Engineering/comment-stinky
Comment Stinky
Detect code-comment smells in any language, explain the cost of each, and propose the rewrite.
Distilled from posts on this blog. Each skill turns one post's argument into a checklist an agent can step through, end to end.
Engineering/comment-stinky
Detect code-comment smells in any language, explain the cost of each, and propose the rewrite.
Engineering/test-stinky
Detect test-suite quality smells in any language or framework, explain the cost of each, and propose a fix with a source link.
Engineering/tauri-stinky
Detect Rust and Tauri maintainability smells across the backend crate, the IPC boundary, and the app shell, explain the cost of each, and propose a fix with a source link.
Engineering/react-stinky
Detect React and TypeScript maintainability smells across the whole component, hook, and module, explain the cost of each, and propose a fix with a source link.
Engineering/visual-consistency
Detect and fix visual and layout consistency defects in rendered UI, the systematic raggedness AI generators emit and seniors notice at a glance.
Engineering/odsf
Author, validate, and maintain a design system for AI agents as a conformant Open Design System Format (ODSF) bundle, a profile (v0.2) of Open Knowledge Format v0.2 that adds design tokens, runnable HTML/CSS example assets, and design-oriented concept types.
Engineering/mcp-server
Build, extend, and maintain a Model Context Protocol (MCP) server across its whole lifecycle against the current spec and official SDKs.
Engineering/godot
Godot game engine development skill, a dated snapshot tracking the current stable Godot (4.x, currently 4.7).
Engineering/android-compose
Modern Android development with Jetpack Compose as the default UI toolkit and Material 3 Expressive as the default design direction, a dated snapshot.
Engineering/javascript-ecosystem
Default to the latest stable major versions of JavaScript and TypeScript frameworks and their current paradigms, instead of the older versions and patterns that dominate LLM training data.
Engineering/theme-colors
Audit and refactor UI code so every color value comes from the theme.
Engineering/audit-actions
Audit a repository's GitHub Actions workflows for unsafe pull_request_target usage that can lead to supply chain compromise.
Engineering/codegen-api
Set up typesafe API code generation in 2026, preferring framework-agnostic options factories over generated hooks.
Engineering/react-compiler
Write and review React code as if the React Compiler is enabled.
Engineering/okf
Create, inspect, retrieve, author, revise, enrich, audit, repair, research, analyze change impact, migrate, validate, and maintain knowledge for AI agents as conformant Open Knowledge Format (OKF) bundles.
Engineering/trust-card
Generate, sign, attest, and verify holistic trust cards for OKF knowledge bundles and agent skills.
Productivity/no-slop
Write and revise human-facing prose in a plain, precise, professional register, stripping the tells that mark text as AI-generated.
Productivity/fable-mode
Adopt the structural operating discipline of Anthropic's Fable model in whatever agent harness is running, so the host model (GPT 5.6, Gemini, or any coding agent) orients, parallelizes, delegates, verifies, and reports the way Fable does.
Productivity/breadcrumbs
Heal codebase understanding gaps exposed during implementation, debugging, or investigation.
Productivity/game-design
Analyze, design, critique, balance, and rework video game mechanics, systems, and interface, grounded in a cross-game pattern catalog and design frameworks (MDA, core loops, flow, motivation, game feel, economy, balance).
Productivity/autopilot
Work autonomously on a project without waiting for direction.
Productivity/ask-ux
Force UX questioning before any UI work, refactor, or redesign.
Productivity/to-story
Reshape a draft ticket, Jira issue, or GitHub issue from an engineer's braindump into a real user story with INVEST-clean acceptance criteria, and split stories that are too large using SPIDR.