Claude Skills by Sheldon-92

TAD document health check and synchronization. CHECK/SYNC modes for handoff cleanup and maintenance.

Start parallel execution for multi-component tasks via parallel-coordinator.

Execute TAD scenario workflows. Use with scenario name parameter.

Check and report TAD configuration status, installation health, and framework state.

Generate or update pair testing brief (TEST_BRIEF.md) for E2E pair testing with 4D Protocol.

Safely update TAD in the current project through the shared updater helper. Use when the user wants to update, upgrade, or check the TAD framework version.

TAD Framework main entry point. Shows framework overview and quick start options.

Professional video production judgment for AI coding agents. Covers storytelling, motion design, audio integration, and tools like HyperFrames and Remotion. Use for any AI-assisted video production, motion graphics, or multimedia content creation task.

Web backend capability pack. Gives AI agents the judgment rules a senior backend engineer applies automatically — API design, architecture selection, application logic, database modeling, security, production readiness, infrastructure, and debugging. 43 concrete decision rules + 46-item production readiness checklist + executable validation scripts. Use for any backend feature, API design, architecture review, database schema, security hardening, or pre-launch checklist task.

Web deployment capability pack. Gives AI agents the judgment rules for platform selection (Vercel/Netlify/Fly.io/Coolify), CI/CD pipeline design (GitHub Actions, SHA pinning, matrix builds), environment configuration (OIDC, secret managers, immutable images), monitoring (Uptime Kuma, Prometheus+Grafana, SLA targets), rollback strategies (blue-green, canary, atomic, Docker SHA), security hardening (headers, Checkov, SSL), and domain/DNS management (custom domains, Let's Encrypt, Cache-Control)...

Web frontend engineering judgment for React. Covers component architecture, state management, design token consumption, styling, performance, accessibility, testing, and visual-code bridge. Loads DESIGN.md when present and turns design artifacts into production-grade code. Use for any React frontend development, component design, or UI implementation task.

Web testing capability pack. Gives AI agents the judgment rules for unit testing (Vitest Browser Mode), API contract testing (Pact/OpenAPI), performance auditing (Core Web Vitals/k6), accessibility compliance (axe-core/Pa11y), human-AI pair testing (4D Protocol), and test strategy design (pyramid/CI/CD pipeline). Research-grounded rules from Playwright, Vitest, k6, axe-core, MSW, and Pact documentation. Use for any web application testing, test infrastructure setup, or quality assurance task.

Web UI design capability pack. Guides AI agents through a Vision → Execution → Validation pipeline across 9 design capabilities: information architecture, wireframing, visual design with anti-slop token system, interaction design, design system selection, responsive design, usability review, design system documentation, and design iteration decisions. Includes 14 verified CLI tools, anti-AI-slop rules (based on Anthropic frontend-design SKILL, Apache 2.0), and a bash+jq token compiler (no npm...

Academic research methodology pack — systematic literature review, citation integrity, quality evaluation. Activates on: 学术, academic, 论文, paper, 文献, literature, meta-analysis, 元分析, PRISMA, systematic review, 系统性综述, PubMed, 文献综述, 学术研究, 科研

Decision navigator for designing reliable agent systems. Guides any AI agent through 10 architectural decisions derived from 3 production systems (Claude Code, OpenClaw, Hermes) and 7 real production disasters. Two modes: /design (new system) and /audit (existing system).

AI voice production judgment for coding agents — TTS tool selection, voice cloning, audiobook/podcast/dubbing pipelines, Apple Silicon optimization, licensing safety

ML model training on cloud GPU — platform selection, LoRA/QLoRA fine-tuning, cost estimation, human-AI collaboration via browser MCP

Three deep skills that turn any AI agent into a product decision partner. Covers adversarial idea validation (/pressure-test), business model generation (/shotgun), and executable product definition (/define) across 6 product types.

Professional video production judgment for AI coding agents — storytelling, motion design, audio, tools (HyperFrames/Remotion)

Web frontend engineering judgment for React — component architecture, state management, design token consumption, styling, performance, accessibility, testing, and visual-code bridge. Loads DESIGN.md when present and turns design artifacts into production-grade code.

Web UI design capability pack. Guides AI agents through a Vision → Execution → Validation pipeline across 9 design capabilities: information architecture, wireframing, visual design with anti-slop token system, interaction design, design system selection, responsive design, usability review, design system documentation, and design iteration decisions. Includes 14 verified CLI tools, anti-AI-slop rules (based on Anthropic frontend-design SKILL, Apache 2.0), and a bash+jq token compiler (no npm...

Review API endpoints for RESTful design, consistency, usability, documentation, and developer experience.

Review system architecture, design patterns, data flow, and structural decisions for scalability, maintainability, and best practices.

Review code for quality, maintainability, security, and adherence to best practices. Identify issues by severity level (P0-P3).

Systematically diagnose and fix bugs, errors, and unexpected behavior in code through structured analysis.

Analyze code for performance issues, inefficient algorithms, memory problems, and optimization opportunities.

Analyze code for security vulnerabilities, potential attack vectors, and compliance with security best practices.

Guide Blake through RED-GREEN-REFACTOR cycle for each implementation unit. Opt-in via config.yaml — disabled by default.

Execute and verify test suites, ensure adequate test coverage, and validate that all tests pass before code integration.

Review user interface implementations for usability, accessibility, visual consistency, and user experience best practices.