Pinned Tweet
2026 will be different.
No more begging for doors that never wanted to open.
God will position me where my value is respected, my work is rewarded, and my wins are undeniable.
Grace will speak for me.
1
5
444
Shuaib Eedris retweeted
if your research process is typing "give me 50 viral video ideas" into chatgpt, you're getting the worst ideas in your niche, and i'll explain exactly why.
every idea it gives you is an average of stuff it already saw during training. you're asking a machine to predict what worked in the past and calling it the future.
so here's the research stack i'd run instead, built on 2 models that came out in the last few weeks. every prompt is in here, so bookmark this one:
first you need to understand what each model does, because they do completely different jobs.
jev came out on september 15 from typesafe AI, and it doesn't write anything. you send it text plus a list of typed questions, and it sends back typed decisions with a probability attached to each one.
it answers in 70 to 500 milliseconds and costs around $0.042 per million input tokens. so you run thousands of yes or no checks every week for pennies.
think of jev as the judge.
opus 5.5 came out on september 22 from anthropic, and it's the analyst. on anthropic's fact-checked research report test it passed 16 times out of 18, while fable 5.1 and opus 5 passed 0 times.
so jev looks at everything, and opus only gets called when something's worth digging into. that split is how the whole thing stays cheap.
before any prompts, there are 3 rules i give both models, and honestly they matter more than the prompts themselves.
rule 1 is that views never prove a niche is profitable, or that a format caused them. rule 2 is that every claim gets a label: observed, baseline, pattern, inference or hypothesis. and rule 3 is that 1 viral video is never a market pattern.
without these, AI will happily tell you a niche is a goldmine because of 1 lucky upload.
then there's 1 formula that replaces hours of scrolling:
relative performance = video views ÷ channel median recent views
500K views on a channel that averages 20K is a 25x outlier. 2M views on a channel that averages 5M is underperforming. you want to study the first one, every time.
now the prompts. paste these into opus 5.5 in this order:
1. "research this youtube market: [NICHE]. analyse audience, subtopics, creator density, formats, recurring questions, monetisation and faceless suitability. separate observed evidence, inference and hypothesis."
2. "map the channels around [MARKET]. don't rank by subscribers. find format leaders, challengers, and channels with outliers 5x or more above their own median."
3. "analyse these outliers. for each one: views, channel baseline, relative performance, title formula, thumbnail concept, hook and structure. never describe performance as causation."
4. "from this dataset, find content gaps: unanswered questions, weak explanations, stale angles, missing audiences and missing formats. never claim nobody has covered something."
5. "topic: [TOPIC]. generate 10 distinct angles. for each: the viewer's question, hook, title, thumbnail concept, payoff and the evidence needed. no synonyms of the same angle."
6. "build the script architecture: cold open, promise, stakes, context, first reveal, escalation, counterpoint, payoff, implication, cta. give every section a retention job."
7. "for every section give me: timestamp, narration, visual, source and on-screen text. no random stock footage."
and between prompt 5 and prompt 6 is where jev comes in.
every idea goes to jev before it reaches opus. you send it the idea, the market evidence, the performance signals and the angles. it sends back a decision, a probability, a confidence score, the evidence for, the evidence against, what's still unknown, and the next action.
anything under your confidence bar dies right there. only the survivors reach opus, so you never pay opus to write a script for a bad idea.
then once a week you run the loop. refresh your channel list, snapshot the views, flag the new outliers, update your gaps, run jev, send the survivors to opus, publish, and feed your own retention data back in.
do this for 8 weeks and you'll have a memory of your market nobody else has, because it's built from your own data. nobody copies that by scrolling the homepage.
if you want the full protocol with the 3 skill files ready to paste, DM me "INTEL" and i'll send it over
(200M+ views generated through AI scriptwriting skill files trained on 8,000+ scripts, one-time payment)
Shuaib Eedris retweeted
If you're looking for a thumbnail composition to use for your next video, here are 15 examples you can use. These come from a list of the most common thumbnail compositions found in videos with over a million views.
