
Marketing | Systems | Growth | Books | some Digital #Marketing Nerd | All about ๐๐ Views my own! โ#Ifollowback #politicallyincorrect
Riyadh
Joined May 2011
- Tweets18.8K
- Following1.5K
- Followers513
- Likes11.1K
Don retweeted
Here's how to use Claude to create this animated clip from just a few screenshots.
From @jake11moran:
โI came with 3 screenshots. One was of our studio, and the rest were the images I wanted to use in the hook. Then I sat down and wrote a simple prompt for @HyperFrames_ studio.
As much context as you can feed is ideal. Opus and these newer models are going to make a lot of these choices. Youโll be amazed by what they choose to do by themselves.โ
๐ Watch our full AI video editing tutorial here: youtu.be/MC1g2fHYC88
Anyone can now make amazing videos with Claude Opus if you know how to prompt it.
Here's my new episode with @jake11moran where he showed me exactly how to use Claude and @HyperFrames_ to:
โ Make a launch video from just a few images
โ Duplicate your favorite creator's video style
โ Make precise edits with the right keywords
Every minute of our 40-min episode is packed with alpha and live demos.
๐ Watch now: youtu.be/MC1g2fHYC88
Thanks to our sponsor:
@WisprFlow: Get 1 month free of the best voice dictation tool wisprflow.ai/?promo_code=PETโฆ
Don retweeted
i just re created kurzgesagt's entire channel in 10 minutes with claude opus
they have 0 competition because every video takes a full team of animators and 1200+ hours to make
i turned it into a claude prompt that im giving out for free
open claude code, paste the prompt, pick an idea, and your video is fully automated
thank me later โ
<inputs>
Ask me for: one topic as a "what if" question (default: "What if the Sun vanished?"), the length (default 30 seconds), and whether I have an ElevenLabs key (if not, use a free local voice).
</inputs>
<direction>
A Kurzgesagt-style animated explainer at 1920x1080, 30fps, drawn entirely in code: one 2D canvas plus one WebGL canvas for planets.
Space: a vertical gradient #081d2c to #102348, five huge parallax nebula blobs (teal rgb 24,150,160 at 20%, blue 40,95,195 at 16%, coral 220,95,110 at 10%, indigo 60,70,175 at 15%), three star layers at parallax depths .12/.35/.6 that twinkle, 40% of the near stars drawn as 4-point sparkles.
The Sun: radius 300px, half off the left edge. A radial gradient #fff7dc to #ffc857 to #ff8f4a with an offset highlight, additive halo rings at 1.23/1.48/1.76/2.1x the radius, 18 faint rotating ray wedges, 28 drifting glowing granules on its surface.
Earth: an orthographic sphere in a fragment shader, 4x supersampled, from a 2048x1024 map painted from longitude/latitude polygons: land #5fc47a, forest #48ad6b, desert #f5c75f, rainforest #3a9d62, ice #f1f8ff, ocean gradient #4dc7eb to #1a66b8, white capsule clouds. Tilt .26 rad, spin .55 degrees per second. Day/night uses smoothstep(-.12, .24, NยทL) with the light direction recomputed from Sun to Earth every frame. Navy night side with ~380 warm city lights, a coral band on the terminator, a cyan rim, ocean specular, an atmosphere halo that is stronger on the lit side.
A small astronaut mascot (~180px) built from rounded rectangles: suit #f3f7fb, orange #ff8f4a boots, a visor gradient #1f5a73 to #0a1c2c with glowing cyan eyes that look at whatever matters, a blinking antenna light, an idle bob, squash and stretch on every pose.
Type: Fredoka 600/700 only. Captions in caps with 3-6px letter spacing in teal #8fd8e6, gold #ffd98a or white, sitting in rounded pills of rgb(6,20,40) at 62%. Every line of text rises 1.3x its own height through a clip on an ease-out-quint.
Finish: a vignette to rgba(4,4,20,.45) and a 6% film grain re-randomized 24 times per second.
Banned: outlines, flares or loops on the Sun's edge, static infographic strips, full stops in on-screen text, text that fades in whole, AI images or AI video, Kurzgesagt's own characters, bird or music.
</direction>
<structure>
30 seconds, every line of narration gets a camera move or a transformation, nothing ever holds still.
