SKILL REGISTRY793 skills · page 1 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
LLM-RELEASE

GPT-5.6 Sol, Terra, and Luna: OpenAI Finally Built a Model Family Instead of a Model

July 9, 2026: OpenAI moves GPT-5.6 to GA — three tiers (Sol, Terra, Luna), 1M context, Programmatic Tool Calling, Ultra mode. The interesting story isn't the benchmarks. It's the structure.

#openai#gpt-5-6#gpt-5#llm-release+6
TUTORIAL

Block Dangerous Commands in Claude Code with a 20-Line Hook

Claude Code will happily `rm -rf` the wrong directory. Wire a 20-line `PreToolUse` hook that vets every Bash command against a denylist of foot-guns and exits non-zero to veto the dangerous ones. Twenty lines, no seatbelt excuses.

#tutorial#practical#claude-code#hooks+4
OPEN SOURCE

Portkey Is the LLM Gateway That Realized LiteLLM Stopped at 'Proxy' and Built the Real Control Plane

Every LLM gateway I've shipped in 18 months has been a glorified routing proxy with a config file. Portkey is the first open-source one that figured out the gateway layer is supposed to be a control plane, not a proxy.

#open source#portkey#llm-gateway#litellm+4
OPINION

Agent Benchmarks Are A Three-Card Monte Game And You Are The Mark

SWE-Bench, tau-Bench, GAIA, OSWorld, WebArena — every public agent leaderboard in 2026 is rigged carnival theatre. Labs know it. Your CFO does not. The score that matters is the one you run yourself on your own tickets.

#opinion#hot-take#agent-benchmarks#swe-bench+4
LLM RELEASES

Leanstral 1.5 Cracked 587 Putnam Problems for $4 Each. Formal Verification Just Got Cheap.

Mistral shipped Leanstral 1.5 — an Apache-2.0 open-weights MoE (119B total, 6.5B active) that solved 587 of 672 Putnam problems for ~$4 each, against Seed-Prover 1.5's $300+. Formal verification just became cheap.

#mistral#leanstral#formal-verification#lean-4+4
TUTORIAL

Cap Your LLM Spend With a Hard Kill Switch in 30 Lines

Pre-counting tokens stops the obvious cost incidents. It does not stop the agent loop that spins for two hours calling gpt-4o-mini 40,000 times because a JSON schema validator keeps returning 400. You need a hard kill switch — a process-level budget that aborts mid-stream when the meter passes the cap. Here is the build, 30 lines.

#tutorial#llm#cost#budget+5
OPINION

Prompt Engineering Is Not A Job Title. Stop Hiring For It.

Every 'Prompt Engineer — $250K + equity' LinkedIn post is a self-own. The job description is shallow, the skill ceiling is depressing, the vendors are writing the role to shift blame off their models, and the tooling that replaces hand-tuned prompting is shipping every six weeks. Hire an AI engineer. Retire the title.

#opinion#hot-take#prompt-engineering#hiring+3
LLM RELEASES

Grok 4.5 Costs $2 a Million Input Tokens. The Benchmark Doesn't Matter.

SpaceXAI shipped Grok 4.5 yesterday at $2 input / $6 output per million tokens — roughly 10x cheaper than Opus 4.8 per solved SWE-Bench task once you count the 4.2x token reduction. The real moat is the Cursor data flywheel, not the leaderboard.

#grok 4.5#xai#cursor#llm pricing+1
OPEN SOURCE

SGLang is the Open-Source Inference Runtime That Finally Treats Structured Output as a First-Class Citizen

Most LLM serving stacks bolt structured generation on top of a chat-completion engine. SGLang flips the script — a frontend DSL and runtime co-designed for branching, parallel, and constrained LLM programs. If your workload looks like an agent, a tree-of-thought, or a JSON-schema-heavy pipeline, it deserves a serious look.

#open source#llm#inference#sglang+3
TUTORIAL

Ship pgvector for Production Embedding Search

Stand up a Postgres + pgvector backend that indexes millions of embeddings and answers nearest-neighbor queries in milliseconds — with the exact schema, index choice, and a working query loop.

#tutorial#pgvector#postgres#embeddings+2
OPINION

Multi-Agent Systems in 2026 Are Mostly One Agent in a Trench Coat

Your fancy multi-agent orchestration is one LLM pretending to be a team. Stop shipping it. Stop selling it. Stop pretending the trench coat is full.

#opinion#hot-take#ai#agents
LLM RELEASES

Claude Sonnet 5 Is the Only LLM That Mattered This Week. Anthropic Just Made Opus a Hard Sell.

Anthropic shipped Claude Sonnet 5 on June 30 with near-Opus-4.8 agentic performance at one-fifth the price, and quietly rug-pulled every team still routing serious work to Opus. The tokenizer change is a 30% price hike nobody is talking about.

#claude#anthropic#sonnet-5#llm-release+4
AI ENGINEERING

MCP Is the USB-C AI Agents Have Been Waiting For

The Model Context Protocol went from Anthropic experiment to industry standard in six months. Here is what it actually gets right, where production implementations are still a mess, and what you should be doing today.

#mcp#model-context-protocol#anthropic#ai-agents+5
AI ENGINEERING

The 2026 Agent Runtime Stack: Why "Just a Loop" Beats Every Framework for 80% of What You're Building, the Five Exceptions That Actually Need LangGraph, Temporal, Restate, DBOS, or Hatchet, and the Stack I'd Ship on Monday Morning

Five frameworks I deleted in 2026 are good software. The sixth is 137 lines of Python handling 11M turns a week. Here is exactly when to use which runtime — and the 20-line agent.py you should have shipped instead of your agent platform.

