# Agent Skill Agent Skills is an open format for extending AI agent capabilities with specialized knowledge and workflows, using skill folders containing metadata, instructions, and optional resources. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Translating CUDA Tile Operations from Python to Rust Using Agentic AI DevFeed: [Translating CUDA Tile Operations from Python to Rust Using Agentic AI]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-09-16T16:28:59Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [CUDA Tile](), [Rust](), [Agent Skill](), [Artificial Intelligence](), [AI Agent](), [GPU](), [benchmarking](), [Compiler]() Tags: [agent-skill](), [agentic-ai](), [agentic-ai-generative-ai](), [ai-agent](), [benchmarking](), [cuda](), [cuda-tile](), [cutile](), [developer-tools-techniques](), [gpu](), [mixture-of-experts-moe](), [python](), [rust]() ### AI overview This NVIDIA developer article explains a multi-agent workflow for translating cuTile Python and Triton-TileIR GPU kernels into cuTile Rust. The team ported 24 public TileGym operators, covering about 40 kernels, and achieved 99.5% of cuTile Python performance on average, with correctness and performance checks at each stage. ### Source excerpt cuTile Rust (cutile-rs) is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to... ## SwiftUI Agent Skill: Install and use with AI coding tools DevFeed: [SwiftUI Agent Skill: Install and use with AI coding tools]() Original publisher: [Read original article]() Author: Antoine van der Lee Published: 2026-09-14T11:49:33Z Content type: article Language: en Sources: [SwiftLee]() Topics: [SwiftUI](), [Agent Skill](), [ai-coding](), [Code quality](), [context window](), [Command-line interface]() Tags: [agent-skill](), [ai-coding](), [ai-development](), [cli](), [code-quality](), [context-window](), [installation](), [open-source](), [swiftui]() ### AI overview This article introduces an open-source SwiftUI Agent Skill for AI coding tools. The skill helps agents build or refactor SwiftUI views, improve generated code quality, and load focused references only when they are relevant to a task. It also explains installation, updates, and compatibility considerations for the skills command-line tool. ### Source excerpt A SwiftUI Agent Skill that helps you build better views or refactor existing ones. It's the reality we're in today, and I honestly can't live without it anymore myself. Several skills helped me improve the code quality produced by agents, and I'm happy to introduce you to my open-source skill for SwiftUI. Before reading this ... -> The post SwiftUI Agent Skill: Install and use with AI coding tools appeared first on SwiftLee. ## Better context, smarter testing: How to give your AI coding agent direct access to k6 docs DevFeed: [Better context, smarter testing: How to give your AI coding agent direct access to k6 docs]() Original publisher: [Read original article]() Author: İnanç Gümüş Published: 2026-09-12T11:22:06.456390Z Content type: article Language: en Sources: [Grafana Labs blog on Grafana Labs]() Topics: [k6](), [Agent Skill](), [AI Agent](), [Command-line interface](), [coding]() Tags: [agent-skill](), [ai](), [ai-agent](), [ai-coding](), [analytics](), [cli](), [grafana](), [k6](), [logs](), [metrics](), [monitoring](), [observability](), [performance-testing](), [testing](), [traces]() ### AI overview The article introduces k6 x docs, an official k6 2.0 command that provides k6 documentation directly in the terminal. It supports API references, guides, best practices, and examples; works offline after the first lookup; matches documentation to the installed k6 version; and includes an agent skill for AI coding assistants. ### Source excerpt As testing workflows become more AI-assisted, fast access to accurate documentation matters more than ever. Whether you're writing a new load test, troubleshooting an issue, or having an AI agent generate a script for you, you need reliable guidance that keeps pace with the way you work. But most documentation still lives in a browser. Every time you or your agent needs to verify an API or look up a best practice, you're forced to leave your terminal or editor and interrupt your workflow. That's why, in k6 2.0, we introduced k6 x docs, an official k6 command that puts the entire k6 documentation library, including API references, guides, best practices, and examples, directly in your terminal. It works offline after first use, matches the docs to your exact k6 version, and includes a built-in agent skill, so AI coding assistants can look up k6 docs faster and most cost-effectively. The problem: documentation lives in the wrong place Most developers know the feeling. You're writing a k6 script, you need to check the signature for http.post or