distrocool Submit a tool
DistroCool Brief

What changed in AI. What you can build with it.

RSS ↗

8 min read

Check a skill. Build a UI. Test one tab.

A useful agent experiment ends with something you can inspect, not a bigger permission list. Start by checking whether a skill can load, build a tiny search field with a clear keyboard behavior, then give a browser agent one harmless page. The software is free; installation, compatible runtimes and your chosen model still have requirements. Keep the first attempt in scratch files and a browser profile with no accounts signed in. We inspected original release notes and documentation, not independently measured these tools or their performance.

Inspect an agent skill

Find out whether an agent can load your skill

What changed

NVIDIA published SkillEvaluator v1.0.1 on November 18, its first complete release in the 1.0 series. HarnessCheck compares skill locations, frontmatter, descriptions and content limits against versioned agent profiles. It can flag a skill that a particular harness may miss, reject or truncate. This is a compatibility check, not a model judging whether the instructions are good.

Why it matters

A carefully written skill cannot help if the agent never sees it. Checking the file contract first gives a builder a concrete place to start before spending tokens on a full evaluation. Keep two questions separate: whether the harness delivers the skill, and whether following it actually improves a task.

Try it

In a separate Python 3.12–3.14 virtual environment, review the package and install the documented CLI; pinning this edition uses: python -m pip install skillevaluator==1.0.1 Copy a small skill you wrote into a scratch folder named my-skill. Do not use private customer material. From its parent directory, run: skillevaluator harness-check ./my-skill Read the result for your actual agent and its supported version. Fix one reported location or frontmatter problem in the scratch copy, then rerun and compare the finding. Optionally run: skillevaluator quality-check ./my-skill Keep any generated report outside my-skill. Stop at these static checks; do not enable all tiers, provision a model, install a skill into a real agent or connect accounts for this first attempt.

Availability & cost: Apache-2.0 source; version 1.0.1 is published on PyPI for Python >=3.12 and <3.15. HarnessCheck needs no model key or agent run. The lightweight quality check needs no API key, security scanner, GPU or Docker. Initial package installation requires downloads; these checks do not require paid inference.

Limits: Harness profiles describe particular releases, not every future agent version. A compatibility result is not evidence that the skill was invoked successfully. A quality score is not a security audit or a measured improvement: publication evidence remains INCOMPLETE until additional checks run. Full validation has separate scanner, model and sandbox requirements. We did not install or run this CLI.

Original sources

Build a small interface

Make a Clear button that gives focus back

What changed

Vercel Labs has released UI SDK as a public beta. Its core package first published version 0.1.0-beta.1 on November 12. Instead of only offering finished components, the library exposes behaviors for focus, selection, popups and keyboard interaction, with framework adapters. The official search-field example combines an input with a conditional Clear button and focus recovery.

Why it matters

A tiny interface is a better first check than asking an agent to rewrite your app. Clearing text is simple to describe, but the keyboard user also needs focus to return somewhere useful. You can inspect and test that behavior before adopting a component system or allowing an agent to operate the interface.

Try it

Use a disposable React 19+ project, not your production app. After reviewing the beta and your dependency policy, install the two documented packages: npm install @ui-sdk/react @ui-sdk/core Use the complete search-field and React examples in the linked README, or give an already available free/local coding assistant this original bounded prompt: In this scratch React project, use UI SDK to make a labeled Search input and a Clear button. Show Clear only when text exists. Clearing must empty the input and return focus to it. Follow the installed package documentation and keep the existing styles. Do not add analytics, accounts, an agent bridge or a deployment. Start the project with its existing development command. Type a fictional query, reach Clear with Tab, activate it with the keyboard, and confirm that the input is empty and focused. Also try a pointer click and an initially empty field. If dependency-age rules block installation, stop rather than disabling them.

Availability & cost: Apache-2.0 library with React, Vue, Svelte, Solid and Web Components adapters. The React quickstart requires React 19 or newer and a compatible project toolchain. The library needs neither paid hosting nor a model API. Any coding assistant is optional and has its own access terms; the README example can be copied manually.

Limits: The beta APIs, documentation and behavior can change, and the project also points to Vercel beta terms. Built-in behaviors do not establish that your composition is accessible. Test labels, keyboard use and focus in the actual app. We inspected the examples but did not compile this component. No claimed reduction in code, tool calls or cost is our own measurement.

Original sources

Test an agent safely

Give OpenCode Browse one clean tab, not your accounts

What changed

OpenCode Browse v0.1.0 was released on November 16 with a Rust rewrite of its CLI, local relay and MCP server. A Chromium extension still drives the browser. Tabs replace the earlier session handle: agents work with the tabs they open and tabs a person explicitly lends them. The release describes a smaller native runtime; that is not an independently verified speed or memory result.

Why it matters

An agent using your ordinary browser can inherit access to real logins and actions. A dedicated test profile lets you inspect the new browsing path without handing over your inbox or payments. Tab ownership helps organize work, but the safer first boundary is having no valuable signed-in session available at all.

Try it

First create a separate Chromium-browser test profile with no accounts signed in. Review the official extension permissions and installer changes. The project documents: npx @opencode/browse install Choose only the intended test agent in its setup picker and pair the extension in that empty profile, not your everyday browser. Setup can edit agent configuration and PATH; inspect those choices before accepting them. Use an MCP-capable agent you already run without paid model calls. Give it this original task: Open https://example.com in a new tab. Read the page title and heading, then report the tab you used. Do not sign in, submit forms, download files, buy anything or inspect other tabs. Stop after the report. Compare its answer with the visible page yourself. Do not lend it existing tabs. If it needs an account or a paid model to proceed, stop rather than expanding this experiment.