Tight on the Sun at 2.25x (0s) โ on the word "vanished" it swells 6% for 0.22s, collapses in 0.33s, then a white flash and a shockwave ring (1s) โ pull back to 1x revealing Earth still lit and the astronaut staring at the empty spot (1.6-3s) โ on "eight" an 8:20 countdown slams in from 1.7x to 1x and starts ticking, a "LAST LIGHT" label rides the edge of the growing dark disc (3.2s) โ dive to 2.3x on Earth with light streaks flowing in (5.6s) โ on "you" a YOU pin drops (7s) โ on "left" a photon lands on the pin with "THIS LIGHT LEFT THE SUN / 8 MIN 20 SEC AGO" (7.5s) โ on "play" the pin morphs into a play button, "YOU PRESSED PLAY / 15 SEC AGO" (8.8s) โ one pull-back from 2.4x to a 0.3x orbit view, "LAST LIGHT" and "GRAVITY" riding the ring (9.6-12.5s) โ on "nothing" a dotted circle at the empty centre (13.4s) โ on "hits" the darkness sweeps Earth in 0.7s, city lights pop on, the countdown turns gold at 0:00 (15.8s) โ on "black" the background fades almost to black (17.4s) โ Jupiter appears, "STILL SHINING FOR 1 HOUR+" (17.9s) โ zoom out, a dashed tangent line, "30 KM/S" as Earth flies straight off (20.8s) โ a thermometer counts 15 to -70ยฐC while frost grows from the poles (22.8s) โ a 0.8s rewind on a separate story clock (24.3s) โ sunglasses drop onto the astronaut (25.2s) โ a photon tagged "8:20 OLD", then the title (27.7s).
For any other topic, keep the same shape: the event happens on its word, pull back to show scale, dive in to make it personal ("you"), pull back out, the consequence with a live counter, an escalation, a funny beat with the mascot, a callback and the title.
</structure>
<build>
1. One HTML file. Every frame is a pure function of time: window.seek(t) draws frame t. No timers, no CSS animation.
2. Camera moves on easeInOutCubic, zoom is interpolated in log space, every pop is a damped spring (damping .42-.5, frequency 12-16).
3. Voice: ElevenLabs eleven_v4 with a designed voice (calm, warm, curious male, late 30s, crisp, light neutral European English), stability .5, similarity .75, generated with timestamps. Without a key, use kokoro-onnx locally and get word times with faster-whisper. Every animation event fires on its word. About 165 words per minute, 0.24s between sentences, a 0.36s beat before the big reveal.
4. The darkness front: any pixel within the front's radius from the Sun turns to night with a 30px soft edge. The front moves at ~47px/s and ramps to 700px/s near Earth.
5. Keep two clocks: ambient time for twinkle, spin and bob, and a separate story clock for events, so a rewind stays consistent.
6. Render with Playwright in headless Edge with the GPU: seek every frame at 30fps and blend 2 subframes (shutter 0.6) for motion blur, then encode with libx264 at CRF 16 for the master and CRF 20 for delivery.
7. Sound: a calm royalty-free space music bed 7dB under the voice, timed so its natural ending lands on the title, swelling 5dB under the title. One downloaded royalty-free sound effect per event kind (collapse, impact, pull-back whoosh, countdown tick, dive, pin tap, photon land, play click, light hit, reveal, frost, rewind), each peak-aligned to its frame and 4-10dB under the voice. Master with gain plus a limiter to -14 LUFS, -2.2dB true peak.
</build>
<gotchas>
Make the WebGL globe canvas at least 2 x radius x zoom x 1.18 pixels or the sphere clips flat in close-ups. Never draw prominences on the Sun's edge, they read as white hooks. Never pad the voice to fit the visuals, tighten the read instead. Speed the darkness front up near Earth or it takes 13 seconds to cross the planet. Show me a contact sheet of every beat before rendering.
</gotchas>
<start>
Ask me the inputs, write the narration with the beat each word triggers, show it to me, then build and render the video.
