SKILL REGISTRY793 skills · page 31 of 34

PAYLOADS
// INTELLIGENCE

Production-tested skills for AI agents. Every skill is security-scanned, tier-rated, and verified. Browse by ecosystem or category below.

Category
Ecosystem
Safety
TUTORIAL

Run a Private ChatGPT Clone on Your Laptop in 10 Minutes: Ollama + Open WebUI

Spin up a private ChatGPT clone on your laptop in 10 minutes with Ollama and Open WebUI. Zero data leaves your machine, zero subscription, full OpenAI-compatible API.

#tutorial#ollama#open-webui#local-llm+4
OPEN SOURCE

Steel.dev Quietly Became the Default Open-Source Browser API for AI Agents. Browserbase Should Be Worried.

Browserbase owns the narrative. Steel.dev owns the deploys. Apache-2.0, one Docker command, 7K stars, batteries-included sessions. The right browser harness in 2026 is the one you can run yourself.

#open-source#steel-dev#browser-api#ai-agents+7
OPINION

Vector Databases Are a Tax on Your Ignorance — Postgres Will Eat Them All by 2027

Pinecone, Weaviate, and Qdrant are a tax on your ignorance. pgvector with DiskANN does the same job on the Postgres instance already running your app — for one tenth the cost, with one tenth the latency. The vector database category is closing. Pay the migration tax now or keep funding someone else's Series C.

#opinion#hot-take#vector-database#postgres+8
OPINION

FineWeb-3's 15 Trillion Tokens Prove the LLM Industry Has Stopped Innovating on Data and Started Hoarding It

Hugging Face just shipped FineWeb-3: 15 trillion tokens. Six times the 2024 release, twice the indexed English web. The dataset is billed as progress. It is an admission — that the data play has shifted from engineering to extraction, and the labs are out of clever ideas.

#opinion#hot-take#ai#llm+6
OPINION

Fine-Tuning Is Dead for 95% of Use Cases. Stop Telling People to Fine-Tune.

Frontier APIs, prompt caching, distillation, and 1M-token context windows have made most custom LoRAs worse than calling Claude with a good system prompt. The fine-tuning cottage industry is selling 2023 infrastructure to a 2026 market.

#opinion#hot-take#fine-tuning#llm+4

Coding Assistants Are Making Software Engineers Worse — And Nobody In Management Wants to Say It

Velocity is up. Comprehension, debugging, and architectural judgment are collapsing. We are celebrating the wrong number.

#opinion#ai#hot-take#developer-tools+2

OpenAI Just Made Cybersecurity the Killer App for AI — And That's a Bigger Deal Than You Think

OpenAI dropped the full GPT-5.5-Cyber, a beefed-up Codex Security plugin, and a 'Patch the Planet' OSS initiative. The week's biggest LLM story.

#llm#ai#openai#cybersecurity+4
OPEN SOURCE

NVIDIA Dynamo Is the Open-Source Inference OS MoE Models Have Been Waiting For. Most Teams Will Still Pick vLLM and Wonder Why Their Bills Are High.

NVIDIA Dynamo, Apache-2.0: KV-aware routing, disaggregated prefill/decode, NIXL transfers. The inference OS MoE teams have been waiting for.

#open-source#nvidia#dynamo#inference+7
LLM RELEASE

Mistral OCR 4 Quietly Solved the Last Mile of RAG, and the RAG Stack Is Now Officially Rewritten

Mistral released OCR 4 on June 24: 170 languages, bounding boxes, typed blocks, confidence scores, $4 per 1,000 pages, 72% human-preference win rate. The boring last-mile RAG layer just became strategically valuable.

#mistral#ocr-4#ocr#document-intelligence+11
OPEN SOURCE

MetaGPT Is the Only Multi-Agent Framework That Took the SOP Seriously, and That's Why It Still Matters in 2026

Everyone has a multi-agent framework. Most reinvented the org chart without the part that actually made the company work. MetaGPT encoded Standardized Operating Procedures as the runtime — Code = SOP(Team) — and that single decision is more interesting than anything LangGraph, CrewAI, or AutoGen shipped in 2025.

#metagpt#multi-agent#open-source#ai-agents+5
AI MODELS

Gemini 3.5 Flash Just Inverted the Model Hierarchy, and Almost Nobody Noticed

Google shipped Gemini 3.5 Flash as GA at I/O on May 19 — default in the Gemini app and AI Mode in Search — beating Gemini 3.1 Pro on coding and agentic benchmarks at roughly 4x the speed. Then Sundar Pichai told the room to expect 3.5 Pro next month. The Flash-as-flagship pattern just got validated.

