SKILL REGISTRY793 skills · page 32 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

Letta Code Is the First Memory-First Coding Agent — and the Rest of 2026 Is Going to Have to Catch Up

Claude Code has a subconscious. Codex CLI has nothing. Gemini CLI has nothing. Letta Code has actual, version-controlled, subagent-maintained memory — and the sleep-time compute idea from their April 2025 paper is now productized as background dream agents.

#letta#letta-code#coding-agent#agent-memory+5

Claude Sonnet 5 Is the First Sonnet That's Actually Worth Using for Agents

On June 30, 2026, Anthropic shipped Claude Sonnet 5 and quietly closed most of the gap to Opus 4.8 at one-third the price. SWE-bench Pro 63.2%, OSWorld 81.2%, HLE 57.4%. The mid-tier is now the new default for production agents.

#anthropic#claude#claude-sonnet-5#sonnet+8
AI ENGINEERING

Stop Ollama Unloading Your Model: The keep_alive Trick

Tired of waiting 15 seconds for Ollama to reload llama3 every time you step away? One tiny env var kills that cold-start penalty for good. Here's the line, the gotchas, and the per-request override.

#ollama#local-llm#llm-inference#performance+3
AI OPINION

Agent Frameworks Are Overhead — Just Write Functions

Most agent frameworks are overengineered abstractions that hide bugs, lock you into their API surface, and make production agents harder to debug. A 100-line vanilla Python tool-calling loop will beat them for 90% of real work — here is the case for skipping the framework.

#ai-agents#opinion#llm#frameworks+3
AI TOOLS

LanceDB Is the Embedded Multimodal Lakehouse, and Most of You Are Paying for a Vector Database Server You Do Not Need

LanceDB is an open-source, embedded multimodal vector database built on the Lance columnar format — Apache 2.0, Rust core, used by Netflix and AWS at production scale. Most RAG and multimodal teams do not need a separate vector database server. Run LanceDB inside your Python process, or on S3, and stop paying Pinecone.

#lancedb#open-source#vector-database#multimodal+3
AI ENGINEERING

Claude Sonnet 5 Honest Take: Does the Agentic Boost Hold Up?

Anthropic dropped Claude Sonnet 5 on June 30, 2026, and the Terminal-Bench jump (+20.7 points) is real. But the new tokenizer quietly adds ~30% to your token bill. Here's my honest take on whether the agentic hype survives contact with production.

#claude#sonnet-5#anthropic#ai-agents+2

Make vLLM 1.8× Faster With Speculative Decoding (and a 0.5B Draft Model)

Your self-hosted 32B is doing 80 tok/s single-stream. Speculative decoding gets you ~1.8× throughput on chat for the cost of one tiny draft model and three CLI flags — with a tokenizer-mismatch footgun that turns output into gibberish without a single warning.

#tutorial#vllm#speculative-decoding#self-hosted-inference+3

The Cheap-Token Era Just Ended. Almost Nobody Has Noticed.

Tokens got 16x cheaper between 2023 and 2026. The next three years will deliver single-digit percentage gains. HBM, power, and latency have run out of headroom — and every AI unit-economics deck is still priced for the wrong world.

#opinion#hot-take#ai-infrastructure#gpu-economics+1
OPINION

AGI Is Not a Milestone. It Is a Marketing Department.

Altman, Hassabis, LeCun cannot agree what AGI means. Every 'AGI benchmark' saturates in a year, the term shows up four times per LP deck, and the best 2026 agent is 31 points short of a junior engineer. AGI is fundraising.

#opinion#hot-take#agi#frontier-labs+3
TUTORIAL

Wire OpenTelemetry Tracing Into a Python LLM App, Pointed at Self-Hosted Langfuse, in Five Lines

Stop maintaining two tracing stacks. Five lines of OpenTelemetry setup pipes every LLM span — model, prompt, tokens — into self-hosted Langfuse via the OTLP HTTP endpoint, with auto-instrumentation for OpenAI and Anthropic.

#tutorial#opentelemetry#otel#langfuse+5
LLM RELEASE

Mistral OCR 4 Is the Death of Cloud OCR for Regulated Industries, and Nobody Has Caught On Yet

Cloud OCR just died for regulated industries. Mistral OCR 4 ships 170 languages as a self-hosted container at $4 per 1,000 pages. The EU's real answer to the OpenAI and Anthropic stack monopoly.

#llm#release#mistral#ocr+5
OPEN SOURCE

Marimo Is the Python Notebook Jupyter Should Have Shipped Five Years Ago, and the Reactive DAG Is the Real Story

Marimo stores notebooks as pure Python, tracks a reactive dependency graph, and runs as a script or deploys as an app from one .py file. After six weeks I'm not going back to .ipynb.

#open-source#marimo#python#notebooks+4

PLAID Made ColBERT the Right Default for Production RAG. Stop Using Dense Bi-Encoders for Half Your Traffic.

Dense retrieval hides a structural bottleneck under precision defaults and reranker hacks. ColBERT keeps per-token representation; PLAID cut the storage cost roughly 5x in a 2022 paper most teams never read. That gap is your long-tail eval failure.