1. Title Head
This is a pretty straightforward composition where you have a face on one side and simple text on the other. The goal is to establish a familiar person while adding context through text.
2. Dramatic Face
With the dramatic face, it's all about emotion. The vagueness is quite intentional, and the viewer may not be certain what the video is about. So why would a person use it? It usually relies on familiarity with the person, who is often a famous person, to draw attention through its unique style choice. While this tends to work best for one-off videos, the uniqueness of this composition means it often does very well. We also tend to pair this with a more serious title.
3. A Affects B
This is a very common thumbnail composition when we want to evoke interest through the interaction between two subjects or the potential conflict. It clearly shows one person or object about to manipulate or target the other.
4. Conversation Question
In this thumbnail composition, we show two people with a question in the middle, as if one person is asking the other. A statement can also be used, but most of the time, we just use a question. The interest comes from wanting to see how people respond. This composition is often used for street interviews.
5. 3-Panel Progress
This composition shows the same object or subject changing over time or moving through different stages. The idea is simple: from left to right, we show clear stages and promise growth or improvement.
6. Problem state
This composition is any thumbnail that focuses on the idea that we're in the middle of a problem and we're showcasing this problem. The beautiful thing about this thumbnail is that it relies on conflict and the uncertainty of something potentially going wrong, which evokes very strong emotions from an audience.
7. Contrast
This is another common viral composition where we highlight a difference (typically in size) between two things. The idea is that we're evoking intrigue by creating strong contrasts, whether it's size, value, complexity, or anything else.
8. Don’t do this
This thumbnail shows an action that is clearly wrong. We show that it’s wrong by using a red X or simple text like “don’t do this,” “don’t rewatch,” or a similar warning. It generally plays on the fear of making the same mistake for people interested in the topic.
9. Eliminators
This thumbnail composition shows the main rule of the video. We already know that many stories become interesting when limitations are added. By adding this rule to the thumbnail, it's a lot easier to get people interested in the video. This one really plays on the idea that people want familiar experiences, but with just a little bit of novelty.
10. Motion Arrow
In this thumbnail composition, movement is implied through an arrow, a pointer, or anything that suggests movement, all while the actual outcome stays hidden. The arrow can even take an impossible shape to evoke more curiosity about what’s going to happen. What makes this one so good is that we're able to add some type of intensity and movement to an otherwise still frame.
11. Conflict
This shows two objects approaching each other with no clear resolution. The tension comes from not knowing what the impact will look like. Usually, the two objects don’t belong together or they're clearly in conflict with each other. This one is about interest through conflict and tension.
12. Mid Progression
In this composition, we show the story already happening. The viewer gets a snapshot from a later stage, with clear progress already being made. They may already be able to envision what progress will look like after this point. But even the lack of certainty around the beginning is often something that could evoke curiosity. One great way to complement this composition is to add something like a day or time marker to make the progression very clear.
13. Comment / Post
This is probably one of the oldest thumbnail compositions on this list, but it still works very well, especially for creators who have built a strong parasocial relationship with their audience. This kind of thumbnail really relies on reactions to a channel or quotes made in an interview, and the viewer already knows what kind of video they can expect. It’s a solid composition, even with its limited appeal.
14. Accusation
This thumbnail composition really plays on aggression and often makes the viewer feel directly targeted. We judge them. We make them feel like they're at the center of our judgment. While this thumbnail can often feel risky, it works incredibly well when combined with a clear authority figure. It’s a riskier composition, though, because if the video isn’t emotionally charged, it can lead to dissatisfaction.
15. Review
This thumbnail composition clearly focuses on quality as a signal. It can be stars, pricing tiers, or maybe even a scale. Whether somebody's going to click or not all comes down to whether they want to experience figuring out if something is actually good or not. Bad reviews spark curiosity about whether it can actually be as bad as people say it is, while good reviews create excitement around how good something is going to be and whether we even agree with the judgment of others. This kind of video tends to be all about extremes.