#gemini#google#llm#ai-models+1
TUTORIAL

Claude Extended Thinking With a Budget: The Cost Knob Anthropic Shipped in March 2026

Extended thinking is the single biggest token-spend lever on Claude, and most teams leave it set to 'as much as it wants.' That is the default. Anthropic shipped a `budget_tokens` field that caps how much Claude is allowed to think before it must answer. One parameter, 40 to 60 percent cost reduction on most agent workloads. Here is the recipe.

#tutorial#claude#extended-thinking#cost-optimization+4
TUTORIAL

Track Every LLM Token With One Python Decorator

Stop guessing where your LLM spend goes. One decorator wraps any LLM call and logs tokens, cost, and latency to a JSONL file you can tail in real time.

#tutorial#python#llm#observability+1
TUTORIAL

Cross-Encoder Reranking for RAG in 30 Lines of Python

Vector search gets you 80% there. Cross-encoder reranking closes the gap. Here's a 30-line Python implementation that lifts retrieval accuracy from ~62% to ~84% on a typical RAG benchmark.

#tutorial#rag#reranking#python+1
OPINION

Million-Token Context Windows Are a Crutch, Not a Solution

Every lab is racing to ship the longest context window — and every team building agents is paying 10x for 10% of the benefit. Long context is a workaround for a problem we refuse to solve: memory.

#opinion#hot-take#ai#llm+4
OPEN SOURCE

OXC Wants Your Build Pipeline. The Compiler Earns It, the LLM Features Don't.

The Rust-based JavaScript toolchain is the real deal — and the AI features bolted on top are exactly the kind of hype-driven engineering decisions I wish the ecosystem would stop making.

#open-source#rust#javascript#toolchain+2
OPEN SOURCE

NVIDIA Dynamo is the first inference stack built for MoE from day one

vLLM wasn't built for MoE. Dynamo is. That changes who wins the inference layer.

#open-source#ai-infrastructure#nvidia#llm-inference+2
LLM RELEASE

OpenAI Stopped Renting GPUs. The Chip Is Called Jalapeño.

OpenAI's first custom inference ASIC took nine months to design, claims 50% lower cost per token, and is targeting 1.3 gigawatts of deployment — this is the day AI stopped being a pure NVIDIA rental business.

#llm-release#openai#inference#silicon+2

Cut Streaming LLM Tail Latency with SSE: The 4 Knobs That Move p99

Your streaming LLM endpoint has 200ms median first-token latency and a 9-second p99. The model is fine — your streaming plumbing is buffering tokens it should be flushing. Four knobs fix it without touching the model server.

#tutorial#sse#streaming#latency+5

Your agent eval takes 6 hours. Here's the 200-line fix.

Three Python knobs — a semaphore, an append-only JSONL log, and a deterministic scorer — turn a 4-hour serial agent eval into a 12-minute parallel run with crash recovery. No Ray, no LangSmith bill.

#tutorial#llm#agents#evals+6

TensorZero Was the Best Open LLMOps Stack I'd Used, and the Repo Got Archived Overnight

11.5K stars, Rust, ~1% of global LLM API traffic, $7.3M seed. On June 12, 2026 the founders archived the GitHub repo without warning and walked away with half the capital. The product was not the problem. The category got eaten while they were still building.

#tensorzero#llmops#open-source#rust+5

Open-Source AI Is Dead — and the Labs Killed It On Purpose

The 'open-source AI caught up' narrative is wrong. The Western labs quit on it, the gap is structural, and the frontier is closed. China is the only game left — and even China is 8–10 months behind.

#opinion#hot-take#open-source#open-weights+7

Coding Agents Will Eat Mid-Level Engineers First, Not the Juniors

The smart money in 2026 is not on AI wiping out junior devs — it's on coding agents dissolving the 50% of staff engineers who are competent but unremarkable. The middle of the bell curve is ground zero.

#opinion#ai-agents#coding-agents#future-of-work+3

Huawei Just Open-Sourced a 92B/6B MoE on Ascend — And Gave Away the Training Ops

On June 30, 2026, Huawei dropped openPangu-2.0-Flash — a 92B-total/6B-active MoE with 512K context, 34T pretraining tokens, and a non-Apache license. SWE-bench Verified 63.1%, LiveCodeBench V6 85.1%, AIME 2026 98.1% w/ Python. The training stack is the real news.

#huawei#openpangu#pangu#ascend+8