Good suggestion. A coding agent can already read markdown files from the main repo, but you could add an explicit skills extension with a dedicated folder and registry.
TOOLS
-

BM25: The Powerful 30-Year-Old Search Algorithm Still Beating Vectors
By
–
Stop using vector search everywhere! A 30-year-old algorithm with zero training, zero embeddings, and zero fine-tuning still powers Elasticsearch, OpenSearch, and most production search systems today. It's called BM25. Let me explain what makes it so powerful: Imagine you're searching for "transformer attention mechanism" in a library of ML papers. BM25 asks three simple questions: "How rare is this word?" Every paper contains "the" and "is", which makes it useless. But "transformer" is specific and informative. BM25 boosts rare words and ignores the noise. → This is IDF(qᵢ) in the formula "How many times does it appear?" If "attention" appears 10 times in a paper, that's a good sign. But 10 vs 100 occurrences won't make much difference. BM25 applies diminishing returns. → This is f(qᵢ, D) combined with k₁ that controls saturation "Is this document unusually long?" A 50-page paper will naturally contain more keywords than a 5-page paper. BM25 levels the playing field so longer documents don't cheat their way to the top. → This is |D|/avgdl controlled by parameter b Three questions. No neural networks. No training data. Just elegant math (refer to the image below) The best part: BM25 excels at exact keyword matching – something embeddings often struggle with. If your user searches for "error code 5012," embeddings might return semantically similar results. BM25 will find the exact match. This is why hybrid search exists. Top RAG systems today combine BM25 with vector search. You get the best of both worlds: semantic understanding AND precise keyword matching. So before you throw GPUs at every search problem, consider BM25. It might already solve your problem, or make your semantic search even better when combined.
→ View original post on X — @akshay_pachaar, 2026-04-05 13:02 UTC
-
Gemma 4 31B Quantized Models Evaluated on NVFP4 and FP8
By
–
Gemma 4 31B, quantized and evaluated. Instruction following evals are live on our NVFP4 and FP8-block model cards. Results look great. Reasoning and vision evals coming later this week. NVFP4: huggingface.co/RedHatAI/gemm… FP8: huggingface.co/RedHatAI/gemm… Red Hat AI (@RedHat_AI) The open source ecosystem moved fast on Gemma 4 today. Google DeepMind released it. @vllm_project had Day 0 support across diverse accelerators. Red Hat AI Inference Server is ready for Gemma 4 experimentation too. Guide in the reply 👇 — https://nitter.net/RedHat_AI/status/2039876315222782215#m
→ View original post on X — @clementdelangue, 2026-04-05 12:20 UTC
-

Agentic AI Periodic Table: Memory, Planning, Tools, Safety
By
–
Agentic AI now has its own “Periodic Table” 🧪🤖 From: LLM, RAG, RL to PLAN, MAS, LTM to SAFE, HUMAN oversight to HR, MKT, LEGAL use cases Autonomous AI = memory + planning + tools + safety + collaboration. It’s a system, not a prompt. Credit: Prem Natarajan #AgenticAI #AIStack #LLM
→ View original post on X — @ingliguori, 2026-04-05 12:17 UTC
-

Harness Engineering: Building Better AI Agent Systems
By
–
I let Claude Code loop for 45 minutes while I was at the gym. Came back. It told me the feature was done. It wasn't. It hadn't even run the tests. Not because the model is dumb. Because I wrapped it in nothing but a loop and a dream. That's harness engineering in one sentence. And no, it's not prompt engineering with a fancier name. The model is the engine. Context is the fuel. The harness is the rest of the car. Steering. Brakes. Lane boundaries. Warning lights. Tools, permissions, tests, retries, guardrails. Engine + fuel but not strong parts in it = dangerous car. So I stopped tuning the engine and started building the car around it. In every skill file (Claude Code, Claude Co-work), I added one last step. After each interaction, the agent reflects on what I liked, what I edited, what failed. Then it updates its own skill to be better next time. Token usage dropped (a lot). Output quality went up. Compounding improvement with zero extra effort from me. LangChain did something similar at a bigger scale. Changed only the harness on a coding agent. Same model. Went from outside the top 30 to top 5 on a benchmark. Same engine, completely different results, just because the car around it was better. Next time your agent breaks, don't blame the model. Fix the car. P.S. Do your agents learn from their mistakes, or do they keep making the same ones?
-
Daily Token Generation Costs and Hermes Business Implementation
By
–
It isn’t. I have met quite a few that are paying hundreds of dollars in token generation every day. And Hermes is running my new business system.
-

Gemma 4 Becomes Top Trending Model on Hugging Face
By
–
Gemma 4 is the #1 trending model on @huggingface 🤗
→ View original post on X — @clementdelangue, 2026-04-05 09:33 UTC
-
MacBook Air M5 Sufficient for Coding Agents Work
By
–
I spent 3 hours this morning working with coding agents on MacBook 16" M5 Max in LOW POWER mode! 😱 I noticed 0 difference! This means a MacBook Air M5 is more than enough for this. BTW Apple Silicon is unbeatable! 🤷🏻♂️
→ View original post on X — @clementdelangue, 2026-04-05 08:53 UTC
-
Gemma-4-E4B: Local AI Agents Identify Sea Animals with Vision
By
–
Watch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀)
— Victor M (@victormustar) 5 avril 2026
I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer! pic.twitter.com/mHPMiPPNSZWatch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀) I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer!
→ View original post on X — @deeplearn007, 2026-04-05 08:41 UTC
-

85 Artificial Intelligence Terms Explained Guide
By
–
85 #AI Terms Explained
by @Python_Dv #ArtificialIntelligence #MachineLearning #ML #Technology