Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

DOG BLADE SWORD SHOWCASE🐶⚔️ M1 - The same as Dark Blade Z Skill - Small dash leaving behind green afterimages while performing multiple slashes X Skill - You turn into a doghouse knocking back your enemies with an explosion after a while (immune to stuns). #Roblox #BloxFruits

Blox_FruitsNews's profile picture

BloxFruitsNews

51,431 subscribers

21,049 Aufrufe • vor 2 Monaten •via X (Twitter)

Gaming#Roblox#BloxFruits
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Strike fear into your enemies, and illuminate them as they fall to your blade ⚔️ The Wings of the Red Griffin Back Trophy will send a surge of energy through your wings as you cut down your foes 🪽 Collect yours with the Deluxe Battle Pass during the Season of Infernal Chaos 🔥
0:14

Sensitive content

Strike fear into your enemies, and illuminate them as they fall to your blade ⚔️ The Wings of the Red Griffin Back Trophy will send a surge of energy through your wings as you cut down your foes 🪽 Collect yours with the Deluxe Battle Pass during the Season of Infernal Chaos 🔥

Diablo

80,893 Aufrufe • vor 1 Jahr

Sandrone E Skill Dash Cancel Tech The standard Sandrone rotation revolves around holding basic attack and pressing E when the bar drains, this will put you back into a charged attack after the E skill animation is done - a way to optimize this is to press E directly after the 3rd Stellar-Conduct hit. This tech involves adding a dash cancel to the E animation, causing the E animation to be interrupted by the dash, with the dash then being overwritten by the still-held charged attack. Note that cancelling the E skill too early will cause her to not drain enough heat for a third Stellar-Conduct shot. This tech requires you to hit a sweet spot between cancelling her E fast enough to save time, while also not doing it too fast as to lose heat drain and miss your third shot before overheat on the next charged attack! -Via Lakkaberry #GenshinImpact
0:14

Sandrone E Skill Dash Cancel Tech The standard Sandrone rotation revolves around holding basic attack and pressing E when the bar drains, this will put you back into a charged attack after the E skill animation is done - a way to optimize this is to press E directly after the 3rd Stellar-Conduct hit. This tech involves adding a dash cancel to the E animation, causing the E animation to be interrupted by the dash, with the dash then being overwritten by the still-held charged attack. Note that cancelling the E skill too early will cause her to not drain enough heat for a third Stellar-Conduct shot. This tech requires you to hit a sweet spot between cancelling her E fast enough to save time, while also not doing it too fast as to lose heat drain and miss your third shot before overheat on the next charged attack! -Via Lakkaberry #GenshinImpact

Genshin Universe

63,931 Aufrufe • vor 4 Monaten

Created on seedance 2.0 Prompt:Hyper-realistic cinematic super-speed fight scene inside a massive abandoned industrial warehouse at night. Moonlight streams through broken factory windows, illuminating drifting dust and smoke. Rusted steel pillars, hanging chains, and scattered metal crates fill the dark industrial space. A dark warrior stands silently in the center as multiple enemies rush toward him from all directions. In an instant, he disappears. A violent burst of shadow energy explodes outward as the warrior teleports at extreme speed. Dark shadow trails and ghost-like afterimages remain in the air as he reappears behind an enemy and delivers a devastating punch that sends the attacker flying across the warehouse. Before the body hits the ground, the warrior vanishes again — teleporting across the battlefield in rapid flashes of shadow. Multiple shadow afterimages appear simultaneously, showing the path of his super-speed movement. He moves faster and faster, appearing above enemies, beside them, behind them — striking with powerful kicks and crushing blows. Each teleport creates a swirl of black smoke-like energy and flickering shadow fragments. Enemies try to surround him, but the warrior becomes almost impossible to track. The camera captures brief slow-motion moments as he reappears mid-air, delivering a spinning kick that launches an enemy into a steel pillar. Shockwaves ripple across the dusty floor. Chains swing violently from the ceiling. Metal crates shatter as enemies crash into them. The battlefield fills with streaks of shadow energy and fading afterimages from his super-speed teleportation. The camera smoothly tracks and circles the fight in a continuous cinematic shot, emphasizing the warrior’s impossible speed and supernatural movement. Epic dark atmosphere, hyper-realistic combat choreography, ultra detailed armor, shadow teleportation effects, extreme super speed movement, dramatic cinematic lighting, IMAX action movie style, 8K ultra realism.
0:15