</start>
kurzgesagt has 25M subs and they still go viral with 15M+ views on every single video for years
nobody copies them because every video takes a full studio of animators and months of work
i rebuilt their format with opus 5.5, 100% code for $0 per video, on the left is my own version i created
he probably averages $150k+ earning per video
9 years ago he posted how he makes 1 video in 1200 hours, i re created this in literally 10 minutes for free (check in comments)
would u guys be interested if i turned this into a free claude skill you can use?
imagine a fully integrated AI future where being banned means you are now economically useless. everybody around you is a superhuman living in the future but you violated TOS and now are cut off.
your smart glasses that showed you a beautiful utopia? the color has left them. you are forced to live in a bleak gray world. you are forced to look your wife in her actual face and she is not happy with you.
you are digging holes with a spoon while everybody else is building skyscrapers with an army of bots.
this is the real doomer catastrophe
open source is the only way to protect your freedom, your economic viability & your ability to tell these companies to fuck right off.
a few months ago openAI and anthropic were desperately begging the admin to make it legal for them to collaborate. if they got their way, one TOS violation on either platform would send you directly to the sunken place.
Don retweeted
This is pure f*cking money
you can now run your own CGI ad agency with Opus 5.5 + Blender
brands pay $1,500โ5,000 for a 15s product spot like this.
glass. liquid. gold. 4 camera shots. 3 formats.
no 3D artist. no studio. a GPU from 2016.
here's the full stack from client brief to final delivery โ
/cgi-ad-studio
โ
โฃ BRIEF
โ โ Claude Code: turns the client brief into a shot list + camera moves
โ claude.com/claude-code
โ
โฃ CONNECT
โ โ Blender MCP: Opus drives Blender live and checks every render
โ github.com/ahujasid/blender-โฆ
โ
โฃ BUILD
โ โ Blender: bottle, amber liquid, fluted gold cap, engraved logo, all from code
โ blender.org
โ
โฃ LIGHT
โ โ Poly Haven: free HDRIs + textures. luxury = 90% lighting
โ polyhaven.com
โ
โฃ CUT
โ โ HyperFrames: titles, overlays and the edit, written as HTML
โ github.com/heygen-com/hyperfโฆ
โ
โ DELIVER
โ FFmpeg: one command โ 16:9 hero, 9:16 reel, 1:1 feed
one brief in. one ad out. one operator.
the agencies charging $5k for this are about to have a very bad year
bookmark this, save yourself from future headaches
Don retweeted
ุดุฎุต ุงุณุชููู 200 ู
ููุงุฑ ุชููู ููู ูุถุจุท ุฅุนุฏุงุฏุงุช Hermes Agentุ ูุงูุญูู ูุฑุฑ ูุดุงุฑู ุดุบูู ู
ุน ุงูุฌู
ูุน ูู ู
ุดุฑูุน ู
ูุชูุญ ุงูู
ุตุฏุฑ ุงุณู
ู Oh-My-Hermes.
ุงูู
ุดุฑูุน ูุฌู ู
ุนู ุฃูุซุฑ ู
ู 150 ู
ูุงุฑุฉุ ููุธุงู
ุฐุงูุฑุฉ ุทูููุฉ ุงูู
ุฏูุ ูุฃุฏูุงุช ูุฅุฏุงุฑุฉ ุงูุฐุงูุฑุฉุ ูุชูุฒูุน ุงูู
ูุงู
ุนูู ูููุงุก ูุฑุนููู ุจุงุณุชุฎุฏุงู
ูู
ุงุฐุฌ ู
ุฎุชููุฉ.
ูููู ุชุญุณููุงุช ู
ุซู ุชุดุบูู ุงูุฃุฏูุงุช ุจุงูุชูุงุฒู ูุชูููู
ุงููุชุงุฆุฌ.
ูุงูุฃุญููุ ู
ุง ุชุญุชุงุฌ ุชุถุจุท ูู ุดูุก ุจููุณูุ ุซุจูุชู ุจุณุทุฑ ูุงุญุฏุ ูุนุทู ุงูู
ูู
ุฉ ุงููู ุชุจููุงุ ููู ูุชููู ุงูุจุงูู ุชููุงุฆููุง.
ุงูู
ุดุฑูุน ู
ุชุงุญ ู
ุฌุงููุง ูู
ูุชูุญ ุงูู
ุตุฏุฑ ุนูู GitHub.
ุฑุงุจุท ุงูู
ุดุฑูุน:
github.com/rlaope/oh-my-hermโฆ
Don retweeted
๐จ ุชุฎูู ุชุชุนูู
Arduino ุจุงููุงู
ู ู
ู ุบูุฑ ู
ุง ุชุดุชุฑู Arduino ูุงุญุฏ!
ู
ุทูุฑ ุงุณู
ู Dilum Sanjaya ุจูู ุชุทุจูู ุชูุงุนูู ุจุงุณุชุฎุฏุงู
Opus 5.5ุ ุจูุญููู ู
ุชุตูุญู ูู
ุนู
ู ุฅููุชุฑูููุงุช ุซูุงุซู ุงูุฃุจุนุงุฏ!