There are so many thumbnail compositions you could use, and it's not like one is particularly better than another. Different ideas call for different thumbnail compositions, and even different audiences are attracted to different thumbnail compositions. Especially since we are getting ready for dynamic thumbnails, it's good to brush up on your knowledge of thumbnail formats.
Shuaib Eedris retweeted
AI video creators dream come true 🤩
TWO FREE AI VIDEO GENERATION TOOLS you can use without paying a single penny
Save this.
Shuaib Eedris retweeted
THINGS YOU CAN DO ONLINE BY YOURSELF NOW IN NIGERIA WITHOUT PAYING AN AGENT.
1. WAEC Digital Certificate: Access and print out your original WAEC certificate online.
waec.org
2. CAC Registration: Register your business or company.
icrp.cac.gov.ng
3. International Passport: Apply for or renew your Nigerian passport.
passport.immigration.gov.ng
4. Driver's Licence: Apply for or renew your driver's licence. nigeriadriverslicence.frsc.g…
5. SCUML Registration: Apply for your SCUML certificate.
scuml.efcc.gov.ng
6. Tinted Glass Permit: Apply for a vehicle tinted glass permit.
possap.gov.ng
7. Police Character Certificate: Apply for a police character certificate.
possap.gov.ng
8. Police Extract: Apply for relevant police extracts.
possap.gov.ng
9. Tax Identification Number (TIN): Register for your tax identification.
selfservice.nrs.gov.ng
10. Birth Attestation: Access birth attestation services.
nationalpopulation.gov.ng
11. NIN Services: Access NIN enrolment information and other services.
nimc.gov.ng
🔥 میخوای Claude Code یا Codex برات موشنگرافیک حرفهای بسازه؟ این ریپو رو از دست نده!
تصور کن بهجای اینکه هر بار از صفر به Agent توضیح بدی چطور یک انیمیشن بسازه، چطور متنها رو متحرک کنه، چطور Timing و Easing رو تنظیم کنه و چطور خروجی نهایی رو بررسی کنه، مجموعهای از دستورالعملهای تخصصی در اختیارش داشته باشی.
دقیقاً کاری که Motion Skills انجام میده!
این پروژه یک مجموعه متنباز شامل ۵۶ Skill در ۱۹ پکیج تخصصی است که به Coding Agentها یاد میده چطور موشنگرافیک، انیمیشن و ویدئو تولید کنن.
🎬 چه کارهایی میتونی باهاش انجام بدی؟
بعضی از حوزههایی که این مجموعه پوشش میده:
🔹 Motion Design: ساخت موشنگرافیک، انیمیشن لوگو، ترکیببندی و طراحی حرکتی
🔹 Kinetic Typography: متحرکسازی حرفهای متن و تایپوگرافی
🔹 TikTok / Reels / Shorts: تولید ویدئوهای عمودی و محتوای کوتاه
🔹 Product & E-commerce Videos: ساخت ویدئوهای تبلیغاتی و معرفی محصولات
🔹 Explainer Videos: تولید ویدئوهای آموزشی و توضیحی
🔹 Data Animation: تبدیل دادهها و نمودارها به انیمیشنهای جذاب
🔹 3D & WebGL: ساخت انیمیشنهای سهبعدی، Shader و صحنههای تعاملی با Three.js
🔹 Web Animation: انیمیشنهای وب با GSAP، SVG و Lottie
🔹 Manim: ساخت انیمیشنهای ریاضی و آموزشی
🔹 Generative Illustration: تولید تصویرسازیهای خلاقانه با کدنویسی
🔹 B-Roll و Talking Head: ساخت نماهای مکمل و ویدئوهای مبتنی بر گوینده
حتی برای ساخت Lower Third شفاف، انیمیشن نقشه، ویدئوهای پیامکی و انیمیشنهای فریمبهفریم با JavaScript هم Skill اختصاصی داره.