#open-source#retrieval#rag#colbert+2

Claude Sonnet 5's 1M Context Window Is a Trap, and the New Tokenizer Is Why

Anthropic bragged about a 1M-token context. What they didn't tell you is the new tokenizer inflates token counts ~30%, so the window holds roughly 23% less text than five 200K Sonnet 4.6 windows would have — and three API fields now return hard 400s.

#llm#release#anthropic#claude-sonnet-5+4
OPEN SOURCE

txtai Is the Only All-in-One AI Framework That Still Cares About CPU Servers, and Most of You Are Sleeping on It

While the rest of the AI world fights over who has the shiniest 8-GPU inference rig, neuml/txtai shipped v9.11 two days ago with a unified embeddings database, a smolagents-backed agent layer, graph + sparse + dense indexing, and bindings in JS/Java/Rust/Go. 12,700 stars. Apache 2.0. Zero VC footprint. This is the framework you should have been benchmarking in 2026.

#txtai#neuml#open-source#semantic-search+7
TUTORIAL

Stop Re-Typing Your Best Prompts: Custom Slash Commands in Claude Code in 30 Lines

Every Claude Code session I open starts with the same four prompts: review the diff, write a commit message, hunt for secrets, and explain the failing test. Custom slash commands turn those into single keystrokes. Here is the directory structure, two real command files, and the three gotchas that will save you an hour.

#tutorial#claude-code#claude#anthropic+4
OPINION

Most "AI Agent" Startups Are CRUD Wrappers

Strip away the word "agentic" from any Series A deck that raised in the last six months and you'll find one of three things: a POST and a GET, a scheduled cron with a prompt, or a vector search returning chunks to a system prompt. A CRUD wrapper with a chat box, dressed up in marketing copy. The investor pitch is buying the abstraction; the unit economics can't survive contact with real customers.

#opinion#agents#ai-startups#crud-wrappers+4
LLM RELEASE

Meituan Just Open-Sourced a 1.6T MoE Trained on 50,000 Chinese ASICs. The Pricing Is the Real Provocation.

On June 30, Meituan open-sourced LongCat-2.0 — a 1.6-trillion-parameter Mixture-of-Experts model with a native 1M-token context, MIT-licensed, trained end-to-end on a 50,000-card domestic Chinese ASIC cluster. It was already top-3 on OpenRouter as the stealth 'Owl Alpha.' Limited-time API pricing: $0.30 in / $1.20 out per million tokens, with cache hits free. The export-control era is closing.

#longcat-2.0#meituan#moe#open-source-llm+7
TUTORIAL

Anthropic's API TTFB Is Mostly Your Fault: Connection Pools + Region Routing in 20 Lines

If your first-token latency to Claude is over 600ms, you probably don't have a network problem — you have a connection-pool problem. Here's the httpx setup, the region-routing trick, and the two gotchas that make the difference between 1.8s and 280ms cold TTFB.

#anthropic#claude#performance#python+3
LLM RELEASE

Poolside's Laguna XS 2.1 Is the First Open-Weights 33B MoE Built for Agentic Coding, and It Beats Claude Haiku 4.5

On July 2, 2026, Poolside open-weighted Laguna XS 2.1: a 33B total / 3B active MoE, 256 experts with top-8 routing, mixed 3:1 sliding-window + global attention, native FP8 KV cache, 256K context, and a separate DFlash speculator that doubles local tok/s. SWE-bench Multilingual 63.1% (+5.4 vs XS.2), SWE-bench Verified 70.9%, $0.10/$0.20 per MTok — half of Haiku 4.5. The first open-weights coding model I'd ship an agent on without hedging.

#poolside#laguna-xs-2-1#open-weights#moe+3
OPINION

The Real Moat in AI Is Not the Model. It Is Taste.

Models are commoditized. Data is a temporary moat. Compute is a treadmill for everyone but the labs. The only durable advantage left in AI is the one thing that cannot be trained, benchmarked, or acquired with a term sheet: taste. The companies that will win the next decade are the ones with the better eye.

#opinion#hot-take#ai-strategy#ai-moats+3
OPEN SOURCE

OpenPipe ART Is the First RL Framework That Actually Makes Sense for Multi-Step Agents — And the Email Agent Beats o3

OpenPipe's ART is an open-source GRPO wrapper that turns your existing Python agent code into a trainable policy, with a real production result: a Qwen 2.5 14B email agent that beats OpenAI o3 on the Enron retrieval benchmark. 10.2k stars, Apache 2.0, last commit two days ago. This is the first RL-for-agents framework I'd actually ship against.

#openpipe#art#grpo#reinforcement-learning+3
OPINION

Your "Autonomous Agent" Is One Confident Hallucination Away From a Lawsuit. Stop Granting Default Autonomy.

Every 'fully autonomous' agent in 2026 ships with the dial cranked to 10 and the guardrails off. The autonomy is the bug, not the feature. Klarna just taught the industry an expensive lesson.

#opinion#hot-take#ai-agents#autonomous-agents+7
LLM RELEASES

OpenAI Just Shipped GPT-5.6 as Three Models. The Sub-Agent "Ultra" Mode Is the Real Story.

OpenAI put GPT-5.6 — Sol, Terra, Luna — into limited preview June 26, 2026. The Ultra mode sub-agent topology and Terminal-Bench SOTA matter more than the three-tier naming scheme.

#openai#gpt-5-6#sol-terra-luna#frontier-models+4