remember how thresholds work, and suddenly you're in a browser tab, searching, scrolling, clicking through navigation, and losing the context you had in your editor. For AI agents, the problem is worse. When they need to reference k6 APIs, best practices, or examples, they either rely on stale training data, hallucinate a function signature, or burn expensive tokens on a web search that may not return the right version of the docs. k6 x docs solves both problems by making documentation a first-class part of the k6 CLI. It gives agents CLI access to k6 docs that automatically detect the k6 version in use and deliver accurate content without leaving the session or performing web searches. How k6 x docs works The use is simple: type k6 x docs, optionally followed by the topic you want to look up. k6 x docs # See all available topics k6 x docs http # Learn about the k6/http module k6 x docs http get # Look up a specific function k6 ## Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond DevFeed: [Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond]() Original publisher: [Read original article]() Author: Guillaume Laforge Published: 2026-09-12T11:04:33.891311Z Content type: release Language: en Sources: [Google Developers Blog]() Topics: [Artificial Intelligence](), [Kotlin](), [AI Development](), [Android](), [Kotlin Multiplatform](), [multiplatform](), [Orchestration](), [Google](), [Persistence](), [Agent Skill](), [LiteRT](), [Cloud]() Tags: [agent-skill](), [agents](), [ai](), [ai-agent](), [ai-agents](), [android](), [building](), [database](), [development-kit](), [firebase](), [incident](), [kotlin](), [multiplatform](), [orchestration](), [persistence](), [production]() ### AI overview Google announces the 1.0 general availability release of the Agent Development Kit (ADK) for Kotlin, a production-ready toolkit for building multi-agent applications with Kotlin, Java, and Android. Built on Kotlin Multiplatform, it provides feature parity with the ADK 1.0 Core and adds Android-first extensions for on-device agents with LiteRT-LM and ML Kit, hybrid cloud workflows through Firebase AI Logic, and state persistence with Room and AppSearch. The release also includes type-safe, compile-time function calling through KSP and declarative agent skills. ### Source excerpt Google has officially released version 1.0 of the Agent Development Kit (ADK) for Kotlin, achieving full feature parity with the Python and Java ADK cores to enable idiomatic, multi-agent AI development. Built on Kotlin Multiplatform (KMP), the framework leverages Kotlin Symbol Processing (KSP) for zero-reflection, type-safe function calling, alongside advanced orchestration capabilities like human-in-the-loop workflows and context compaction. Additionally, the release introduces a robust suite of Android-first extensions, allowing mobile developers to integrate local models via LiteRT-LM, cloud reasoning through Firebase AI, session persistence using Room, and semantic memory powered by AppSearch. ## Auditing Coding-Agent Configuration, Skills, Memory, and Hooks DevFeed: [Auditing Coding-Agent Configuration, Skills, Memory, and Hooks]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-27T14:31:10Z Content type: tutorial Language: en Sources: [Elevate]() Topics: [Agent Skill](), [configuration](), [AI-assisted coding](), [Claude](), [sdlc]() Tags: [agent](), [agent-skill](), [agent-skills](), [claude](), [coding-agents](), [configuration](), [markdown](), [sdlc]() ### AI overview This practical guide argues that coding-agent configuration files can become outdated as models, harnesses, and codebases change. It recommends periodically reviewing configuration, memory, skills, and hooks, while acknowledging concerns about token costs, excessive instructions, and uncertain effects on quality. The author describes using Claude's /doctor and maintaining Agent Skill packages. ### Source excerpt A practical guide to auditing what your coding agent still needs. ## Ship agent skills like packages: discovery index, digests, and install sources DevFeed: [Ship agent skills like packages: discovery index, digests, and install sources]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-08-12T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Agent Skills](), [Agent Skill](), [ai-coding](), [Publishing](), [GitHub](), [make](), [rubygems]() Tags: [agent-experience](), [agent-skill](), [agent-skills](), [ai](), [coding](), [coding-agents](), [dx](), [github](), [jamstack](), [json](), [llms](), [npm](), [rubygems](), [sha-256](), [skills]() ### AI overview This tutorial explains how to publish agent skills so AI coding agents can discover and install them. It covers a .well-known/agent-skills/index.json discovery index, SHA-256 integrity