Created on seedance 2.0 Prompt:Hyper-realistic cinematic super-speed fight scene inside a massive abandoned industrial warehouse at night. Moonlight streams through broken factory windows, illuminating drifting dust and smoke. Rusted steel pillars, hanging chains, and scattered metal crates fill the dark industrial space. A dark warrior stands silently in the center as multiple enemies rush toward him from all directions. In an instant, he disappears. A violent burst of shadow energy explodes outward as the warrior teleports at extreme speed. Dark shadow trails and ghost-like afterimages remain in the air as he reappears behind an enemy and delivers a devastating punch that sends the attacker flying across the warehouse. Before the body hits the ground, the warrior vanishes again — teleporting across the battlefield in rapid flashes of shadow. Multiple shadow afterimages appear simultaneously, showing the path of his super-speed movement. He moves faster and faster, appearing above enemies, beside them, behind them — striking with powerful kicks and crushing blows. Each teleport creates a swirl of black smoke-like energy and flickering shadow fragments. Enemies try to surround him, but the warrior becomes almost impossible to track. The camera captures brief slow-motion moments as he reappears mid-air, delivering a spinning kick that launches an enemy into a steel pillar. Shockwaves ripple across the dusty floor. Chains swing violently from the ceiling. Metal crates shatter as enemies crash into them. The battlefield fills with streaks of shadow energy and fading afterimages from his super-speed teleportation. The camera smoothly tracks and circles the fight in a continuous cinematic shot, emphasizing the warrior’s impossible speed and supernatural movement. Epic dark atmosphere, hyper-realistic combat choreography, ultra detailed armor, shadow teleportation effects, extreme super speed movement, dramatic cinematic lighting, IMAX action movie style, 8K ultra realism.

Nawal

16,383 Aufrufe • vor 3 Monaten

Created with Seedance 2.0 Prompt: Fast-paced, hyper-realistic cinematic action video of a young female soccer player with long dark hair, wearing glasses and a red and green Portugal-themed jersey, playing in a packed stadium. Sparks fly as she dribbles. The camera cuts to her rocketing into the sky above the clouds, where a massive glowing fire dragon coils around her as she performs an acrobatic bicycle kick on a soccer ball. Cut back to the stadium: she strikes the ball, sending a trail of intense fire toward the goal. The ball shatters a massive glass wall in front of the net, knocking the goalkeeper back into an explosion of smoke. The player lands gracefully back on the pitch, surrounded by a ring of fire, smiling as the fire dragon swirls majestically behind her. High contrast, dynamic lighting, 8k resolution, photorealistic textures, Unreal Engine 5 render style.
0:15

Created with Seedance 2.0 Prompt: Fast-paced, hyper-realistic cinematic action video of a young female soccer player with long dark hair, wearing glasses and a red and green Portugal-themed jersey, playing in a packed stadium. Sparks fly as she dribbles. The camera cuts to her rocketing into the sky above the clouds, where a massive glowing fire dragon coils around her as she performs an acrobatic bicycle kick on a soccer ball. Cut back to the stadium: she strikes the ball, sending a trail of intense fire toward the goal. The ball shatters a massive glass wall in front of the net, knocking the goalkeeper back into an explosion of smoke. The player lands gracefully back on the pitch, surrounded by a ring of fire, smiling as the fire dragon swirls majestically behind her. High contrast, dynamic lighting, 8k resolution, photorealistic textures, Unreal Engine 5 render style.

Zyrella

21,628 Aufrufe • vor 3 Monaten

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.
0:18

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

47,002 Aufrufe • vor 4 Monaten

This young girl in red and green plaid pajamas sits at the wheel of a red Kioti tractor and slowly drives it across the muddy yard while a calm chocolate lab sits right beside her on the seat like a passenger. The big rear tires churn up dirt as she steers and the dog just looks around completely relaxed with the whole rig bouncing along. You watch a little kid turn a real piece of farm equipment into her personal ride with the family dog along for the adventure. Do you think it is adorable and harmless fun that builds confidence in kids or do you say letting a child drive heavy machinery like that with a dog on board is straight up reckless and asking for an accident? Would you let your kid do the same or keep them far away from the controls?
0:11

This young girl in red and green plaid pajamas sits at the wheel of a red Kioti tractor and slowly drives it across the muddy yard while a calm chocolate lab sits right beside her on the seat like a passenger. The big rear tires churn up dirt as she steers and the dog just looks around completely relaxed with the whole rig bouncing along. You watch a little kid turn a real piece of farm equipment into her personal ride with the family dog along for the adventure. Do you think it is adorable and harmless fun that builds confidence in kids or do you say letting a child drive heavy machinery like that with a dog on board is straight up reckless and asking for an accident? Would you let your kid do the same or keep them far away from the controls?

Ryan Cey

77,028 Aufrufe • vor 5 Monaten

Seedence 2.0 on CapCut While the world ran from danger she walked toward it. Prompt: A young East Asian woman in her mid-20s stands calmly in a crowded modern shopping mall; suddenly a towering anime-style villain in dark dramatic armor appears causing chaos, people screaming and fleeing in all directions; the woman steps forward fearlessly, draws a sleek blade from her side, her eyes sharp and glowing slightly; she moves with fluid precision striking the villain with powerful calculated blows while pushing civilians to safety; final shot shows her standing victorious, villain on the ground, mall silent, civilians watching in awe behind her; then slowly the villain dissolves into shadow and disappears, the blade vanishes from her hand, the mall lights return to normal brightness, people resume walking and shopping as if nothing happened, the woman adjusts her bag on her shoulder and calmly continues walking through the mall alone — dramatic cinematic lighting, slow motion impact moments, handheld dynamic camera, high contrast color grade transitioning back to warm natural mall lighting, 16:9.
0:15