ุงุณู
ุงูุชุทุจูู: Learn Arduino
ูุงูุฃูููุ ููู 11 ุฏุฑุณ ู
ุฌุงูู!
โก ูุชูุฏุฑ:
- ุชูุตู ุงูู
ูููุงุช ุจููุญุฉ Arduino Uno ุงูุชุฑุงุถูุฉ.
- ุชูุชุจ ุงูููุฏ ูุชุดุบููู ูุชุดูู ุงูู LED ุจูููุฑ.
- ุชุชุญูู
ูู ุงูู
ูุชูุฑ ูุงูุณูุฑูู.
- ุชุฌุฑุจ ุงูุญุณุงุณุงุช ูุชุดูู ุงูุจูุงูุงุช ูุญุธุฉ ุจูุญุธุฉ.
- ุชุจูู ู
ุดุฑูุน ุฅุดุงุฑุฉ ู
ุฑูุฑ ุจุชุณุชุฌูุจ ูุนุงุฆู ูุฏุงู
ูุง.
ูู ุฏู ู
ู ุงูู
ุชุตูุญุ ู
ู ุบูุฑ ู
ุง ุชุญุชุงุฌ ุชุดุชุฑู ุฃู ู
ูููุงุช ุฅููุชุฑูููุฉ!
ูุงููุฑู ููุง ุฅูู ู
ุด ุจุชุชูุฑุฌ ุนูู ููุฏูู ูุจุชุญุงูู ุชูููุฏ ุงููู ูููโฆ
ุฅูุช ุจุชุจูู ุงูุฏุงุฆุฑุฉ ุจููุณูุ ุจุชุดุบูู ุงูููุฏุ ูุจุชุดูู ุงููุชูุฌุฉ ูุฏุงู
ู ูู ุงูููุช ุงููุนูู.
ูุฏู ู
ู
ูู ูุบููุฑ ุทุฑููุฉ ุชุนููู
ุงูุฅููุชุฑูููุงุช ููู
ุจุชุฏุฆููุ ุฎุตูุตูุง ูู ุงูุฃู
ุงูู ุงููู ู
ูููุงุด ู
ุนุงู
ู ู
ุฌูุฒุฉ.
ุงูู
ุซูุฑ ููุงูุชู
ุงู
ู
ุด ู
ุฌุฑุฏ ู
ุญุงูุงุฉ Arduinoโฆ
ููู ุฅู ุงูุฐูุงุก ุงูุงุตุทูุงุนู ุจุฏุฃ ูุณููู ุจูุงุก ุชุฌุงุฑุจ ุชุนููู
ูุฉ ุชูุงุนููุฉ ูุงูุช ู
ุญุชุงุฌุฉ ููุช ูู
ุฌููุฏ ูุจูุฑูู.
๐ ุฌุฑูุจู ูุงุจุญุซ ุนู: Learn Arduino by Dilum Sanjaya
Don retweeted
Educational slide work with Gpt image 2.5
Prompt:
A professional educational infographic for a [Subject], designed in a modern "Terrestrial Life" series style. The layout features a large, realistic 3D central illustration of the [Subject] with anatomical labels like "Compound Eyes," "Thorax," and "Abdomen" using thin pointer lines. The color palette is clean with soft beige and muted tones. The composition includes multiple data modules: a "Quick Profile" sidebar, a "Top 5 Amazing Facts" list, a "Size Comparison" chart against a human silhouette, and a "Knowledge Score" star rating system. Include a "Detail Focus" section on the right with four square macro-photography close-ups of life stages or specific features. The bottom features "Habitat" and "Diet" icons, a "Conservation Status" slider, and a small "Did You Know?" footer. High resolution, crisp typography, clean vector lines, and a professional scientific journal aesthetic.