Availability & cost: MIT-licensed bridge and a Chromium extension; documented browsers include Chrome, Edge, Brave and Chromium. The native runtime does not use Node.js or Playwright underneath, but the npm launcher requires Node 22+. It does not include a model: use an existing free/local MCP-capable setup, with its separate hardware and model terms.

Limits: The extension requests powerful debugger and website permissions. Material read from a page can reach the agent model provider, and page text can contain prompt injection. A separate profile and a prompt are not a complete sandbox. Installation and automatic updates change local software/configuration; review them. We did not install Browse, verify its isolation or reproduce the headline memory claims.

Original sources

4 more signals

Useful checks and updates. Guidance shows its check date; event dates identify actual announcements.

  • Kitesurf is open source, not a free hosted browser

    Cloudflare open-sourced its experimental browser engine on November 13 under Apache-2.0. Local development uses Wrangler; the README requires Bazelisk, Node 22+ and pinned pnpm, with a substantial first build. Read those requirements before trying the local health endpoint. Deploying it on Cloudflare needs a Workers Paid plan because of Dynamic Workers. CDP support is not full Chromium compatibility; do not substitute it for your only real-browser QA.

  • Turn a small source set into an interactive study page

    Google announced Gemini Notebook sites on November 16. On the web, an eligible user aged 18+ can ask the notebook chat to make a site from sources they can edit. Try a fictional project checklist and inspect every generated date. Standard access exists without a paid AI plan, but rollout and compute quotas apply; stop when the free allowance is unavailable. Sharing a site requires notebook access, so never publish one containing private sources.

  • Agent identity is not account permission

    Poppy 1.0 separates session identity from OAuth account access. Read its discovery and authorization sections, then write a local table for one toy app: what is public, what needs read access, and what changes need explicit approval. Reading the public specification costs nothing. A recognized agent or a valid session does not itself authorize transactions, and a protocol description is not proof your implementation is secure.

  • Plan for a malicious page before opening it

    Microsoft recommends layered defenses for indirect prompt injection, including isolating untrusted text, least privilege, tool-chain checks and human review of risky actions. For your next browser test, write down the forbidden actions and keep sending, purchasing and account changes unavailable. The guidance is free to read; the named enterprise services are not required for that checklist. No prompt or scanner guarantees that every injection is stopped.

Build something cool

Make one tiny interface pass a real user journey

Use the linked free website-check workflow for your scratch search field. Specify three checks: an empty field has no Clear control; typing shows Clear; keyboard activation clears the query and restores input focus. Inspect the actual browser state and record failures, not just an agent report. Keep any browsing agent in a separate signed-out profile with no form submission or external actions authorized. This is a small acceptance checklist, not a security certification or a production release.

Open the DistroCool workflow →

Was this edition useful?

Your choice helps us shape future editions. No account needed.

Edition archive

Search by topic, story or idea. Every edition has a permanent link.

Check a skill. Build a UI. Test one tab.

Check an agent skill, build a focused search box with UI SDK, and give an agent a clean browser tab. Three free-first experiments, with setup and limits.

8 min read · Read edition ↗

Run a local model. Check what it gets wrong.

Try llama.cpp 1.0, turn your own voice into local notes with Yogurt, and test whether an assistant solves your problem rather than obeying a bad premise.

8 min read · Read edition ↗

Shield prompts from injection, control robots, and cluster embeddings 10x faster

Try IBM Granite LLMON to stop prompt injection with structural token delimiters, run Runway Praxis-1 robotics policies in MuJoCo, and cluster millions of vectors 10x faster with FAISS 1.16.0 e-means. Three free, open-weight experiments.

6 min read · Read edition ↗

Give your AI agent a safer practice run

Try BotPsy without executing tools, inspect UI states with Storybook 11, and search a small local folder with Kensaku. Three free, bounded experiments.

7 min read · Read edition ↗

Local AI you can hear, inspect and simulate

Try on-device speech with Phonon, inspect a Swift ticket router, and explore MuJoCo 4 in your browser. Free first steps, with setup and limits spelled out.

7 min read · Read edition ↗

Three free local AI tools that give your agents real superpowers

Control web browsers with Browser Use, build custom Model Context Protocol tools in 10 lines with FastMCP, and force local Ollama models into strict Pydantic JSON schemas. Free, open-source, and runnable on your laptop today.

4 min read · Read edition ↗

Three free AI experiments for your weekend

Make a chore anthem, give your doodle six moods, and find a genuinely free local adventure. Three original prompts, simple steps and the catches to check.

5 min read · Read edition ↗

Make your own escape-room game

Three useful things to try with free Google AI access, without installing software. Original prompts, short steps and the catches worth knowing.

4 min read · Read edition ↗

Test agent memory before trusting it; inspect model fairness and TPU serving

IBM's agent playbook experiment, Allen Institute's FairStress benchmark and PyTorch-native TPU serving offer three bounded ways to check an AI system instead of accepting a headline.

5 min read · Read edition ↗

The useful edge: check the agent, protect the pull request, run a model locally

Three practical shifts for builders: GitHub adds AI Scan to pull requests, Llama Windows lowers the local-model setup barrier, and Google shows how to evaluate agents beyond a demo.

4 min read · Read edition ↗