digests, single-file, multi-file, and bundle packaging, multiple install commands, and hosting skills from a GitHub repository while re-hosting the served files on the publisher's domain. ### Source excerpt How to publish agent skills so any AI coding agent can find and install them: the .well-known/agent-skills/index.json discovery index, SHA-256 integrity digests, single-file vs multi-file vs bundle packaging, and every install command. Worked from the catalog we just open-sourced. ## Why every engineering org needs an agentic registry DevFeed: [Why every engineering org needs an agentic registry]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-08-10T11:43:10Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Skill](), [MCP](), [cursor](), [Azure](), [bedrock](), [site-reliability-engineering]() Tags: [agent-skill](), [agentic](), [agents](), [azure](), [bedrock](), [coding](), [governance](), [mcp](), [slack](), [workflows]() ### AI overview The article argues that engineering organizations need an agentic registry to manage the rapid growth of agents and skills. It describes registries for SKILL.md files, deployed agents, and approved MCP servers, with capabilities for discovery, standardization, governance, and workflow composition. ### Source excerpt Why every engineering org needs an agentic registry ## AWS Supports Agent Plugins: An Open Standard for Portable Agent Extensions DevFeed: [AWS Supports Agent Plugins: An Open Standard for Portable Agent Extensions]() Original publisher: [Read original article]() Author: Libby Clark Published: 2026-08-06T17:21:21Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Agent Skill](), [Agent Skills](), [AI Agent](), [MCP Server](), [Open Source](), [Amazon Web Services](), [Model Context Protocol]() Tags: [agent-skill](), [agent-skills](), [ai-agent](), [aws](), [cursor](), [javascript](), [mcp](), [mcp-server](), [microsoft](), [model-context-protocol](), [open-source](), [openai](), [vercel](), [vs-code]() ### AI overview AWS supports Agent Plugins 1.0.0, an open source, vendor-neutral specification for packaging AI agent extensions in a common format. The standard is intended to let developers package an extension once and distribute it across compatible clients such as Kiro, VS Code, Cursor, and other tools. Its initial version standardizes Agent Skills and MCP servers, with hooks and custom agents planned for future versions. ### Source excerpt If you've ever built an MCP server or agent skill, you know that packaging it means adapting for one client, re-writing for another, and repeating that for every tool your team uses. Agent Plugins 1.0.0 is an open source, vendor-neutral specification that gives AI agent extensions a common packaging format so you can package an [...] ## esparagus: ESP32 flashing with structured output for CI and coding agents DevFeed: [esparagus: ESP32 flashing with structured output for CI and coding agents]() Original publisher: [Read original article]() Author: John Lee Published: 2026-08-01T00:00:00Z Content type: tutorial Language: en Sources: [Blog on Developer Portal]() Topics: [ESP32](), [observability](), [Rust](), [Command-line interface](), [Agent Skill](), [ci](), [MCP Server]() Tags: [agent-skill](), [ai](), [blog](), [ci](), [ci-cd](), [cli](), [esp32](), [esptool](), [flashing](), [mcp](), [mcp-server](), [observability](), [rust]() ### AI overview This article introduces esparagus, a Rust flasher for the ESP32 family that behaviorally ports esptool's flashing paths. It adds machine-oriented observability through NDJSON events, structured reports, stable exit codes, crash detection, and integrations including a direct CLI, an Agent Skill, and an MCP server. ### Source excerpt esparagus is an ESP32-family flasher written in Rust -- a behavioral port of esptool's protocol, sync, reset, and stub-loader paths, wrapped in an observability layer built for programs rather than humans: NDJSON events, a machine-readable report file, stable exit codes, and an expect-style serial monitor with built-in crash detection. This article explains why that layer exists, how the flash-test-fix feedback loop works, and the three ways to integrate it -- direct CLI, an Agent Skill, and an MCP server. ## How to free up Xcode disk space safely with an AI Agent DevFeed: [How to free up Xcode disk space safely with an AI Agent]() Original publisher: [Read original article]() Author: Antoine van der Lee Published: 2026-07-27T08:34:16Z Content type: tutorial Language: en Sources: [SwiftLee]() Topics: [Xcode](), [AI Agent](), [Agent Skill](), [Open Source]() Tags: [agent-skill](), [agent-skills](), [ai-agent](), [ai-development](), [derived-data](), [developer-tools](), [disk-space](), [how-to](), [open-source](), [workflow](), [xcode]() ### AI overview This