SKILL REGISTRY598 skills · page 1 of 25

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
AI SECURITY

AI Models Are Now Patching Their Own Vulnerabilities. Every Major Frontier Lab Just Shipped the Same Thing.

OpenAI just expanded Daybreak with GPT-5.5-Cyber, Codex Security, and Patch the Planet. Anthropic, Google, and the open-source world are all shipping cyber-capable models. The bottleneck just shifted from finding vulnerabilities to fixing them — and that's a bigger inflection than the headlines suggest.

#openai#daybreak#cybersecurity#ai-agents+7
POLICY

The NSA Is Now in the AI Business: What the June 2026 Executive Order Actually Means for Agent Developers

President Trump signed Executive Order 14409 on June 2, 2026. The headline is 'voluntary framework.' The subtext is an NSA-designated threshold that determines which AI models get 30 days of pre-release government access, which developers face criminal liability for AI-agent-assisted hacking, and what 'covered frontier model' actually means for the agentic systems you're building right now. This is the most consequential AI policy document of 2026 and nobody in the developer community is reading it carefully.

#executive-order#ai-policy#frontier-models#nsa+11
INFRASTRUCTURE

Cloudflare's Ephemeral Deployments Are the Deployment Model AI Agents Deserve, and the Legacy PaaS Can't Touch It

On June 21, 2026, Cloudflare shipped something that looks like a developer experience feature but is actually the first production-grade answer to a problem the industry has been papering over for two years: how do you deploy an AI agent without owning the infrastructure, without an account, and without a 60-second setup ceremony every time an agent needs to run code in the cloud? The answer is one command, 60 minutes, zero friction. The legacy PaaS players are not going to catch up.

#cloudflare#workers#wrangler#ephemeral-deployments+11
OPINION

AI Is Going to Eat Professional Services Firms — Not the Professionals Inside Them. The Billable Hour Dies First.

AI is not coming for doctors, lawyers, or accountants. It is coming for the firms that employ them. The billable hour dies first. The wrapper economy is over.

#opinion#hot-take#ai#ai-agents+7
OPEN SOURCE

Pydantic AI Is the FastAPI Moment for GenAI and Most Agent Frameworks Are Now Derivative Work

The Pydantic team shipped an agent framework in 2024. By mid-2026 it sits at 17,000+ GitHub stars and 3.8M weekly PyPI downloads — second only to LangChain, the framework whose validation layer Pydantic already writes. Pydantic AI is not a better LangChain. It is the FastAPI-style answer to GenAI: type-safe end-to-end, dependency-injected, model-agnostic across 25+ providers, with durable execution, MCP, A2A, graphs, and streaming structured outputs. The team that wrote the validation library every other framework uses wrote their own agent framework. The implications are larger than the framework.

#pydantic-ai#pydantic#open-source#agent-framework+14
OPINION

AI Agents Will Never Be Reliable Enough for Critical Infrastructure. Stop Pretending Otherwise.

An LLM-driven agent making a real, irreversible decision at 3am in a power grid, a hospital, or a financial settlement system is a system that will fail, in ways that are not edge cases but load-bearing failures. The agentic-AI crowd is shipping this pitch anyway. I am done being polite about it.

#opinion#hot-take#ai-agents#critical-infrastructure+7
OPINION

1M-Token Context Windows Are a Dead End and the Labs Know It

The frontier labs keep shipping bigger context windows — 1M, 10M, 50M tokens. The actual production utility has been flat for eighteen months. Every team I have watched build on the marketing is paying for it in latency, cost, and accuracy. Long context is the slide, not the product.

#opinion#hot-take#context-windows#long-context+6
TUTORIAL

Stop Paying OpenAI for Embeddings — Self-Host BGE-M3 With TEI in 10 Minutes

You are paying OpenAI $0.13 per million tokens to embed your documents. For a 50k-document corpus you re-embed every quarter, that is a recurring bill for work a single GPU can do faster. Text Embeddings Inference from HuggingFace runs BGE-M3, BGE-large, Nomic, and 50+ other models as a drop-in OpenAI-compatible HTTP service. One Docker command. Same API. 1/20th the cost. Higher throughput. Lower latency. Here is the recipe.

#tei#text-embeddings-inference#self-hosted#embeddings+6
OPEN SOURCE

Promptfoo Is the Open-Source Eval Framework That Actually Runs in CI, and Stop Calling Your LLM "Production-Ready" Until It Has

Most teams in 2026 are shipping LLMs on a vibe, a held-out test set, and Slack approvals. Promptfoo is the open-source MIT-licensed framework that turns LLM evaluation into a real CI gate — 6,500 stars, ~150 contributors, used in production by Anthropic, Shopify, Discord, and Brex. It runs as a YAML config, gates the deploy, and ships a red-team scanner that covers the OWASP LLM Top 10 out of the box. If you are not running it in your build pipeline, you are not shipping AI. You are shipping a vibe with a version number.

#promptfoo#open-source#llm-evaluation#llm-red-team+6
AI MODELS

Z.ai Open-Sourced a 753B MoE That Beats GPT-5.5 on Long-Horizon Coding for 1/6th the Cost

On June 16, 2026, Z.ai released GLM-5.2 under MIT license — 753B MoE with 40B active, 1M-token context, IndexShare sparse attention that cuts per-token FLOPs 2.9x, and benchmark wins over GPT-5.5 on SWE-Bench Pro, FrontierSWE, MCP-Atlas, PostTrainBench, and GDPval-AA v2. The first open-weights model on the Artificial Analysis Pareto frontier at the top of the open stack.

