reels-research
Skill1 starsChanged 22 days agoMITView on GitHub
Researches what is working on Instagram Reels right now for one topic, market and language - top recent Reels and their patterns, current trends, common mistakes, and Instagram's own rules and recommendations (originality, recommendation guidelines, ranking signals) - using only sources from the last 12 months (6 with recent), each with a link and date. Use when the user asks what works on Instagram Reels for a topic, why Reels fail, Reels trends for X, or as part of viral-checklist.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jindratilk/reels-research-mcptheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jindratilk/reels-research-mcp★ 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 repository10 other files it gives its agents.
- publish-rulerSkill
- shorts-researchSkill
- similar-videosSkill
- source-checkSkill
- tiktok-researchSkill
- trend-ideasSkill
- video-packagingSkill
- video-scoreSkill
- viral-checklistSkill
- youtube-researchSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Write today's date at the top of your notes.
- Distinctive: line 54
Every finding needs a link and a publish date inside the window.
- Very specific: line 56
No numbers from memory. If you cannot find a current source, leave it out or add it to gaps.
- Distinctive: line 57
Do not use paid scraping tools or log in to Instagram to collect data.
- Distinctive: line 58
Keep claims short and specific, in plain words.
- Very specific: line 60
When done, run source-check on the notes, unless the user asked you not to.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Instagram Reels research
Finds what is working on Instagram Reels for one topic, and what is not, with a source and date for every finding.
Inputs
| Input | Default |
| topic | ask if missing |
| market (country) | US |
| language | en |
| window | 12 months (recent = 6 months) |
Write today's date at the top of your notes. Every date check uses it.
Output
notes-reels.json in the format in shared/checklist-format.md. Aim for 15 to 30 findings. List what you could not find under gaps.
Where to look, in this order
- Instagram's own rules and tips (official).
- How Reels are ranked: Meta Transparency Center, "Explaining ranking" pages for Instagram Reels (transparency.meta.com/features/explaining-ranking). These pages list the signals Instagram uses.
- Recommendation guidelines (what Instagram will not recommend) and original content rules: help.instagram.com and about.instagram.com/blog. Instagram has been changing how it treats reposted and unoriginal content; find the latest change and its date.
- Instagram's creator channels: creators.instagram.com, the @creators account, and Adam Mosseri's announcements (usually reported by trade press on the same day; use the report's date and link to the original post if you can).
- AI labels ("AI info") and branded content rules.
- Recent top Reels in the topic (examples). Instagram has no public trending list. Search the web for recent viral Reels in the topic and market, with the year in the query. Keep only Reels where a dated page shows the view or like count. Note the hook, length, format, on-screen text, audio, and call to action.
- Studies and analysis (data, analysis). Recent studies with a sample size and dates (for example Reels length, posting frequency, carousel vs Reels reach). Note who ran them and how many accounts or posts they looked at.
- Failures (mistakes). Watermarks from other apps, reposted content, low resolution, text placed under the app buttons, engagement bait, and anything Instagram says it will not recommend. A mistake needs a reason and a source.
What to pull out
Cover each of these, or list it as a gap:
- Hook: first 1 to 3 seconds of top Reels in the topic
- Length that works now (with the source's date)
- Shape and safe zones: 9:16, where text must not go (under the caption and buttons)
- Pacing, structure, payoff
- On-screen text, captions, cover image
- Audio: original audio, trending audio, voice over
- Sends (shares in DMs), saves, comments: which ones Instagram says matter, with the date it said so
- Calls to action that work and ones that count as engagement bait
- Posting frequency and hashtags (only with a dated source)
- Original content rules, reposts, watermarks, AI labels
- Topic-specific risks
Rules
- Every finding needs a link and a publish date inside the window. No date, no finding.
- Market and language must match, or the finding is marked
"scope": "global"(platform-wide announcements only). - No numbers from memory. If you cannot find a current source, leave it out or add it to
gaps. - Do not use paid scraping tools or log in to Instagram to collect data. Public pages and official sources only.
- Keep claims short and specific, in plain words.
When done, run source-check on the notes, unless the user asked you not to.
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.