tutorial explains why Xcode can consume substantial disk space, especially when multiple AI agents use separate Git worktrees. It introduces an open-source Xcode Disk Cleanup Agent Skill that searches common storage locations and requires explicit approval before deleting anything. ### Source excerpt Xcode disk space can grow rapidly without you noticing. Especially these days, with multiple agents turning multiple worktrees into silent disk space occupiers. Where I used to only focus on deleting old Simulators every now and then, I'm now also actively managing worktrees and derived data folders. There are great Mac apps and open-source projects ... -> The post How to free up Xcode disk space safely with an AI Agent appeared first on SwiftLee. ## @clickhouse/rowbinary: when your library is also a parser compiler DevFeed: [@clickhouse/rowbinary: when your library is also a parser compiler]() Original publisher: [Read original article]() Author: Peter Leonov Published: 2026-07-14T20:59:26Z Content type: article Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [Node.js](), [Parser](), [Agent Skill](), [Compiler](), [coding]() Tags: [agent-skill](), [bugs](), [clickhouse](), [coding](), [cost](), [generate](), [javascript](), [node-js]() ### AI overview @clickhouse/rowbinary is a Node.js library for reading and writing ClickHouse RowBinary formats. It also provides an Agent Skill that lets a coding agent generate query-specific parsers from the library's reading primitives, producing faster parsers with less runtime dispatch and reducing risks associated with handwritten binary decoders. ### Source excerpt We've released @clickhouse/rowbinary a Node.js reader and writer for ClickHouse's RowBinary formats. You can import it and call its generic parser like any other library. But it also ships as an Agent Skill: point a coding agent at the bundled `SKILL.md` ## Vercel's Agent Framework, Netflix's Generative Homepage, and a Repo That Writes Less Code: The Tokenizer Edition #33 DevFeed: [Vercel's Agent Framework, Netflix's Generative Homepage, and a Repo That Writes Less Code: The Tokenizer Edition #33]() Original publisher: [Read original article]() Author: Sairam Sundaresan Published: 2026-07-05T05:27:18Z Content type: article Language: en Sources: [Gradient Ascent]() Topics: [Artificial Intelligence](), [Agent Skill](), [ZEIT](), [AI-assisted coding](), [Netflix]() Tags: [ai](), [coding](), [coding-agents](), [generative](), [models](), [netflix](), [tools](), [vercel]() ### AI overview This newsletter edition curates AI and machine learning resources, including papers, videos, articles, tools, and learning materials. Topics include Program-as-Weights, bounded-memory long-horizon agents, coding-agent benchmarks, Netflix's model-generated homepage, Vercel's file-first framework for durable agents, and tools for distributed model inference. ### Source excerpt This week's most valuable AI resources ## Agentic Autonomy Levels DevFeed: [Agentic Autonomy Levels]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-03T14:30:33Z Content type: article Language: en Sources: [Elevate]() Topics: [Artificial Intelligence](), [Orchestration](), [Agent Skill](), [Claude](), [Claude Code](), [codex]() Tags: [agent](), [agentic](), [agentic-engineering](), [agents](), [ai](), [claude](), [claude-code](), [codex](), [delegation](), [multi-agent](), [orchestration](), [parallel](), [scopes](), [trust](), [verification]() ### AI overview This article proposes a two-axis model for evaluating agentic engineering: agency, describing how independently a single agent operates, and orchestration, describing the skill of coordinating multiple agents. It argues that a single autonomy ladder is insufficient for multi-agent work and emphasizes matching autonomy levels with appropriate verification. ### Source excerpt A working model of autonomy for agentic engineering ## Agentic Autonomy Levels DevFeed: [Agentic Autonomy Levels]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-02T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Artificial Intelligence](), [Orchestration](), [Agent Skill]() Tags: [agentic](), [agentic-engineering](), [ai](), [delegation](), [multi-agent](), [orchestration](), [scale](), [scopes](), [trust](), [verification]() ### AI overview The article argues that agent autonomy should be evaluated on two separate axes: agency, describing how independently an agent pursues a goal, and orchestration, describing the ability to coordinate multiple agents. It emphasizes choosing an autonomy level per task and defending that choice through verification. ### Source excerpt The action in agentic engineering has moved from prompting to operating. Autonomy isn't one ladder, it's two axes (agency and orchestration) and six levels