Smashing the MCP + Skill Tradeoff: More Guidance, Better Agents?
This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry . Project Overview I've been working on a Tokyo public transit M…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Skills Sprawl: When Too Much of a Good Thing Confuses Your AI Agent
Introduction In this post, we’re going to look at the problem of Skills Sprawl . What happens if you have too many skills? We’ll understand LLM deci…
The Plan and the Worker: Two Open Specifications for Agent Harnesses
Every agent harness solves the same two problems, and almost every one of them solves both privately. The first problem is decomposition. A task arr…
I made my SaaS installable by AI agents. Here's what was broken.
Two weeks ago I watched an agent run a full product launch on Waitlister, my waitlist tool. It created the waitlist, generated and published a landi…
From Clicks to Documentation: Converting D365 Task Recordings into L4 Guides
Intro : Documenting business processes in Dynamics 365 can be time-consuming. Functional consultants and process owners often need to turn Task Reco…
Model Routing Made My AI Agents Cheaper. It Didn't Make Them Easier to Trust.
I spent a while optimizing what my AI agents cost to run. Cheap models for routine work. Better models when the task actually needed them. That made…
LoopX: A Control Plane for AI Agents That Have to Keep Working for Days
If you have ever pointed a coding agent at a multi-day goal, you know the failure mode. It is not that the model writes a bad function. It is that o…
Test smarter with Snagly: 30 open-source QA skills for AI coding agents
If you've experimented with AI-driven testing, you've probably lived this cycle: you ask an AI agent to "test the checkout flow," and it does someth…
Qwen3.8-Max Just Went GA: A Developer's Guide to Alibaba's 2.4T Model
Alibaba made Qwen3.8-Max generally available on August 3, 2026 . This is a practical rundown for developers: what the model is, what it costs, how t…
Behind the scenes: How we build, test, and scale Google Agent Skills
AI agents are only as good as the instructions and context you give them. When we launched Google Agent Skills , our goal was simple: encode Google…
Resolve Open Questions: a /qa Skill for Claude Code
By @atwellpub , GBTI Network Member . Originally published on gbti.network . Claude Code loads any markdown file at .claude/skills/<name>/SKIL…
How I Use Codex to Build Applications Without Losing Control
In 2026, there is a great deal of discussion around Agentic Coding . Every week, a new framework, orchestrator, or multi-agent system appears. To an…
Build a Support Copilot That Loads the Runbook Before It Calls a Tool
An AI support demo can look finished after it answers one question and calls one API. The production tension appears later: the model has instructio…
Skills vs MCP: How AI tools have evolved
Eighteen months ago, MCP was the thing. Every demo and chatbot connector was running on MCP under the hood. When I started seeing everyone talk abou…
garden-skills packages taste and process for AI coding agents
ConardLi's garden-skills makes a specific bet: what holds AI coding agents back is not raw capability but taste and process discipline. Each skill i…
How to structure CLAUDE.md, Skills and Agents
Hi friends Here's a tip for when you're setting up Claude Code (or any coding agent) in a real codebase, this came in clutch for me when I discovere…
AgentScaffold: Memory, Peer Review, and Continuous Improvement for AI Coding Agents
An AI coding agent will never tell you it's guessing. It doesn't hedge before a wrong answer, doesn't slow down when it's about to break something t…
Why Your AI Agent's Biggest Vulnerability Isn't a Missing Firewall
(initially published at https://www.humanbound.ai/blog/why-your-ai-agents-biggest-vulnerability-isnt-a-missing-firewall ) Three incidents, one root…
Prose in the Control Plane: Why AI Agent Frameworks Are Not Engineering (Yet)
Skill frameworks for AI coding agents are exploding in popularity. As of July 2026, Superpowers has roughly 256,000 GitHub stars, Matt Pocock's skil…
Superpowers vs Agent Skills vs Pocock: Three Philosophies of AI Coding Workflows
Every few months, a new framework appears promising to make AI coding agents write better code. Three have risen above the noise in 2025 and 2026: S…
How I Built an AI Review Skill That Refuses to Ship Bad Work
How I Built an AI Review Skill That Refuses to Ship Bad Work The fastest way to create AI slop is not to use a bad model. It is to accept a polished…
From First-Run Drop-Off to First Useful Agent Run
I keep coming back to the same onboarding question: what happens in the first 10 minutes? For agent tools, that window is brutal. A developer opens…
Stop re-explaining your codebase to every AI agent — `cast-skills`
The annoying part of AI coding tools Every session, the agent forgets: your module boundaries the “every user belongs to an org” rule that lives in…
Teaching AI Agents to Time-Travel: Building a Temporal Debugging Skill
Your AI agent is confident. It points to line 42 of PaymentService.java . "There's your null pointer exception." You check. Line 42 is a comment. Th…
Make AI Agents See Your Website
AI coding agents are now part of the developer workflow. Whether we like that shift or hate it, users ask Codex, Cursor, Claude Code, GitHub Copilot…
Introduction to Agentic AI
Introduction to Agentic AI You must be hearing the term "Agentic AI" a lot and wondering what it means. In this blog, I am going to explain: What is…
I Built a PDF Report Generator for NVIDIA SkillSpector Because AI Skills Need Better Security Reviews
A few weeks ago, I started looking more seriously at AI “skills.” Not skills in the human sense. I mean the installable skill packages used by AI co…
I Rolled Back My MCP Skills Experiment. Here's What I Learned
TL;DR I introduced a SKILL layer while improving fare extraction in a MCP-based transit agent. After that, the agent stopped reliably using the MCP…
I built an AI that presents my slides for me so I don't have to talk in meetings anymore
I hate presenting. Not the prep, not the content, the actual moment of unmuting, sharing my screen, and narrating 20 slides to a wall of black camer…
I Spent a Week Fixing the Wrong Skill (And Other Lessons from Evaluating an AI PR Reviewer)
TLDR The baseline model (Claude Opus, no guidance) already catches ~65% of textbook bugs. The plugin's value comes from false positive suppression a…