๐ค Made with AI
APInex is giving GPT-6 Luna, DeepSeek V4 Pro, Gemini 3.8 Flash, Kimi K3 and 15+ more for FREEE
no card needed, 3M free tokens per day on free-category models
what you get:
> GPT-6 Luna free
> DeepSeek V4 Pro free
> DeepSeek V4 Flash free
> GLM 5.3 Flash free
> Qwen 3.8 Max free
> Gemini 3.8 Flash free
> Gemini 3.1 Pro free
> Kimi K3 free
> Claude Sonnet 4.6 free
> Claude Opus 4.6 free
> MiMo, MiniMax, Jev, Hy4 free too
> plus paid models from $0.04/1M
how to claim (under 1 min):
step 1: go to apinex.bond
step 2: sign up and grab your API key
step 3: set base URL to apinex.bond/v1
works in any OpenAI-compatible client, Cursor, Claude Code, Codex, custom scripts
step 4: start prompting
important:
> this is a third-party proxy so don't send any sensitive data through it
> 3M free tokens per day on free models only, not unlimited
> free access can change anytime
no card, no plan, just use it
Don retweeted
GLM 5.3 UNCENSORED is FREE? ๐ณ
Hereโs whatโs being offered on XPLabs:
โ GLM 5.3 Large (uncensored)
โ 1.05M token context window
โ 60 tokens/sec
Get your API key here:
platform.xplabs.ai
Go test it ๐
Don retweeted
็ดๆฅๆพๅผ Seedance 2.5 ๅ้ฃไบ็ฆไบบ็ skill ๅง๏ผ
็ฐๅจๅช่ฆ Opus 5.5 + MiniMax H3๏ผๆ้ณไธๅจ่พๅ ไธ่ต็่ฟ็ง้ญๆงMV๏ผไธไธชไบบๅ ๅๅ้ๅฐฑ่ฝๆ ่้ไบงใ
ไบบ็ฉๅจๆๅ้ๅคด่ดจๆ็ดๆฅ้็ปดๆๅป๏ผๆ นๆฌไธ้่ฆไปปไฝ็ๅญฆ่ฐๅใ
Meet Oh-My-Hermes
I burned 200B tokens tuning my Hermes Agent setup, and now you can get all of it with a one-line install.
It comes with 150+ skills, a long-term memory system that lasts twice as long, graph engineering, and memory-management skills. It also includes subagent routing across model chains, plus optimizations like parallel tool calling and evals.
You don't need to do much, though. Just install it and give it a task. Everything is optimized to route automatically. Hermes Agent is excellent, and I love this technology.
I put a lot into making it really good, then open-sourced it so you can enjoy it right away. Meet oh-my-hermes.
GitHub: github.com/rlaope/oh-my-hermโฆ
#hermes
Don retweeted
We just open-sourced 1,300+ 3D models.
All 39 GB are free to download on Hugging Face.
huggingface.co/datasets/scenโฆ
> made with Hitem3D, Meshy, Rodin, Tripo, Claude Opus 5.5 3D and GPT-6 Astra 3D, which all run on Scenario
> includes the input images, prompts and settings that made them
> GLBs up to 8K textures, native Blender files from Opus and Astra, CC BY 4.0
Don retweeted
this is f*cking brilliant...
a 16-year-old CS student in China figured out how to run 300 Grok Bots for less than $0.02 per bot per week.
the same swarm could cost $4,500 a week.
he eliminated pointless status checks, stopped rereading entire chat histories, and killed endless retry loops.
now most bots only wake up when there's actual work to do.