you move between per task. The real question is what level a task deserves, and what verification makes that level defensible. ## Learning faster with Antigravity DevFeed: [Learning faster with Antigravity]() Original publisher: [Read original article]() Author: Andrew Brogdon Published: 2026-07-01T04:08:53Z Content type: article Language: en Sources: [Flutter - Medium]() Topics: [Flutter](), [Agent Skill](), [ai-coding](), [Python](), [Development](), [SDK]() Tags: [agent-skill](), [agentic-ai](), [ai-coding](), [architecture](), [development](), [flutter](), [gemini](), [google-antigravity](), [ios](), [multi-agent](), [python](), [sdk](), [web-development]() ### AI overview The article describes using Antigravity and a structured, iterative workflow to learn Python-based Agent Development Kit (ADK) concepts and build Flutter frontends for an existing multi-agent research coordinator. The author created a reusable developer skill, flutter_frontend_for_adk, with reference documents covering agent analysis, frontend usage, architecture, and design. ### Source excerpt Dash enjoying AntigravityCreating Flutter frontends for ADK How can I build a Flutter frontend for an agent when that agent is built with an SDK and a language I've never used before? This was the challenge I faced when approaching a Python-based agent written with Agent Development Kit (ADK). With limited experience in Python and no prior exposure to the ADK framework, building a client that integrates with the backend server presented a significant learning curve. Plus, even if I could get a coding agent to crank out something that worked, finishing the project without understanding the code was also a form of failure. After a few false starts, though, I found an answer. Using a structured, iterative workflow with my AI coding partner, Antigravity, I created a reusable developer skill that codified what I learned with each go-round. I started from scratch, generated notes about the code, created multiple apps that connected to the deep_search agent (a multi-agent research coordinator from the official ADK samples repository), and incrementally built up the skill and my own understanding. At times, I was using multiple agents at the same time, an "author" agent to create the skill with me, and a "coder" agent to use that guidance to build frontends. What I ended up with was an agent skill called flutter_frontend_for_adk. It includes five reference docs that guide Antigravity through a sequence of phases, each one ending in a deliverable. The first phases generated the following notes files, so that I could structure how the "coder" agent thought about the task as it analyzed the agent and prepared to generate the app: AGENT_INTERFACE_NOTES.md -- Notes taken during an analysis of the agent's source code. What is it meant to accomplish and how is it constructed? What are the interfaces and APIs this agent exposes and how do they work? FRONTEND_USAGE_NOTES.md -- The first spec. What should the frontend do and how should users interact with it? FRONTEND_ARCHITECTURE_NOTE ## How to Build, Theme, and Audit Material Design 3 UIs with AI Agents DevFeed: [How to Build, Theme, and Audit Material Design 3 UIs with AI Agents]() Original publisher: [Read original article]() Author: Ivan Morgillo Published: 2026-06-02T17:00:00Z Content type: tutorial Language: en Sources: [Ivan Morgillo]() Topics: [Material Design](), [Agent Skill](), [Compose](), [AI Agent](), [Kotlin](), [Accessibility](), [Flutter]() Tags: [accessibility](), [agent-skill](), [ai-agents](), [audit](), [compose](), [css](), [flutter](), [kotlin](), [material-design]() ### AI overview A practical guide to an MIT-licensed agent skill for building and auditing Material Design 3 interfaces. It covers component generation, seed-color theme creation for light and dark modes, responsive app shells, accessibility checks, and support for Compose, Flutter, CSS, and JSON outputs. ### Source excerpt A practical guide to material-3-skill -- components, theme generation, the 10-category MD3 audit, and the real Compose bugs it catches in production code. ## Building for the AI era: Chainguard partners with Endor Labs DevFeed: [Building for the AI era: Chainguard partners with Endor Labs]() Original publisher: [Read original article]() Published: 2026-05-19T00:00:00Z Content type: article Language: en Sources: [Chainguard: Unchained]() Topics: [supply-chain-security](), [Application Security](), [Artificial Intelligence](), [AI-assisted coding](), [chainguard containers](), [Containers](), [Library](), [Agent Skill](), [CI/CD]() Tags: [agent](), [ai](), [ai-coding-agents](), [application-security](), [chainguard](), [chainguard-containers](), [chainguard-libraries](), [containers](), [cves](), [endor](), [endor-labs](), [observability](), [provenance](), [sboms](), [software-supply-chain](), [vulnerabilities]() ### AI