#agent-runtime#langgraph#temporal#restate+6
AI ENGINEERING

Computer Use Agents Are Still Mostly Theater — And the 2026 Production Stack That Actually Works

The demos are real. The production systems are mostly theater. Here is the hard technical map of what computer use agents can actually do in July 2026, the three architectural approaches, the six failure modes that kill deployments, and the production stack with code that works.

#computer-use-agents#agentic-AI#desktop-automation#anthropic-computer-use+6
AI ENGINEERING

Agent Skills Are the New APIs: Why the SKILL.md Format Just Won, How the Marketplace Quietly Became the Largest Software Surface on Earth, and the Stack I'd Ship in July 2026

The skills economy is the new software supply chain. 180,000+ skills on the public registries, 1M+ in private use, growing 4,200/week on the public side and 25,000/week across enterprise marketplaces. The SKILL.md format is the universal agent skill artifact, the install path is one command, the four marketplaces that matter are Skills.sh, the Claude Skills Registry, Hugging Face Skills Hub, and Microsoft Copilot Studio. Here is the format, the install mechanics, the security model, the economics ($380M direct, $1.5B annualized), and the stack I'd ship Monday morning if I were a team building a real skill product this quarter.

#agent-skills#SKILL.md#skills-marketplace#skills.sh+6
AI ENGINEERING

Real-Time Voice Agents Are the New Default UI, and the Stack Most Teams Are Using Is Two Years Behind

Voice is the new default UI. The STT → LLM → TTS pipeline that 80% of teams are shipping is dead for production use. The right architecture in 2026 is end-to-end speech-to-speech with the model as the agent, and the four production systems I'd actually build on are OpenAI Realtime, Gemini Live, Kyutai Moshi, and Sesame CSM. Here is the full stack, the code, the latency benchmarks, and the cost numbers from four production deployments.

#voice-agents#speech-to-speech#OpenAI-Realtime#Gemini-Live+6
AI ENGINEERING

AI Browsers Killed the Search Bar: How Perplexity Comet, ChatGPT Atlas, Arc Search, and Google AI Mode Are Eating the Web's Oldest Interface — And Why Most Teams Are Building Them Backwards

The chat box is the new front door. The browser is the new agent runtime. Perplexity Comet, ChatGPT Atlas, and Google's AI Mode have crossed 100M daily users between them, and the architectural pattern most teams are shipping (sidebar AI on top of Chrome) is wrong. Here is the engineering stack I would build if I were shipping a consumer AI browser in July 2026: Chromium fork with native MCP, Rust agent loop in the browser process, three-tier model strategy (local / mid / frontier), and on-device user-controlled memory.

#AI-browsers#Perplexity-Comet#ChatGPT-Atlas#Arc-Search+6
AI ENGINEERING

WebGPU Just Killed the API-First AI Stack: Ship a 100% Browser-Side LLM Agent in 100 Lines (No Backend, No API Keys, No Cloud Bill)

WebGPU plus WebLLM plus transformers.js reached production in 2026. A 3B-parameter model now runs entirely in the browser, calls tools, and persists memory across sessions. The cloud is now the accelerator, not the runtime. Here is the full stack: 94 lines of TypeScript, a 4 GB model file, and zero API keys.

#WebGPU#WebLLM#transformers.js#browser-llm+6
OPEN SOURCE

SkyReels-V4 Is the First Open-Source Model That Generates Video and Audio Together, and the Dual-Stream MMDiT Is the Real Story

Open-source video models have been silent for two years. Skywork AI's SkyReels-V4 ships joint video and audio generation in a single forward pass at 1080p/32 FPS, and the dual-stream MMDiT architecture is a serious bet on independent unimodal objectives over the obvious cross-attention fusion everyone else tried first.

#open-source#skyreels-v4#skywork-ai#video-generation+7
LLM RELEASE

OpenAI's GPT-5.6 Ships Three Models, Zero Public Access: Sol, Terra, Luna and the New Government-Vetted Rollout

OpenAI dropped GPT-5.6 today — three tiers named Sol, Terra, and Luna at $5/$30, $2.50/$15, and $1/$6 per million tokens — and locked all of them behind a 'limited preview' for roughly 20 vetted partners at the U.S. government's request. The model is real, the benchmarks are real, and the rollout is the story.

#llm-release#june-2026#gpt-5-6#openai+6
NEWSLETTER

AI Agent News Roundup — Week of June 20, 2026

Seven stories that defined the week: Anthropic's models pulled mid-launch, three frontier models dropped in two weeks, Google bet its enterprise future on agents, and the unit economics of premium AI subscriptions started looking like a problem nobody wants to name.

#ai-news#newsletter#anthropic#openai+10
OPINION

Vector Databases Are Dead. SQL Won. Stop Betting on the Wrong Layer.

Pinecone, Weaviate, Qdrant, and the rest of the dedicated vector store layer are a 2022 bet that lost. Postgres swallowed them. The query you are paying $30k/month to run is a JOIN with an ORDER BY and a LIMIT.

#opinion#hot-take#vector-databases#postgres+3
OPEN SOURCE

Unsloth: The Triton-First Fine-Tuning Stack That Made PEFT a Weekend Project

Unsloth hit 2x faster training and 70% less VRAM by hand-writing Triton kernels for attention, RoPE, cross-entropy, RMS layernorm, MLP, and QKV — and then shipped a no-code web UI (Studio) in March 2026. With 500+ supported models, Apache 2.0, and a one-line GGUF export, it is the most disciplined open-source fine-tuning library shipping in 2026, and the boring infrastructure choice that just became the ambitious one.

#unsloth#triton#fine-tuning#open-source+11