Seedence 2.0 on CapCut While the world ran from danger she walked toward it. Prompt: A young East Asian woman in her mid-20s stands calmly in a crowded modern shopping mall; suddenly a towering anime-style villain in dark dramatic armor appears causing chaos, people screaming and fleeing in all directions; the woman steps forward fearlessly, draws a sleek blade from her side, her eyes sharp and glowing slightly; she moves with fluid precision striking the villain with powerful calculated blows while pushing civilians to safety; final shot shows her standing victorious, villain on the ground, mall silent, civilians watching in awe behind her; then slowly the villain dissolves into shadow and disappears, the blade vanishes from her hand, the mall lights return to normal brightness, people resume walking and shopping as if nothing happened, the woman adjusts her bag on her shoulder and calmly continues walking through the mall alone — dramatic cinematic lighting, slow motion impact moments, handheld dynamic camera, high contrast color grade transitioning back to warm natural mall lighting, 16:9.

𝗦𝗮𝗻𝗶𝗮

12,722 Aufrufe • vor 3 Monaten

How to build a viral Web3 app in an afternoon using the ChainGPT AI skill for Claude Code. No coding experience required. I built Roast My Wallet. Paste any Ethereum wallet address, get a savage AI-generated roast of your trading history, a Degen Score out of 100, an on-chain report card, and three AI-generated NFT portraits. Here's exactly how it came together. Setup (3 minutes): 🔸Install Claude Code at 🔸Run /plugin install ChainGPT-org/chaingpt-claude-skill 🔸Get an API key at 🔸Type /chaingpt and describe what you want to build What the skill actually does: The ChainGPT skill doesn't just give you starter code. It knows the entire API. Every endpoint, every parameter, every credit cost, every error code. When I asked it to build the roast feature, it knew to call the LLM endpoint, how to stream the response back to the browser in real time, and how to handle errors automatically. I didn't look up a single thing. How it works under the hood: 1. Pulls real ETH balance and transaction count from the Ethereum blockchain 2. Feeds those numbers into ChainGPT's LLM and streams the roast back live 3. Calculates a Degen Score from your tx count vs balance ratio 4. Generates a report card with letter grades across Trading, Patience, Risk, Diamond Hands, and NGMI 5. Uses the roast text to generate three custom NFT portraits in parallel via VeloGen 6. Packages everything into a downloadable PNG card ready to post 7. Every feature came from describing what I wanted: 8. "Make the API key server-side." Done. 9. "Add an animated arc gauge for the degen score." Done. 10. "Generate NFT portraits using the roast text as context." Done. I never wrote a function or debugged an API response. I described outcomes. The ChainGPT skill handled the rest. If you can describe what you want to build, you can build it. Get your API key. Install the skill. /plugin install ChainGPT-org/chaingpt-claude-skill Anyone can build with ChainGPT AI!
0:11

How to build a viral Web3 app in an afternoon using the ChainGPT AI skill for Claude Code. No coding experience required. I built Roast My Wallet. Paste any Ethereum wallet address, get a savage AI-generated roast of your trading history, a Degen Score out of 100, an on-chain report card, and three AI-generated NFT portraits. Here's exactly how it came together. Setup (3 minutes): 🔸Install Claude Code at 🔸Run /plugin install ChainGPT-org/chaingpt-claude-skill 🔸Get an API key at 🔸Type /chaingpt and describe what you want to build What the skill actually does: The ChainGPT skill doesn't just give you starter code. It knows the entire API. Every endpoint, every parameter, every credit cost, every error code. When I asked it to build the roast feature, it knew to call the LLM endpoint, how to stream the response back to the browser in real time, and how to handle errors automatically. I didn't look up a single thing. How it works under the hood: 1. Pulls real ETH balance and transaction count from the Ethereum blockchain 2. Feeds those numbers into ChainGPT's LLM and streams the roast back live 3. Calculates a Degen Score from your tx count vs balance ratio 4. Generates a report card with letter grades across Trading, Patience, Risk, Diamond Hands, and NGMI 5. Uses the roast text to generate three custom NFT portraits in parallel via VeloGen 6. Packages everything into a downloadable PNG card ready to post 7. Every feature came from describing what I wanted: 8. "Make the API key server-side." Done. 9. "Add an animated arc gauge for the degen score." Done. 10. "Generate NFT portraits using the roast text as context." Done. I never wrote a function or debugged an API response. I described outcomes. The ChainGPT skill handled the rest. If you can describe what you want to build, you can build it. Get your API key. Install the skill. /plugin install ChainGPT-org/chaingpt-claude-skill Anyone can build with ChainGPT AI!