overview Chainguard partners with Endor Labs to help teams building with AI coding agents secure the software supply chain. Chainguard provides source-built artifacts, daily rebuilds, signed SBOMs, and SLSA Level 3 provenance, while Endor Labs analyzes application context to identify vulnerabilities that are genuinely reachable and exploitable. ### Source excerpt Chainguard and Endor Labs help teams build securely at AI speed with source-built artifacts, exploitability analysis, and fewer vulnerabilities to triage. ## An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent... DevFeed: [An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent...]() Original publisher: [Read original article]() Author: Pinterest Engineering Published: 2026-05-12T16:01:00Z Content type: article Language: en Sources: [Pinterest Engineering Blog - Medium]() Topics: [Agent Skill](), [Artificial Intelligence](), [Claude Code](), [codex](), [Bash](), [iOS](), [JSON]() Tags: [agent](), [agent-skill](), [agentic-coding](), [agents](), [ai](), [ai-agents](), [analysis](), [architecture](), [bash](), [claude-code](), [code](), [codex](), [debug](), [engineering](), [engineering-culture](), [how-to](), [openai](), [pinterest](), [programming](), [skills](), [testing](), [workflows]() ### AI overview An engineer's guide to testing AI skill invocation in repositories and custom skills. It describes a Bash-based harness that runs positive and negative prompts, captures verbose logs, parses JSON-streamed output, and measures invocation reliability across an internal Codex fork and Claude Code. ### Source excerpt An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent Performance in Any Repository or Skill Author: Daniel Reed The tech industry is currently seeing a massive overhaul in the way we work and many are enjoying the benefits of AI agents, particularly when automating engineer workflows and serving domain-specific knowledge. However, relying on agents to consistently invoke a custom skill can be surprisingly unreliable at times. When adopting a new skill intended to help agents write code for Pinterest's iOS architecture (I'll call it rx-mvvm) we discovered that sometimes our knowledge skill wasn't being loaded into our agents. To address this, we conducted a series of tests on Pin-agent (an internal fork of OpenAI's Codex) and Claude Code to quantify the reliability of skill invocation and identify some best practices to maximize performance. This was a direct result of observing agents struggling to meet the skills bar during architectural reviews. We found that by applying different techniques we could track and drastically improve skill invocation rates on both tested agents. How to Build A Skill Test Harness Building a reliable test harness for agent skill invocation requires three key components working in concert. The Core Tool is a Bash script that orchestrates automated testing by piping prompts to your agent and capturing verbose output logs. The core execution is simple: if echo "$prompt" | claude --print --verbose --output-format stream-json > "$log_file" 2>&1; then command_success=true fi The script runs all test cases in sequence, collecting logs for later analysis. We ran the entire suite multiple times to account for the nondeterministic nature of agents. Prompts were categorized into two categories defined as arrays: Positive Cases -- 15 prompts covering the full spectrum of skill domains: CORE_PROMPTS=( "load the rx-mvvm-architecture skill" "check if this follows rx-mvvm patterns" # ... 13 more cases ) Negative Case ## Introducing Skills for Dart and Flutter DevFeed: [Introducing Skills for Dart and Flutter]() Original publisher: [Read original article]() Author: Mariam Hasnany Published: 2026-05-06T18:19:09Z Content type: release Language: en Sources: [Flutter - Medium]() Topics: [Agent Skills](), [Dart](), [Flutter](), [Agent Skill](), [MCP](), [MCP Server](), [AI-assisted coding]() Tags: [agent-skill](), [agent-skills](), [agents](), [ai](), [ai-agent](), [ai-agents](), [ai-development](), [coding](), [coding-agents](), [dart](), [efficiency](), [flutter](), [flutter-app-development](), [libraries](), [mcp](), [mcp-server](), [skills](), [tests](), [tools]() ### AI overview Flutter is introducing Agent Skills for Dart and Flutter to give AI tools domain-specific expertise for professional development tasks. The task-oriented skills provide tailored instructions for workflows such as adaptive layouts and enhance the Dart MCP server, aiming to improve accuracy and reduce token usage. ### Source excerpt Introducing prepackaged Dart and Flutter Skills!Improving AI with domain expertise AI agents are