line 26
Only in niche communities, no major creators yet → emergence
- Distinctive: line 34
Every trend has a template (the repeatable structure) and instances (specific executions).
- Distinctive: line 40
Not every trend fits every creator.
≈ “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
Trend Radar
Every social media trend follows a lifecycle. Knowing where a trend sits in that lifecycle is more valuable than knowing the trend exists.
Trend Lifecycle
Emergence — small creators, niche communities. The format is still rough and evolving. Few people have seen it. This is where trend-spotters live.
Growth — mid-tier creators adopt it. The format solidifies into a repeatable template. Daily volume is climbing. This is the best time to participate — algorithmic boost is highest, the audience isn't tired of it yet.
Peak — everyone's doing it, including brand accounts. Your non-social-media friends have seen it. Maximum visibility but diminishing returns for new entries.
Saturation — "enough with this trend" comments appear. Engagement rates on new entries drop. Late entries feel like they're behind.
Ironic revival — parodies, meta-commentary, "remember when we all did this?" Can be a second window for creators who do meta-humor well.
Most trends spend 1-3 weeks in the growth-to-peak window. Some (especially sound-driven TikTok trends) move faster. YouTube topic trends move slower and last longer.
Reading Lifecycle Signals
- Only in niche communities, no major creators yet → emergence
- Clear repeatable format, mid-tier creators posting versions, volume climbing → growth
- Brand accounts participating, mainstream awareness → peak
- "Stop doing this" commentary, dropping engagement on new entries → saturation
- Parodies and meta-commentary outnumber sincere entries → ironic revival
Template Extraction
Every trend has a template (the repeatable structure) and instances (specific executions). To participate well, extract the template — what stays the same across every version? What's the fill-in-the-blank?
A creator should fill the template with their own niche and voice, not copy someone else's instance. The template is the trend. The instance is the creator's contribution.
Niche Relevance
Not every trend fits every creator. Before participating, ask:
- Does my audience care about this topic or format?
- Can I connect this to my content pillars naturally, or would it feel forced?
- Does participating align with my voice, or would I be performing someone else's style?
- Is there a genuine angle from my niche, or am I just jumping on it for reach?
A fitness creator doing a cooking trend needs a fitness angle. A finance creator doing a dance trend needs to be funny enough to pull it off. If the connection is forced, skip it.
Timing
Early participation (growth phase) gets the most algorithmic boost. Peak phase still works but needs a strong unique angle to stand out. Saturation is too late unless you're doing meta-commentary or parody.
Rule of thumb: if you have to ask "is this still trending?" — you're probably late.
Platform-Specific Mechanics
Load the relevant platform reference from references/platforms/{platform}.md in this skill's own directory. Key differences: TikTok trends are often sound-driven, Instagram trends are format/template-driven, YouTube trends are topic/challenge-driven and move slower. X trends are conversation-driven and move fastest but burn out within hours.
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.