ChainGPT

29,339 Aufrufe • vor 4 Monaten

This is the easiest way to make $10k/month with organic affiliate and AI Arcads launched an ai ugc studio that lets you build an entire army of hyper-real AI actors Then you turn any static image into a high-quality video showcasing any product go to TikTok and make an account + warm it up using arcads you can run an entirely AI UGC account using the same character over and over, making it seem like an authentic TT page Mix the content up with slideshows and videos with the same character Here's the AI stack gameplan: - Claude to help you write scripts - Arcads to generate an image of an AI girlie that fits your product demographic Scroll tiktok and save + download every video / slideshow you see made by clippers promoting a product (there's literally loads) Your going to find an offer on whop for making money online or spirituality and target it towards girls feed all these videos you scraped into a custom google gemini gem trained to deconstruct hooks / angles for you for easy hook inspiration + ideas Deconstruct the hooks, put them into Claude and ask it to give you hooks for the same style of video put for your products your promoting For the videos do caption and reaction + showcase formats Generate the reactions using the character you made in arc ads then manually record the showcasing of the product or proof of the product working Also for caption generate a 8-10 second video you can put text over Include your CTA in the video for reaction style and captions for caption style Plus generate images with the same character and make slideshows directed to your product Now rinse and repeat this make multiple accounts with multiple different avatars and print
0:14

This is the easiest way to make $10k/month with organic affiliate and AI Arcads launched an ai ugc studio that lets you build an entire army of hyper-real AI actors Then you turn any static image into a high-quality video showcasing any product go to TikTok and make an account + warm it up using arcads you can run an entirely AI UGC account using the same character over and over, making it seem like an authentic TT page Mix the content up with slideshows and videos with the same character Here's the AI stack gameplan: - Claude to help you write scripts - Arcads to generate an image of an AI girlie that fits your product demographic Scroll tiktok and save + download every video / slideshow you see made by clippers promoting a product (there's literally loads) Your going to find an offer on whop for making money online or spirituality and target it towards girls feed all these videos you scraped into a custom google gemini gem trained to deconstruct hooks / angles for you for easy hook inspiration + ideas Deconstruct the hooks, put them into Claude and ask it to give you hooks for the same style of video put for your products your promoting For the videos do caption and reaction + showcase formats Generate the reactions using the character you made in arc ads then manually record the showcasing of the product or proof of the product working Also for caption generate a 8-10 second video you can put text over Include your CTA in the video for reaction style and captions for caption style Plus generate images with the same character and make slideshows directed to your product Now rinse and repeat this make multiple accounts with multiple different avatars and print

Pounds

32,407 Aufrufe • vor 8 Monaten

Plumes of Salvation Amano Miyahi "Are you hurt? Let me tend to your wounds~" This pure white, feather-soft attire makes Amano Miyahi feel as though she might float away with every step... 🔥 Basic Attack Target takes damage equal to a certain amount of caster's ATK. 🗡️Special Skill The target takes damage equal to a certain amount of ATK. Bestow an ATK Boost equal to a certain amount of the caster's current ATK for 2 turns on all allies except the caster. Additionally, based on the target's stacks of Counter Mark: increase the ATK Boost by a certain percentage per stack, and remove 10 stack(s) of Counter Mark from the target. After casting the skill, inflict 4 stacks of Counter Mark on the target. Passive: When an ally deals attribute advantage damage to an enemy, inflict 1 stack of Soul Charm on the target for 2 turns. ⚔️Ultimate Skill Enter Universe's Manifestation state for 3 turns. Universe's Manifestation: During this state, increase the caster's ATK and allies' attribute advantage damage. [Event Exclusive Code]: aHbjRV4Jsg1 #RiseofEros #TribulationoftheGodofDesire #AmanoMiyahi
0:19

Sensitive content

Plumes of Salvation Amano Miyahi "Are you hurt? Let me tend to your wounds~" This pure white, feather-soft attire makes Amano Miyahi feel as though she might float away with every step... 🔥 Basic Attack Target takes damage equal to a certain amount of caster's ATK. 🗡️Special Skill The target takes damage equal to a certain amount of ATK. Bestow an ATK Boost equal to a certain amount of the caster's current ATK for 2 turns on all allies except the caster. Additionally, based on the target's stacks of Counter Mark: increase the ATK Boost by a certain percentage per stack, and remove 10 stack(s) of Counter Mark from the target. After casting the skill, inflict 4 stacks of Counter Mark on the target. Passive: When an ally deals attribute advantage damage to an enemy, inflict 1 stack of Soul Charm on the target for 2 turns. ⚔️Ultimate Skill Enter Universe's Manifestation state for 3 turns. Universe's Manifestation: During this state, increase the caster's ATK and allies' attribute advantage damage. [Event Exclusive Code]: aHbjRV4Jsg1 #RiseofEros #TribulationoftheGodofDesire #AmanoMiyahi

Rise of Eros

46,805 Aufrufe • vor 21 Tagen

After some discussion, I'm going to experiment with focusing on an almost 'heist-like' aspect to the game. When you first arrive the house is dark and the ghosts unbothered. As you make noise and create a disturbance the house slowly comes alive. (for example fuseboxes let you turn on the lights, but generate a burst of activity when flipped on) I think this might change the ghost hand dynamic. Maybe instead of an enemy that grabs you, and you break free from, they are instead a trap that when they grab you, the struggle is to not make noise while they're having their fun?
0:10

After some discussion, I'm going to experiment with focusing on an almost 'heist-like' aspect to the game. When you first arrive the house is dark and the ghosts unbothered. As you make noise and create a disturbance the house slowly comes alive. (for example fuseboxes let you turn on the lights, but generate a burst of activity when flipped on) I think this might change the ghost hand dynamic. Maybe instead of an enemy that grabs you, and you break free from, they are instead a trap that when they grab you, the struggle is to not make noise while they're having their fun?

