inwo inwo.
← all tags

#skills

11 posts

Ponytail: The Best Code Is the Code Your Agent Never Writes

Jun 27, 2026 · Shingo Nakamura · AI

Ponytail is a one-file 'lazy senior dev' skill that makes coding agents stop and pick the simplest solution that works — cutting code by ~54% (and tokens ~22%) on a real agentic benchmark. What it is, how the ladder works, what trusted reviewers found, and the honest caveats.

claude-codellmtokensskills
read more →

Anthropic Cybersecurity Skills: A Structured Security Playbook for AI Agents

Jun 18, 2026 · Shingo Nakamura · AI

A community-built, Apache-2.0 library of 754 structured cybersecurity skills that give an AI agent senior-analyst playbooks — mapped to MITRE ATT&CK, NIST CSF 2.0, ATLAS, D3FEND and NIST AI RMF. What it is, how the skills are built, defensive use cases, how it compares, and the honest tradeoffs (including its dual-use responsibility).

cybersecurityskillsclaudedefensive-security
read more →

Matt Pocock's Skills for Real Engineers: Small, Composable Agent Skills

Jun 11, 2026 · Shingo Nakamura · AI

mattpocock/skills is Matt Pocock's everyday .claude skills folder, published — small, composable agent skills that fix the common failure modes of coding agents (misalignment, verbosity, broken code, ball-of-mud architecture) without taking over your process. What it is, how it works, the standout grilling and TDD skills, and the honest tradeoffs.

skillsclaude-codeagentstypescript
read more →

UI UX Pro Max: A Design-Intelligence Skill for Your Coding Agent

Jun 3, 2026 · Shingo Nakamura · AI

UI UX Pro Max is an open-source AI skill that gives a coding agent a design brain — a reasoning engine that turns a one-line prompt into a complete design system with styles, palettes, typography, and anti-patterns. What it is, how it works, what it produces, and the honest tradeoffs.

ui-ux-pro-maxclaude-codeskillsdesign-systems
read more →

Awesome Claude Code: A Curated Directory for Your Claude Code Workflow

May 30, 2026 · Shingo Nakamura · AI

awesome-claude-code is a selectively curated 'awesome list' of skills, agents, hooks, slash commands, status lines, CLAUDE.md files and tooling for Claude Code. What it is, how it's organized and curated, the standout categories, how it compares to bigger aggregators, and the honest tradeoffs.

awesome-claude-codeclaude-codeawesome-listskills
read more →

Caveman: Why Use Many Token When Few Do Trick

May 1, 2026 · Shingo Nakamura · AI

A Claude Code skill that makes the agent talk like a caveman — cutting output tokens by up to ~75% while keeping full technical accuracy. Why, how it works, how to install it, and real before/after numbers.

claude-codellmtokensproductivity
read more →