generalists, but when it comes to professional Flutter development, "general" isn't enough. To build production-grade apps, you need an assistant that understands the nuance of localization, the latest Dart language features, and how to add integration tests. Today, we're introducing Agent Skills for Flutter and Dart -- a new way to give your AI tools domain-specific expertise. Beyond the knowledge gap One of the primary challenges in AI development is the "knowledge gap." Flutter and Dart can launch new features more quickly than LLMs can update their fixed training data. As a part of how we are thinking about AI, we are looking for ways to not only address the knowledge gap but also ensure the agent applies that knowledge to achieve the task accurately and efficiently following the most optimal workflows. A little over a year ago, Model Context Protocols (MCP) were the way to provide more AI domain-specific expertise. While MCP gives an agent access to specialized tools, an Agent Skill teaches the agent how to use those tools for a specific task. Think of it this way: MCP provides the hammer and nails (the tools), while a Skill provides the blueprint and the professional know-how to build the house. Skills improve context efficiency through "progressive disclosure". This is similar to how deferred loading works in Flutter, where apps can load libraries when needed, coding agents load Skills when they are relevant to what you're trying to do . For Flutter and Dart, these Skills provide tailored instructions for common workflows, and enhance the tools provided in the Dart MCP server to reduce the knowledge gap, which improves accuracy and lowers token usage. A task-oriented approach Our early experimentation revealed that Skills that only provide documentation don't add as much value as we initially assumed. Since Flutter's comprehensive and well written documentation is ## Android ❤ Gemini CLI - tech debt detection Code Maat skill DevFeed: [Android ❤ Gemini CLI - tech debt detection Code Maat skill]() Original publisher: [Read original article]() Published: 2026-03-08T00:00:00Z Content type: tutorial Language: en Sources: [maiatoday]() Topics: [Android](), [Tech Debt](), [Agent Skill](), [Command-line interface](), [Artificial Intelligence](), [Code](), [Git](), [Android Studio]() Tags: [adb](), [agent-skill](), [ai](), [android](), [cli](), [code](), [code-maat](), [command-line](), [gemini](), [gemini-cli](), [git](), [tech-debt]() ### AI overview This tutorial explores using Gemini CLI and an agent skill with Code Maat to identify technical-debt hotspots in the Habitica Android codebase. It describes using Git history to analyze file churn and logical coupling, and compares the approach with the Gemini Agent in Android Studio. ### Source excerpt Introduction What AI tools work for building Android apps? I am exploring some variations. In this post I will look at Gemini CLI, tech debt detection with a skill using Code Maat and how this compares with the Agent of Gemini in Android Studio. I am not starting with a new project. What if you have an existing codebase and you want to find the best place to tackle some tech debt that will make a difference for everyone. The sample codebase is the Habitica app, which had its first commit in 2015. Rather than poking at the code in a random or an "intuitive" way or asking the AI questions, let's look at a more deterministic way to answer this question. Or rather, let's teach the agent to use some scripts to answer this question. The benefit of packaging this functionality in a skill is that you can create this specialisation and script usage in a skill that will be loaded lazily only when you need it. The theory - Code as Crime scene Adam Tornhill wrote a book, Your Code as a Crime Scene, that uses your git history and applies forensic science to figure out where the hotspots, logical coupling, churn and more can be found in your code base. He has a java tool called Code Maat that you can use to analyse this information. The problem is, it is a bit finicky to setup and run and I can never remember all the command line parameters for git or for the tool. The theory TLDR is if you can see which large files change often or which files always change together, you can see which parts of your code are brittle or are coupled. The added benefit is that this analysis is language neutral. So if you build an agent skill for this, it can be used on any codebase. Creating the Code Maat Skill What do we need the link to Code Maat optionally download the code-maat standalone jar and put it in ~/tools/code-maat.jar to speed up the first run Gemini CLI + authentication and API key if you have it the skill-creator skill - this is part of the Gemini CLI install the Habitica Android app