SeraF

26,872 Aufrufe • vor 4 Monaten

Softmax vs Sigmoid ✍️ Interact 👉 = Softmax = Softmax is how deep networks turn raw scores into a probability distribution — the final layer of every classifier, and the core of every attention head in a transformer. To see what it does, picture five boba tea shops on the same block, all competing for your dollar. Five candidates: a, b, c, d, e — different chains, different brewing styles, different pearls. A boba reviewer hands you a 𝘤𝘩𝘦𝘸𝘪𝘯𝘦𝘴𝘴 𝘴𝘤𝘰𝘳𝘦 for each — higher means perfectly chewy "QQ" pearls with the right bite (ask a Taiwanese friend to find out what QQ means). Negative scores are real: mushy bobas, overcooked pearls, a batch left sitting too long. How do you turn five chewiness scores into an allocation that adds to a whole dollar? You could spend everything at the chewiest shop, but that ignores how good the runners-up are. Softmax is the smooth alternative. Read the diagram left to right. First, raise each score to e^{x} — this does two things: it turns negative chewiness into small positives, and it stretches the gaps between scores exponentially. Then sum all five into a single total Z. Finally, divide each e^{x} by Z to get a probability. The five probabilities add up to one, so you can read them as percentages of your dollar. The chewiest shop gets the biggest slice — but never the whole dollar. That's the point of softmax: it ranks confidently while still leaving room for the others. = Sigmoid = Sigmoid squashes any real number into a probability between 0 and 1 — the classic activation for binary classification, and still the gating function inside LSTMs and GRUs. Same boba block as the previous Softmax example, narrowed to just two contenders — a hot new shop `a` with chewiness score x, and your usual go-to `b` whose score is pinned at zero (the neutral baseline you've come to expect). Sigmoid is just softmax with two players, one of them pinned to zero. Read the diagram left to right. First, raise each score to e^{x} — for the usual shop `b` whose score is zero, this is just e^0 = 1 (the constant baseline). Then sum the two into a total Z. Finally, divide each e^{x} by Z to get a probability. The two probabilities add up to one — the new shop wins more of your dollar when its pearls get chewier, and your usual keeps the rest. That's the point of sigmoid: it turns a single chewiness score into a clean 0-to-1 chance you'll try the new place over your usual. --- AI Math, Algorithms, Architectures by hand ✍️ Subscribe to my 60K+ reader newsletter 👉
0:14

Softmax vs Sigmoid ✍️ Interact 👉 = Softmax = Softmax is how deep networks turn raw scores into a probability distribution — the final layer of every classifier, and the core of every attention head in a transformer. To see what it does, picture five boba tea shops on the same block, all competing for your dollar. Five candidates: a, b, c, d, e — different chains, different brewing styles, different pearls. A boba reviewer hands you a 𝘤𝘩𝘦𝘸𝘪𝘯𝘦𝘴𝘴 𝘴𝘤𝘰𝘳𝘦 for each — higher means perfectly chewy "QQ" pearls with the right bite (ask a Taiwanese friend to find out what QQ means). Negative scores are real: mushy bobas, overcooked pearls, a batch left sitting too long. How do you turn five chewiness scores into an allocation that adds to a whole dollar? You could spend everything at the chewiest shop, but that ignores how good the runners-up are. Softmax is the smooth alternative. Read the diagram left to right. First, raise each score to e^{x} — this does two things: it turns negative chewiness into small positives, and it stretches the gaps between scores exponentially. Then sum all five into a single total Z. Finally, divide each e^{x} by Z to get a probability. The five probabilities add up to one, so you can read them as percentages of your dollar. The chewiest shop gets the biggest slice — but never the whole dollar. That's the point of softmax: it ranks confidently while still leaving room for the others. = Sigmoid = Sigmoid squashes any real number into a probability between 0 and 1 — the classic activation for binary classification, and still the gating function inside LSTMs and GRUs. Same boba block as the previous Softmax example, narrowed to just two contenders — a hot new shop `a` with chewiness score x, and your usual go-to `b` whose score is pinned at zero (the neutral baseline you've come to expect). Sigmoid is just softmax with two players, one of them pinned to zero. Read the diagram left to right. First, raise each score to e^{x} — for the usual shop `b` whose score is zero, this is just e^0 = 1 (the constant baseline). Then sum the two into a total Z. Finally, divide each e^{x} by Z to get a probability. The two probabilities add up to one — the new shop wins more of your dollar when its pearls get chewier, and your usual keeps the rest. That's the point of sigmoid: it turns a single chewiness score into a clean 0-to-1 chance you'll try the new place over your usual. --- AI Math, Algorithms, Architectures by hand ✍️ Subscribe to my 60K+ reader newsletter 👉