Here 20 GitHub repos he used to make the setup cheaper:
01 Crawl4AI โ turn web pages into clean Markdown before analysis, reducing the navigation menus and page clutter your bot has to read
github.com/unclecode/crawl4aโฆ
02 Firecrawl โ collect web content as Markdown or structured data so your workflow can select the fields it actually needs
github.com/firecrawl/firecraโฆ
03 Chonkie โ split long documents into manageable chunks so retrieval can select relevant passages instead of attaching the whole document
github.com/feyninc/chonkie
04 FlagEmbedding โ rerank retrieved passages before generation, keeping the strongest evidence and dropping irrelevant matches from the prompt
github.com/FlagOpen/FlagEmbeโฆ
05 LLMLingua โ compress lengthy inputs before the model reads them. preserve the facts, constraints, and qualifications your task depends on
github.com/microsoft/LLMLingโฆ
06 RTK โ compress common command outputs before they enter the conversation, keeping repetitive logs from swallowing the useful context
github.com/rtk-ai/rtk
07 GPTCache โ reuse suitable answers to similar requests instead of generating them again. define matching and freshness rules around the task
github.com/zilliztech/GPTCacโฆ
08 Portkey Gateway โ cache matching API responses behind a shared gateway, letting connected workflows reuse answers across repeated requests
github.com/Portkey-AI/gatewaโฆ
09 Prefect โ cache successful task results and reuse them when the configured inputs match, avoiding unnecessary reruns of completed workflow steps
github.com/PrefectHQ/prefect
10 Mem0 โ store and retrieve relevant facts across runs so each assignment can start with selected memory instead of the entire conversation
github.com/mem0ai/mem0
11 Graphiti โ keep changing facts and relationships in a searchable graph, then retrieve the relevant context instead of replaying the event history
github.com/getzep/graphiti
12 requests-cache โ keep fetched responses with expiry rules, then let your scripts reuse valid data before asking the bot to investigate again
github.com/requests-cache/reโฆ
13 Hishel โ add HTTP caching and revalidation to your fetching tools, keeping unchanged responses out of repeated download-and-analysis cycles
github.com/karpetrosyan/hishโฆ
14 APScheduler โ schedule lightweight checks in Python and batch nonurgent work before handing useful updates to the agent
github.com/agronholm/apschedโฆ
15 Celery โ put background jobs on a worker queue so code handles waiting and dispatch while model calls happen inside the tasks that need them
github.com/celery/celery
16 PyBreaker โ pause calls to a repeatedly failing service after a configured threshold, stopping one broken dependency from generating endless attempts
github.com/danielfm/pybreakeโฆ
17 LiteLLM โ track spending and set budgets for connected API calls before one runaway workflow eats the whole allowance
github.com/BerriAI/litellm
18 RouteLLM โ route simpler API requests to a cheaper model and reserve the stronger one for work that needs it
github.com/lm-sys/RouteLLM
19 Semantic Router โ match requests to predefined workflows using local embeddings instead of paying a large model to decide every next step
github.com/aurelio-labs/semaโฆ
20 Phoenix โ trace your instrumented AI workflow, inspect repeated calls, and compare changes against output quality before keeping an โoptimizationโ
github.com/Arize-ai/phoenix
connect the tools your workflow needs through the terminal, MCP, or your own code. route API calls through the gateway or router you choose so its controls actually apply
start with the biggest leak: oversized inputs, repeated research, empty checks, or failed operations that keep restarting
filter before reading โ reuse before generating โ check for changes โ stop failed loops
then measure completed work against total usage, including the tools running around your bot
the full course below shows how to put the workflow together โ
Don retweeted
Create these 6 files before you start vibe coding:
โข PRD.md: what you're building and for whom
โข ARCHITECTURE.md: stack, folders, data flow
โข DESIGN.md: colors, fonts, components, vibe
โข RULES.md: coding style and what the AI must never do
โข TASKS.md: small steps, one at a time
โข PROGRESS.md: what's done, what broke, what's next
No files = the AI guesses.
6 files = the AI follows your plan.
10 minutes of writing saves 10 hours of fixing.
Bookmark this before your next build.
Don retweeted
The creator of Claude Code says there's no secret to prompting. His whole method fits in 3 lines
Boris Cherny says prompt wording mattered a lot back in the Sonnet 3.5 days. Now Claude only needs to know 3 things:
1. What you want it to do.
2. How much effort to spend.
3. How to check it did the right thing.
He showed a real prompt that uses all 3. He asked Opus 5.5 for an interactive website about a podcast episode:
The goal: "narrate the entire episode, focus on the business wisdom."
The effort: "use lots of tokens."
The check: "iterate till you're proud of it."
He also named the look he wanted: "New Yorker or NYT data viz vibes."
No role-play or templates. One paragraph, the way you'd brief a coworker.
I made a prompt that rewrites any request using his method. It's on the image.
