Skip to content

Standard Reader

Tag

Skills

Articles and publications tagged Skills across the Atmosphere.

12articles9publications

Articles

Publications

Klinchapp BlogSep 15, 2026

Your Workplace AI Readiness: A 30-Day Audit for Employees and Managers

Assess your team's AI adoption readiness in 30 days with our concrete audit checklist. Validate data quality, capabilities, and processes before rolling out ...

workplaceai-adoption

Klinchapp BlogSep 8, 2026

How to Actually Use AI Without Burning Out (Or Getting Caught Behind)

Learn how to use AI at work without overwhelm. 5 practical steps to boost productivity and skip the burnout—master one tool deeply instead of chasing every t...

workplaceai-adoption

Klinchapp BlogSep 4, 2026

The AI Tools Actually Winning in Your Office Right Now

Discover which best AI tools for work 2026 your team actually needs. From Notion to Claude to Cursor—see what's winning in real offices today.

workplaceai-adoption

I'm Not Doctor Who

I'm Not Doctor WhoAug 22, 2026

#oneaday Day 806: Absolute Direction (5 points)

We had a second game of Big Walk today, and one thing I appear to have impressed on the rest of my group is that I have a very good sense of direction, even in a virtual space. This is not something I tend to brag about -- because why would you? -- but it...

absolute directionbig walk

ai-monitor

ai-monitorAug 9, 2026

#agent #skills #inspiration

https://hugobowne.github.io/show-us-your-agent-skills/agent-skills/

subaud

subaudJul 31, 2026

Authoring an llms.txt for AI Agents

The first consumer of my runner-set library — a CDK construct that runs GitHub Actions jobs on Lambda MicroVMs — was another of my own repos, and the migration was done by an AI agent. The Claude session that moved its nine CI jobs onto the runners filed a field report, and reading it back, every failure it hit traced to something the documentation didn't say, not something it said wrong. The docs never said whether a job can run Docker. The agent probed, hit a sudo failure (no_new_privs is se

documentationAgents

Ewan's Project DocumentationJul 21, 2026

letta-coding-agent

Memory repository for a Letta Code coding agent — stores persistent persona and user identity projected into the agent's context at runtime.

fubits.devJun 15, 2026

My Svelte 5 & SvelteKit Essentials

Collection of some useful resources on learning & working with Svelte

Svelte 5SvelteKit

subaud

subaudMay 29, 2026

Skills Instead of Setup Docs

My now-playing kiosk has a long install document, and it's a long document. Three hundred and ninety-three lines, eight sequential phases, six environment variables that each gate a different optional install path, and a fifty-line section on a particular display whose touch input lives on a separate USB cable from its video. In addition to this, I wrote a Claude Code skills bundle that walks the same install conversationally. The two ship together in the repo right now. The long doc is the fa

claude-codeskills

subaud

subaudApr 20, 2026

Teaching Claude to Do Woodworking

One of the best parts about Claude Code is that the "code" in the name is misnomer. The fact is that it can be used for a wide variety of things. I wanted to use it to help with some woodworking projects. But part of the problem was that I didn't know where to start. I am very inexperienced at this which leads me to lean in to using Claude Code to help with research and planning. So that's where I got started can we work on creating some plugins/skills/agents and anything else that would be

Claude Codeskills

Strangelove-AIMar 7, 2026

Overview: Building Skills for Claude

An overview of building skills for Claude - definition, design principles, testing, and distribution

Scott Spence

Scott SpenceFeb 8, 2026

Measuring Claude Code Skill Activation With Sandboxed Evals

Remember that post where I tested skill activation with the Claude API and got the forced-eval hook to 84%? That was running against Haiku 4.5 with synthetic API calls. Good for iteration speed, but it wasn’t testing the actual thing. It was testing...

claudeclaude-code

You've reached the end.