Tom Yeh

74,503 Aufrufe • vor 4 Monaten

THESE 5 SKILLS TURN HERMES AGENT INTO A SELF-RUNNING POWERHOUSE - ON NOUS RESEARCH’S #1 AGENT ON OPENROUTER. Hermes already writes its own skills and remembers across sessions. These 5 from the community ecosystem push it further - drop them in ~/.hermes/skills/ and go. ANTHROPIC-CYBERSECURITY-SKILLS (4K★) by mukul975 · production the most comprehensive security skill pack in the ecosystem. what it adds: → 753+ structured cybersecurity skills mapped to MITRE ATT&CK → also covers NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF → turns Hermes into a recon + defense analyst, not a guesser → install: hermes skills install from the hub the workhorse of the list - start here. CHAINLINK-AGENT-SKILLS by Chainlink - official · production low profile, highest trust: it’s first-party from Chainlink itself. what it adds: → oracle network data, CCIP, smart-contract interaction skills → built on the spec - portable across clients → teaches the agent correct on-chain calls instead of hallucinated ABIs → official source, security-scanned on install stop letting the model guess your contract reads. HERMES-SKILL-FACTORY by Romanescu11 · beta the meta-layer - a skill that makes more skills. what it adds: → point it at any repetitive task → it auto-generates a reusable skill → stacks on top of Hermes’s own learning loop → turns your workflows into a self-growing skill library → install from the awesome-hermes-agent list this is what compounds your setup over time. AGENTCASH by Merit-Systems · beta the connector that gives your agent a wallet. what it adds: → access to 300+ premium APIs through one skill → pays for them via x402 or MPP - free USDC to start testing → web scraping, image gen, email sending - all behind one auth → a fresh Hermes + AgentCash alone is already dangerous the cleanest way to plug in paid tools. X-TWITTER-SCRAPER by Xquik-dev · beta drives typed X access through 43 narrow SKILL.md folders. what it adds: → reads (search, timelines, mentions, trends, bookmarks, for-you) → writes (post, DM, follow, profile) + bulk extraction (followers, lists, spaces) → AI composition: write-tweets, write-threads, optimize → security-scanned before it’s trusted feed its output straight into your scheduled briefings. BONUS - the registry itself: HERMESHUB by amanning3390. Browse, search, and install community skills with a 65+ rule security scanner - blocks prompt injection and data exfiltration before anything runs. Creator marketplace with x402/Stripe payments. hermes skills browse to start. If you install nothing else, wire up the hub. the stack in one line: hermeshub + skill-factory build & manage the library → cybersecurity + chainlink + agentcash + x-scraper give it real-world reach → Hermes runs it all on a $5 VPS while you sleep. which of these are you running? FULL HERMES SKILL-STACK PLAYBOOK 👇
0:14

THESE 5 SKILLS TURN HERMES AGENT INTO A SELF-RUNNING POWERHOUSE - ON NOUS RESEARCH’S #1 AGENT ON OPENROUTER. Hermes already writes its own skills and remembers across sessions. These 5 from the community ecosystem push it further - drop them in ~/.hermes/skills/ and go. ANTHROPIC-CYBERSECURITY-SKILLS (4K★) by mukul975 · production the most comprehensive security skill pack in the ecosystem. what it adds: → 753+ structured cybersecurity skills mapped to MITRE ATT&CK → also covers NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF → turns Hermes into a recon + defense analyst, not a guesser → install: hermes skills install from the hub the workhorse of the list - start here. CHAINLINK-AGENT-SKILLS by Chainlink - official · production low profile, highest trust: it’s first-party from Chainlink itself. what it adds: → oracle network data, CCIP, smart-contract interaction skills → built on the spec - portable across clients → teaches the agent correct on-chain calls instead of hallucinated ABIs → official source, security-scanned on install stop letting the model guess your contract reads. HERMES-SKILL-FACTORY by Romanescu11 · beta the meta-layer - a skill that makes more skills. what it adds: → point it at any repetitive task → it auto-generates a reusable skill → stacks on top of Hermes’s own learning loop → turns your workflows into a self-growing skill library → install from the awesome-hermes-agent list this is what compounds your setup over time. AGENTCASH by Merit-Systems · beta the connector that gives your agent a wallet. what it adds: → access to 300+ premium APIs through one skill → pays for them via x402 or MPP - free USDC to start testing → web scraping, image gen, email sending - all behind one auth → a fresh Hermes + AgentCash alone is already dangerous the cleanest way to plug in paid tools. X-TWITTER-SCRAPER by Xquik-dev · beta drives typed X access through 43 narrow SKILL.md folders. what it adds: → reads (search, timelines, mentions, trends, bookmarks, for-you) → writes (post, DM, follow, profile) + bulk extraction (followers, lists, spaces) → AI composition: write-tweets, write-threads, optimize → security-scanned before it’s trusted feed its output straight into your scheduled briefings. BONUS - the registry itself: HERMESHUB by amanning3390. Browse, search, and install community skills with a 65+ rule security scanner - blocks prompt injection and data exfiltration before anything runs. Creator marketplace with x402/Stripe payments. hermes skills browse to start. If you install nothing else, wire up the hub. the stack in one line: hermeshub + skill-factory build & manage the library → cybersecurity + chainlink + agentcash + x-scraper give it real-world reach → Hermes runs it all on a $5 VPS while you sleep. which of these are you running? FULL HERMES SKILL-STACK PLAYBOOK 👇

ZEUS⚡️

21,710 Aufrufe • vor 3 Monaten

Stop manually making flowcharts. Try this GitHub skill with Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.
0:12

Stop manually making flowcharts. Try this GitHub skill with Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.