Don retweeted
THIS IS F*CKING INSANE
SpaceXAI just dropped 146 Grok Bot templates worth $29,200 for FREE
bots like these basically cost $50โ$200 each. and thatโs just the official collection. GitHub already has 700+ bots, including complete teams with specialist roles, ready-made handoffs, and separate verifiers
20 GitHub projects you should open first:
01 Agent Org Chart โ ready-made team structures for engineering, marketing, support, and sales. pick the organization your job needs instead of inventing every role
github.com/serenakeyitan/ageโฆ
02 Grok Factory โ one Firstmate routes software, research, and general work to the right specialists, then brings back reports or reviewed pull requests
github.com/jaredtrichard/groโฆ
03 multiBot โ creates purpose-built teammates that delegate heavy work to coding CLIs, keeping Grok Bot focused on coordination and returning the result
github.com/simo255/multiBot
04 Grok Bot Architecture โ a blueprint for a chief of staff, specialist bots, structured handoffs, connected tools, and human approval points on one shared computer
github.com/tiagovilasboas/grโฆ
05 Foreman โ inspects a hosted bot crew, surfaces stalled work, and records evidence behind completion claims. a separate checker supplies the passing verdict
github.com/Archive228/foremaโฆ
06 Grok Bot Second Brain โ a five-bot setup with Conductor, Capture, Memory, Ops, and Research, sharing a knowledge vault and defined responsibilities
github.com/mKay00/grok-bot-sโฆ
07 grokbot-skills โ reusable skills for debugging, brainstorming, writing, and observing tasks, with upstream sources and licenses preserved
github.com/jeremybrasher/groโฆ
08 grokbot-x โ an X content workflow that scouts posts, prepares drafts, publishes through Typefully, and uses logged results to evaluate changes to its writing skills
github.com/YannisKiefer/grokโฆ
09 Restaurant Scout โ a specialist setup for finding food brands and creators, preparing shoppable-content scripts, and organizing the findings into a catalog workflow
github.com/mykemueller1-ctrlโฆ
10 Grok Bot Shopping โ shopping skills for product search, merchant checkout, Shopify discount-code tests, and order workflows, plus an optional Buyer bot
github.com/steve228uk/grok-bโฆ
11 PhoneZero โ gives Grok Bot a phone workflow for tasks like restaurant bookings. it prepares the call plan, waits for approval, and reports the outcome
github.com/function1st/Phoneโฆ
12 Unlist โ a privacy assistant playbook for people-search opt-outs, with site records, letter generation, submission logs, and follow-up tracking
github.com/shawnyeager/unlisโฆ
13 Grok Bot Gateway โ lets coding agents and scripts list bots, read conversations, and send tasks through a gateway bot using a webhook routine
github.com/dimpurr/grok-bot-โฆ
14 grokbot-queue โ queues and dispatches tasks across multiple Grok Bots, then collects their results using SSH and unofficial desktop automation
github.com/ShuhangGe/grokbotโฆ
15 Thin Grok Bot โ a delegation skill that keeps the bot team focused on routing while deeper builds and investigations run through coding CLIs or cloud agents
github.com/Luca-Blight/thin-โฆ
16 BOTROSTER โ a separate self-hosted alternative with persistent named teammates, shared files, a browser, scheduled work, and approval controls
github.com/mandarwagh9/botroโฆ
17 Root Agent โ a coordinator that determines which specialists a request needs, manages assignments, and hands domain work to leads
github.com/MrBekoX/root-agenโฆ
18 Grok Bot Profiles โ four focused roles: Spec Writer, Bug Reproducer, PR Producer, and PR Verifier. implementation and verification stay in separate conversations
github.com/HAEGONG/grok-bot-โฆ
19 Grok Bot Templates โ 49 templates with defined jobs, outputs, skills, routines, and boundaries, plus team setups you can adapt to your work
github.com/cobusgreyling/groโฆ
20 HyperGrok Trading Desk โ seven bots covering market data, research, strategy, risk, execution, and review. starts in research mode; live trades require your approval
github.com/galleonlabs/hyperโฆ
give the first team a job with an obvious finish line: one researched brief, one reviewed PR, or one prepared batch of drafts
then check how much work you actually accepted and what it cost to produce. a larger roster earns its place when it improves that result
the setup can be free. paying several bots to repeat the same investigation still costs you
save this before you spend another weekend building a workflow that already exists
the article below shows how to keep context smaller, reuse completed work, and contain retries so more of your Grok Bot budget reaches the finished result โ
Don retweeted
Here's what you will do;
1/ Go to telusinternational. com
2/ Register an account
3/ Get approved
4/ Review content and evaluate search results
5/ Get paid $12 to $20/hr
6/ Used by google, microsoft, and meta
7/ Stable work every month
Well thank me now๐.