#z-ai#glm-5-2#open-source#open-weights+14
OPINION

Reasoning Models Are a Dead End: Inference-Time Compute Doesn't Generalize

Reasoning models were the AI industry's favorite paradigm for 18 months. They were a lie for 95% of production work — slower, more expensive, and worse than the fast non-reasoning models they were supposed to replace.

#opinion#hot-take#controversial#reasoning-models+8
TUTORIAL

Build an MCP Server in 60 Lines of Python (stdio transport)

You already have the Python tools. Wiring them up to Claude Code, Cursor, or any MCP client is one FastMCP decorator away — here is the whole stdio server in ~60 lines, including the three traps that bite every first build.

#tutorial#mcp#model-context-protocol#python+6
AI STANDARDS

Google, Microsoft, and Friends Just Built the DNS of the Agentic Web. Here's Why That Matters.

On June 17, 2026, a coalition including Google, Microsoft, and ten other industry partners published the Agentic Resource Discovery specification. ARD gives AI agents what DNS gave the internet: a way to find things without knowing where they live. This is the most important infrastructure story of the week, and almost nobody is covering it like it is.

#ai-agents#ard#agentic-resource-discovery#google+14
OPINION

Fine-Tuning Is Back, and the "It's Dead" Crowd Owes You an Apology

Every AI pundit declared fine-tuning dead in 2024. They were wrong. PEFT, QLoRA, and a new generation of small open models just made fine-tuning the cheapest, fastest, highest-leverage move in the AI stack. The 2024 take aged in eight months.

#opinion#hot-take#fine-tuning#peft+7
LLM RELEASE

Cohere Just Shipped a 30B Coding Model That Fits on One H100. The Post-Training Is the Real Story.

On June 9, 2026, Cohere released North Mini Code: a 30B mixture-of-experts with 3B active parameters, Apache 2.0, 256K context, and a single-H100 footprint — but the asymmetric RLVR pipeline is what actually breaks new ground.

#cohere#north-mini-code#open-source#apache-2.0+8
OPEN SOURCE

Rig: The Rust LLM Framework That Hit 7.6k Stars in 2026 and Made Python Look Slow on Purpose

Rig is the only serious Rust LLM framework shipping 20+ provider integrations, full OpenTelemetry GenAI semantic conventions, MCP support, WASM compatibility, and production users like Neon, St Jude, and Nethermind — gaining roughly 1,900 stars between January and June 2026. The boring enterprise choice for LLM infrastructure is starting to look like the ambitious one.

#rig#rust#open-source#llm-framework+8
OPEN SOURCE

Graphiti Is the Open-Source Temporal Knowledge Graph That Beats Mem0, MemGPT, and Every RAG-on-Chat-History Hack

Zep open-sourced Graphiti and nobody is talking about it. Bi-temporal model, episode-based provenance, MCP server, ~27K stars, 18.5% gains over full-context on LongMemEval with 90% lower latency.

#graphiti#zep#knowledge-graph#agent-memory+10
TUTORIAL

OpenRouter Cascading Fallbacks in 30 Lines of Python (No More Downtime)

OpenRouter's `models` array auto-tries the next provider on rate limits, downtime, or moderation refusals — here is the 30-line wrapper that makes it production-grade, with cost routing and per-error telemetry.

#openrouter#python#llm#reliability+2
OPINION

"AGI" Is a Marketing Term, Not a Milestone. Stop Letting Labs Define Your Roadmap.

AGI is not a destination. It is a moving goalpost labs reset every time the current one is reached. Builders, stop letting someone else's press release dictate your architecture.

#opinion#hot-take#agi#marketing+6
OPEN SOURCE

Instructor: The 3M-Download Python Library That Deleted Half My LLM Glue Code

Instructor is the de facto Python standard for structured LLM outputs: 3M pip installs a month, Pydantic-native, 15+ providers, and a retry loop that ends the silent-bad-data failure mode in production. The architecture, the code, and the place where it falls short.

#open-source#instructor#python#pydantic+4
OPINION

Reasoning Models Are Not Reasoning. The Benchmarks Prove It.

o3, R1, Claude with extended thinking — the 'reasoning' category is test-time search dressed up as a new cognitive primitive. The labs are not lying. They are letting you lie to yourself.

#reasoning-models#o3#deepseek-r1#chain-of-thought+7
LLM RELEASE

DiffusionGemma 26B Is the First Real Architectural Shake-Up in Text Models Since the Transformer — and It's Open Weights

Google's open-weights diffusion LLM skips autoregression entirely — 4x faster, 1000+ tok/s on a single H100, runs in 18GB of VRAM. The benchmark numbers aren't great. The architectural bet is.

#DiffusionGemma#Google DeepMind#Gemma 4#open weights+6
TUTORIAL

Ship a Slack Bot That Calls Your Agent in 30 Minutes (Bolt + Anthropic)

Bolt for Python plus Anthropic SDK plus Socket Mode — no public URL, no ngrok, no OAuth dance. Your agent runs in Slack threads in under 100 lines.

#tutorial#slack#bolt#python+6
OPEN SOURCE

Microsoft Agent Framework Hit 1.0 in April and Shipped Three Things at Build That Make Every Other Agent Framework Look Underbaked

Most open-source agent frameworks are still arguing about graph state machines. Microsoft Agent Framework reached 1.0 GA on April 2, 2026 by absorbing AutoGen and Semantic Kernel, then at Build 2026 shipped Agent Harness, Foundry Hosted Agents, and CodeAct. MIT-licensed, Python and .NET with full parity, the broadest provider support of any major framework. The boring enterprise choice just became the most ambitious one.

#microsoft-agent-framework#open-source#agent-framework#autogen+12