Alex Veremeyenko

52,933 Aufrufe • vor 9 Tagen

I just built a Claude skill that writes 20 Meta ad hooks in 60 seconds 🤯 Give it your product, your audience, and your best-performing angles → it writes hooks across 10 proven frameworks, each one targeted at a specific customer pain point. All inside Claude Cowork. Perfect for DTC brands and agencies who are still writing hooks from scratch every time they need new creative — staring at a blank doc, scrolling competitors for inspiration, and recycling the same 3 angles because you ran out of ideas two weeks ago. If you're launching Meta Ads and your hook writing process looks like this — open a Google Doc, try to remember what worked last time, write 5 hooks that all sound the same, run them, 4 flop, go back to the doc, repeat ... This skill replaces the entire process: → You give it your product name, key benefits, and target customer → It writes hooks across 10 frameworks: problem-solution, curiosity gap, bold claim, social proof, before/after, us vs them, question, contrarian, urgency, and storytelling → Each hook targets a specific pain point — not generic "Shop now" copy → Generates 2 variations per framework so you have options to test → Outputs everything organized by framework with notes on when to use each one → Takes about 60 seconds No blank page. No recycling the same 3 angles. No writing 5 hooks that all sound like the same ad. What you get: → 20 hooks across 10 proven frameworks, ready to drop into your ads → Each hook written for a specific customer pain point, not a generic audience → Framework labels so you know which hook type you're testing → A reusable skill — run it for every new product, every new campaign, every new angle sprint → Works from a product brief — no API connection, no CSV export, no setup beyond installing the skill One product brief. 20 hooks. 60 seconds. I put together the full skill file plus a playbook showing how to install it, customize the frameworks, and run your first hook sprint. Want it for free? > Like this post > Comment "HOOKS" And I'll send it over (must be following so I can DM)
0:16

I just built a Claude skill that writes 20 Meta ad hooks in 60 seconds 🤯 Give it your product, your audience, and your best-performing angles → it writes hooks across 10 proven frameworks, each one targeted at a specific customer pain point. All inside Claude Cowork. Perfect for DTC brands and agencies who are still writing hooks from scratch every time they need new creative — staring at a blank doc, scrolling competitors for inspiration, and recycling the same 3 angles because you ran out of ideas two weeks ago. If you're launching Meta Ads and your hook writing process looks like this — open a Google Doc, try to remember what worked last time, write 5 hooks that all sound the same, run them, 4 flop, go back to the doc, repeat ... This skill replaces the entire process: → You give it your product name, key benefits, and target customer → It writes hooks across 10 frameworks: problem-solution, curiosity gap, bold claim, social proof, before/after, us vs them, question, contrarian, urgency, and storytelling → Each hook targets a specific pain point — not generic "Shop now" copy → Generates 2 variations per framework so you have options to test → Outputs everything organized by framework with notes on when to use each one → Takes about 60 seconds No blank page. No recycling the same 3 angles. No writing 5 hooks that all sound like the same ad. What you get: → 20 hooks across 10 proven frameworks, ready to drop into your ads → Each hook written for a specific customer pain point, not a generic audience → Framework labels so you know which hook type you're testing → A reusable skill — run it for every new product, every new campaign, every new angle sprint → Works from a product brief — no API connection, no CSV export, no setup beyond installing the skill One product brief. 20 hooks. 60 seconds. I put together the full skill file plus a playbook showing how to install it, customize the frameworks, and run your first hook sprint. Want it for free? > Like this post > Comment "HOOKS" And I'll send it over (must be following so I can DM)

Mike Futia

17,027 Aufrufe • vor 5 Monaten

I just built a Claude Cowork skill that turns your Google Ads data into a visual performance dashboard in 60 seconds 🤯 One prompt → campaign breakdowns, CPA trends, spend vs conversions charts, and hourly conversion patterns, all rendered as an interactive HTML dashboard you open in Chrome. All inside Claude Cowork. Perfect for DTC brands and agencies who are pulling Google Ads data into spreadsheets every week, manually building charts, and spending an hour formatting a report that's outdated by the time you send it. If you're managing Google Ads and your weekly reporting workflow looks like this — export a CSV, open Google Sheets, build a pivot table, copy the numbers into a slide deck, manually create charts, format everything, realize you forgot a campaign, start over ... This skill does the whole thing in one prompt: → Connects to your live Google Ads data via MCP → Pulls spend, conversions, CPA, ROAS, CTR across every campaign → Builds an interactive HTML dashboard → Summary cards at the top: total spend, total conversions, avg CPA, avg ROAS → Bar chart comparing spend vs conversions by campaign → CPA trend line over the last 30 days → Campaign table ranked by performance, color-coded green/yellow/red → Opens in Chrome: hover over charts, compare campaigns, screenshot for your team No spreadsheets. No manual chart building. No hour-long formatting sessions. What you get: → A visual dashboard from live data in under 60 seconds → Campaign performance you can actually see, not just read in a table → CPA trends that show you where things are heading, not just where they are → A dashboard you can screenshot and drop into Slack, a client report, or a team standup → Reusable — run it weekly and the data updates automatically One prompt. Live data. A finished dashboard you open in your browser. I put together a playbook with the full skill file, the setup, and the exact prompts to customize the dashboard for your account. Want it for free? > Like this post > Comment "DASH" And I'll send it over (must be following so I can DM)
0:11