HOLY SH*T, ELON MUSK PUT SPACEXAI'S BEST ENGINEERS ON A LIVE STREAM TO SHOW EXACTLY HOW TO BUILD A COMPANY WITH GROK BOTS
they start from an empty github org and zero bots. 72 hours, live.
how to use grok bot, from their demo:
step 1: make one bot per job, not one chat per task
step 2: tell it the result you want, voice works too
step 3: set approval rules, e.g. ask me before sending any email
step 4: show it a task once on screen, it saves it as a skill
step 5: add a routine, e.g. every morning at 9 it sends you a summary
step 6: if it refuses or asks questions, teach it, it keeps that in memory
the parts worth watching:
11:29 - the first hires: which bots they pick
20:23 - building a bot from scratch with one voice prompt
22:54 - teaching a bot a task by doing it once
25:21 - setting up a 9 am routine
save this and study the article below, it has ready-made grok bot configs you can copy โ
Don retweeted
๐ Faceless YouTube (Documentaries)
โ
โโโ ๐ Niche & Topic Selection
โ โโโ ๐ High-Retention Documentary Niches
โ โโโ ๐ Evergreen vs Trend-Based Topics
โ โโโ ๐ Competitor Channel Breakdown
โ โโโ ๐ Audience Psychology (Curiosity + Emotion)
โ
โโโ ๐ Research System
โ โโโ ๐ Source Gathering Workflow
โ โโโ ๐ Fact-Checking & Accuracy Systems
โ โโโ ๐ Story Angle Development
โ โโโ ๐ Research Prompt Libraries
โ
โโโ ๐ Script Frameworks
โ โโโ ๐ Hook Structures (Curiosity Gaps)
โ โโโ ๐ Narrative Arcs for Documentaries
โ โโโ ๐ Tension & Payoff Timing
โ โโโ ๐ Cliffhanger & Retention Techniques
โ โโโ ๐ AI Script Prompts for Docs
โ
โโโ ๐ Visual Storytelling
โ โโโ ๐ B-Roll Sourcing & Licensing
โ โโโ ๐ AI Image + Video Generation
โ โโโ ๐ Stock Footage Workflows
โ โโโ ๐ Archival Footage Systems
โ โโโ ๐ Scene Composition Rules
โ
โโโ ๐ Voiceover & Narration
โ โโโ ๐ AI Voice Selection (Tone Matching)
โ โโโ ๐ Pacing & Emotion Control
โ โโโ ๐ Script-to-Voice Alignment
โ โโโ ๐ Audio Cleanup & Mixing
โ
โโโ ๐ Editing & Packaging
โ โโโ ๐ Documentary Editing Templates
โ โโโ ๐ Pacing for High Retention
โ โโโ ๐ Text Overlays & Motion Graphics
โ โโโ ๐ Music & Sound Design Systems
โ โโโ ๐ Color Grading Styles
โ
โโโ ๐ Thumbnails & Titles
โ โโโ ๐ Documentary CTR Formulas
โ โโโ ๐ Curiosity-Driven Thumbnails
โ โโโ ๐ Title Hooks That Work
โ โโโ ๐ A/B Testing Systems
โ
โโโ ๐ Growth Engine
โ โโโ ๐ YouTube SEO for Documentaries
โ โโโ ๐ Titles & Descriptions That Convert
โ โโโ ๐ Upload Cadence & Series Strategy
โ โโโ ๐ Analytics That Matter
โ
โโโ ๐ Monetization
โ โโโ ๐ AdSense Optimization
โ โโโ ๐ Digital Products Tied to Niches
โ โโโ ๐ Affiliate Offers (Tools, Books, Courses)
โ โโโ ๐ Channel Memberships / Community
โ โโโ ๐ Scaling to Multiple Doc Channels
โ
โโโ ๐ Automation & Systems
โโโ ๐ Full Faceless Doc Workflow
โโโ ๐ Content Pipeline SOPs
โโโ ๐ Prompt Libraries
โโโ ๐ Outsourcing Rules
โโโ ๐ Scaling Multiple Channels
๐ Save this
Don retweeted
I open-sourced my viral Head of Content Grok Bot.
This is the team I used to generate 2.2M impressions in October.
(bookmark so you don't lose this)
This template will:
โข Launch your Head of Content Bot
โข Build your brand strategy (voice, tone, positioning)
โข Deploy 10+ content subagents tailored to your needs
โข Walk you through all MCP integrations (connecting your ๐ account, Notion content database, etc.)
โข Build your content agent skills & necessary context
I got a lot of requests for this. Hope you guys enjoy!
Save: x.ai/bot/WWdl6r61XsoZR3nyXwLโฆ



















