⚙️ نکته جالب این پروژه چیه؟
موضوع فقط تولید انیمیشن نیست؛ بلکه روی کنترل کیفیت خروجی هم تمرکز کرده.
بسیاری از Skillهای این مجموعه یک چرخه مشخص برای بررسی خروجی دارن:
۱. Agent انیمیشن رو تولید میکنه.
۲. از فریمهای خروجی تصویر میگیره.
۳. فریمها رو بررسی میکنه تا مشکلات بصری مشخص بشن.
۴. در صورت نیاز خروجی رو اصلاح میکنه.
یعنی بهجای اینکه Agent صرفاً کد بنویسه و امیدوار باشیم خروجی درست باشه، خودش هم نتیجه کارش رو بررسی میکنه.
🛠 چطور نصبش کنیم؟
یکی از مزیتهای خوب پروژه اینه که لازم نیست تمام ۵۶ Skill رو نصب کنی. هر پکیج بهصورت مستقل قابل نصبه و میتونی فقط موارد موردنیازت رو انتخاب کنی.
مثلاً برای تولید ویدئوهای کوتاه:
npx skills add iart-ai/tiktok-video-skills
برای انیمیشن دادهها:
npx skills add iart-ai/data-animation-skills
برای موشندیزاین:
npx skills add iart-ai/motion-design-skills
حتی میتونی بعضی پکیجها رو مستقیماً بهعنوان Plugin در Claude Code اضافه کنی:
/plugin marketplace add iart-ai/web-animation-skills
این Skillها با Claude Code، Codex، Cursor و بیش از ۴۰ Agent دیگه سازگاری دارن.
📌 یک نکته مهم:
این پروژه خودش یک مدل تولید ویدئو یا نرمافزار تدوین نیست. در واقع دانش و Workflow تخصصی رو در اختیار Agent قرار میده تا بتونه با ابزارهایی مثل Remotion و Manim خروجی قابل ویرایش تولید کنه.
همچنین با مجوز MIT منتشر شده و میتونی آزادانه ازش استفاده کنی.
به نظرم برای کسانی که با Claude Code و Remotion یا HyperFrames موشنگرافیک تولید میکنن، این مجموعه ارزش بررسی جدی داره. چون بهجای اینکه هر بار همه جزئیات فنی و اصول طراحی حرکتی رو در Prompt توضیح بدن، میتونن از Workflowهای آماده استفاده کنن.
🔗 لینک GitHub:
github.com/iart-ai/motion-sk…
کانال تلگرام : t.me/yarad_ai
Shuaib Eedris retweeted
add these three terms to your channel's blocklist and watch your views climb like crazy
Shuaib Eedris retweeted
There's no rush to Greatness cos u only got one chance to be the new Guy...so work!!..
Shuaib Eedris retweeted
1. Remotion: github.com/remotion-dev/remo…
2. Herk Edit Kit: github.com/nateherkai/herk-e…
3. OpenFilm: github.com/openfilm/openfilm
4. OpenMontage: github.com/OpenMontageInc/Op…
5. HyperFrames: github.com/heygen-com/hyperf…
Shuaib Eedris retweeted
Nothing is ever as bad as you think it is because no one cares about you as much as you think they do.
Shuaib Eedris retweeted
The concept of money is quite easy and my dad broke it down for us easily.
To make money, you have to sell a product or a skill.
To lose money, you have to purchase a product or a service.
To multiply money, you have to invest.
If you do not purchase, money will not leave.
If you do not have a product or service to sell, money will not enter.
If you do not invest wisely, money will not multiply.
If your purchases are higher than your income, you go broke.
If you delay gratification, the money stays longer.
If you delay gratification but do not invest "WISELY", especially in a country like Nigeria, the money stays longer but risk losing value over time.
This is basically the summary of every finance book ever written.



