I just built a Claude Cowork skill that turns your Google Ads data into a visual performance dashboard in 60 seconds 🤯 One prompt → campaign breakdowns, CPA trends, spend vs conversions charts, and hourly conversion patterns, all rendered as an interactive HTML dashboard you open in Chrome. All inside Claude Cowork. Perfect for DTC brands and agencies who are pulling Google Ads data into spreadsheets every week, manually building charts, and spending an hour formatting a report that's outdated by the time you send it. If you're managing Google Ads and your weekly reporting workflow looks like this — export a CSV, open Google Sheets, build a pivot table, copy the numbers into a slide deck, manually create charts, format everything, realize you forgot a campaign, start over ... This skill does the whole thing in one prompt: → Connects to your live Google Ads data via MCP → Pulls spend, conversions, CPA, ROAS, CTR across every campaign → Builds an interactive HTML dashboard → Summary cards at the top: total spend, total conversions, avg CPA, avg ROAS → Bar chart comparing spend vs conversions by campaign → CPA trend line over the last 30 days → Campaign table ranked by performance, color-coded green/yellow/red → Opens in Chrome: hover over charts, compare campaigns, screenshot for your team No spreadsheets. No manual chart building. No hour-long formatting sessions. What you get: → A visual dashboard from live data in under 60 seconds → Campaign performance you can actually see, not just read in a table → CPA trends that show you where things are heading, not just where they are → A dashboard you can screenshot and drop into Slack, a client report, or a team standup → Reusable — run it weekly and the data updates automatically One prompt. Live data. A finished dashboard you open in your browser. I put together a playbook with the full skill file, the setup, and the exact prompts to customize the dashboard for your account. Want it for free? > Like this post > Comment "DASH" And I'll send it over (must be following so I can DM)

Mike Futia

39,021 Aufrufe • vor 6 Monaten

Doomed Miriam "Young master, here is today's schedule, twenty-two tasks in total. Please confirm." As the embodiment of the perfect maid, Miriam is stern with others and utterly relentless with herself. Under her devoted service, even the most hopeless slacker can be forged into an elite! 🔥 Basic Attack The target takes damage equal to a certain amount of ATK. 🗡️ Special Skill The target takes damage equal to a certain amount of ATK, and bestow 1 stack of Pulse Sensation on caster. Passive: When the caster receives healing or status effects from active skills of other Personas, bestow 1 stack of Pulse Sensation on the caster. This effect can trigger at most once per skill. If the status effect is restricted by E.RES, it cannot be triggered. ⚔️ Ultimate Skill The target takes damage equal to a certain amount of ATK, and bestow 1 stack of Pulse Sensation on caster. If the caster has acquired 6 stacks of Pulse Sensation before the skill is cast, there will be 100% chance to inflict Confuse on the target for 1 turn. This will additionally increase this skill's damage buff. Remove all stacks of Pulse Sensation after this effect is triggered. Passive: At the start of the caster's turn, if her Pulse Sensation reaches 6 stacks, it will reset this skill's cooldown. [Event Exclusive Code]:KT1qgtQk53i #RiseofEros #MaidenWarfare #Miriam
0:19

Sensitive content

Doomed Miriam "Young master, here is today's schedule, twenty-two tasks in total. Please confirm." As the embodiment of the perfect maid, Miriam is stern with others and utterly relentless with herself. Under her devoted service, even the most hopeless slacker can be forged into an elite! 🔥 Basic Attack The target takes damage equal to a certain amount of ATK. 🗡️ Special Skill The target takes damage equal to a certain amount of ATK, and bestow 1 stack of Pulse Sensation on caster. Passive: When the caster receives healing or status effects from active skills of other Personas, bestow 1 stack of Pulse Sensation on the caster. This effect can trigger at most once per skill. If the status effect is restricted by E.RES, it cannot be triggered. ⚔️ Ultimate Skill The target takes damage equal to a certain amount of ATK, and bestow 1 stack of Pulse Sensation on caster. If the caster has acquired 6 stacks of Pulse Sensation before the skill is cast, there will be 100% chance to inflict Confuse on the target for 1 turn. This will additionally increase this skill's damage buff. Remove all stacks of Pulse Sensation after this effect is triggered. Passive: At the start of the caster's turn, if her Pulse Sensation reaches 6 stacks, it will reset this skill's cooldown. [Event Exclusive Code]:KT1qgtQk53i #RiseofEros #MaidenWarfare #Miriam

Rise of Eros

109,670 Aufrufe • vor 7 Monaten