Skill Creator

majiayu000

6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗

window-function-builder

majiayu000's avatarfrom majiayu000★ 5

Эксперт SQL window functions. Используй для аналитических запросов, OVER clauses и ranking functions.

architecture-adr

majiayu000's avatarfrom majiayu000★ 5

When making significant architectural decisions that need to be documented. Used by ARCHITECT-AGENT.

git-workflows

majiayu000's avatarfrom majiayu000★ 5

Execute git operations using Conventional Commits format with proper branching strategies and safe workflows. Use when making commits, managing branches, or performing git operations.

blog-post-reviewer

majiayu000's avatarfrom majiayu000★ 5

Review and provide feedback on blog posts to ensure they match the established writing voice and style guidelines.

process-inbox

majiayu000's avatarfrom majiayu000★ 5

Guide user through inbox processing, clarifying and organizing items one at a time using the clarify and organize workflow. Automatically invoked when user wants to process their inbox.

diataxis

majiayu000's avatarfrom majiayu000★ 5

Create and evaluate documentation using the Diátaxis framework. Use when writing, organizing, or auditing documentation to ensure it serves distinct user needs through four systematic categories (Tutorials, How-to Guides, Reference, Explanation). Ideal for diagnosing documentation problems, separating mixed content, and ensuring each piece serves a single, clear purpose.

test-strategy

majiayu000's avatarfrom majiayu000★ 5

Production-grade test strategy skill with risk-based testing, coverage analysis, quality gates, and resource optimization

ui-ux-guidelines

majiayu000's avatarfrom majiayu000★ 5

Enforce comprehensive UI/UX best practices for accessible, performant, and delightful interfaces. Use when building components, reviewing UI code, or evaluating user experiences.

distribution-analyzer

majiayu000's avatarfrom majiayu000★ 5

Эксперт анализа распределений. Используй для statistical distributions, data analysis и hypothesis testing.

problem-solving

majiayu000's avatarfrom majiayu000★ 5

Apply systematic problem-solving techniques for marketing challenges including campaign complexity (simplification cascades), creative blocks (collision-zone thinking), recurring campaign patterns (meta-pattern recognition), assumption constraints (inversion exercise), audience scale uncertainty (scale game), and dispatch when stuck. Techniques derived from proven problem-solving frameworks adapted for marketing execution.

fosmvvm-leaf-view-generator

majiayu000's avatarfrom majiayu000★ 5

Generate Leaf templates (Views) for FOSMVVM WebApps. Use when creating HTML views that render ViewModels - both full-page templates and fragments for HTML-over-the-wire updates.

compress-session

majiayu000's avatarfrom majiayu000★ 5

Compress session conversation into structured summary for system memory. Activate when user says "compress", "compress session", or after significant work. Captures decisions, tools built, breakthroughs, and context that git commits can't preserve.

nix-check

majiayu000's avatarfrom majiayu000★ 5

Check and validate NixOS configuration. Use when asked to check, validate, lint, or verify the nix config, flake, or configuration files.

systems-thinking-dsl-generator

majiayu000's avatarfrom majiayu000★ 5

Generates DSL code for the Systems Thinking Tool (systemsthinkingtool.com). Creates system dynamics models with stocks, flows, constants, delays, lookup tables, and graphs. Based on actual implementation at github.com/doodzik/systems-thinking-tool.

shader-effects

majiayu000's avatarfrom majiayu000★ 5

Visual shader effects—glow/bloom, chromatic aberration, distortion, vignette, film grain, scanlines, glitch, dissolve, outline, and fresnel. Use when adding visual polish, post-processing effects, or stylized rendering to shaders.

design-doc-reviewer

majiayu000's avatarfrom majiayu000★ 5

Use when reviewing design documents, technical specifications, or architecture docs before implementation planning. Performs exhaustive analysis to ensure the design is specific enough to create a detailed, coherent, and actionable implementation plan without hand-waving or ambiguity.

logs

majiayu000's avatarfrom majiayu000★ 5

View Vercel deployment logs. Use when the user says "show logs", "check logs", "vercel logs", or "what went wrong with the deployment".

typescript-standards

majiayu000's avatarfrom majiayu000★ 5

Guide for creating TypeScript libraries using the typescript-library-template pattern and applying its standards to existing projects. Use when setting up new npm packages, standardizing build scripts, configuring tooling (tsup, Vitest, ESLint, Prettier), or applying dual module format patterns.

lead-gen-calculator

majiayu000's avatarfrom majiayu000★ 5

Multi-step calculator UI for Astro. Quote tools, pricing calculators. Uses astro-forms for backend.

upgrade-flake

majiayu000's avatarfrom majiayu000★ 5

Update flake.lock to get latest packages within the current NixOS release - runs nix flake update, checks build, and optionally applies

context-resume

majiayu000's avatarfrom majiayu000★ 5

Load module context from handoff files to resume work

update-pr

majiayu000's avatarfrom majiayu000★ 5

Creates comprehensive PR descriptions by systematically reviewing ALL changes - features, bug fixes, tests, docs, and infrastructure. Use when user wants to update PR description, prepare PR for review, or document branch changes. Requires gh CLI.

wp-theme-development

majiayu000's avatarfrom majiayu000★ 5

WordPress theme development best practices and standards. Use when building new themes, creating custom templates, implementing theme features, working with template hierarchy, customizer options, or FSE block themes, or when user mentions "theme development", "child theme", "template hierarchy", "theme.json", "customizer", "template parts", "block theme", "classic theme", or "theme standards".

uncertainty-routing

majiayu000's avatarfrom majiayu000★ 5

Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".