Claude Skills by mattnigh

User experience and visual design expert - creates wireframes, mockups, and interactive prototypes. Ensures WCAG accessibility and mobile responsiveness. Self-evaluates using 8-metric UX standard (8.0/10 minimum).

Initialize a dagster project using the create-dagster cli. Create a dagster project, uv virtual environment, and everything needed for a user to run dg dev or dg check defs successfully. (project)

[Utility] Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

[Task Mgmt] A Skill that adds new tasks with priority tags to Docs/Task/{StepName}_Task.md documents for multi-agent parallel development. AI agent MUST invoke this skill AUTOMATICALLY when (1) discovering new work items during implementation, (2) user requests a new feature/fix, (3) breaking down a large task into subtasks, (4) identifying follow-up work after completing a task. CRITICAL - Never modify document structure, only add tasks with proper priority tags (!high, !medium, !low). Tasks...

[Task Mgmt] A Skill that syncs task status in Docs/Task/{StepName}_Task.md by moving tasks between sections (Backlog, Worker1, Worker2, Worker3, Review, Done) with priority-aware management for multi-agent parallel development. AI agent MUST invoke this skill AUTOMATICALLY when (1) starting work on a task - move to assigned Worker, (2) AI completing work - move to Review (NOT Done). CRITICAL - AI CANNOT move to Done or Backlog. Only User/Reviewer can move tasks to Done or Backlog. (user)

Package expertise into discoverable, reusable capabilities that extend Claude's functionality. Use when creating new Skills, understanding how Skills work, or organizing existing capabilities.

Teaches how to write effective documentation and instructions for LLMs by assuming competence, using progressive disclosure, prioritizing examples over explanations, and building feedback loops into workflows.

Manage Cloudflare R2 object storage for file hosting using Wrangler CLI. Use when uploading files to R2, managing buckets, configuring public access, or when user mentions "R2", "Wrangler", "upload to cloud", or "image hosting".

Production-ready Nuxt 4 framework development with SSR, composables, data fetching, server routes, and Cloudflare deployment. Use when: building Nuxt 4 applications, implementing SSR patterns, creating composables, server routes, middleware, data fetching, state management, debugging hydration issues, deploying to Cloudflare, optimizing performance, or setting up testing with Vitest. Keywords: Nuxt 4, Nuxt v4, SSR, universal rendering, Nitro, Vue 3, useState, useFetch, useAsyncData, $fetch,...

This skill should modify the category screens and add the requested scrcpy options to the UI, depending on the type of the option (text, toggle, dropdown, etc.). Use this skill for adding new scrcpy options in the UI.

Creates specialized AI agents with optimized system prompts using the official 5-phase SOP methodology (v2.0 adds Phase 0 expertise loading), combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge. Integrates with recursive improvement loop.

Comprehensive framework for analyzing, creating, and refining prompts for AI systems (v2.0 adds Phase 0 expertise loading and quality scoring). Use when creating prompts for Claude, ChatGPT, or other language models, improving existing prompts, or applying evidence-based prompt engineering techniques. Integrates with recursive improvement loop as Phase 2 of 5-phase workflow. Distinct from prompt-forge (which improves system prompts).

Executable implementation of the Propose -> Test -> Compare -> Commit -> Rollback pipeline for recursive self-improvement. Provides concrete commands and workflows for each stage.

Meta-prompt that generates improved prompts and templates. Can improve other prompts including Skill Forge and even itself. All improvements are gated by frozen eval harness. Use when optimizing prompts, creating prompt diffs, or running the recursive improvement loop.

Advanced skill creation system for Claude Code using 8-phase methodology (v2.0 adds Phase 0 expertise loading). Combines deep intent analysis, evidence-based prompting principles, and systematic skill engineering. Use when creating new skills or refining existing skills. Integrates with recursive improvement loop - can rebuild itself using previous version. Transforms skill creation from template filling into strategic design.

Manual API testing commands for pharmaceutical test generation workflow. Use when testing Docker-based FastAPI endpoints with Clerk JWT authentication, submitting URS files, and monitoring job execution. Provides WSL-compatible commands for token generation, job submission, status monitoring, and log inspection.

Validates Requirements Phase completion before advancing to Design Phase. Checks business requirements document for completeness, quality gate compliance, and readiness for design work.

Validates Design Phase completion before advancing to Implementation Phase. Checks functional specifications, database design, and UI/UX design for completeness and technical feasibility.

Validates Implementation Phase completion before advancing to Testing Phase. Checks code compilation, test coverage, implementation completeness, and code quality standards.

Validates Finalization Phase completion before workflow concludes. Checks documentation updates, file registry, git commits, deployment readiness, and lessons learned contributions.

Deploys WitchCityRope to production environment on DigitalOcean. Automates build, registry push, server deployment, database migrations (if needed), health verification, and rollback capability. SINGLE SOURCE OF TRUTH for production deployment automation.

Calculates context-appropriate quality gate thresholds based on work type (Feature/Bug/Hotfix/Docs/Refactor). Ensures rigorous standards for features, pragmatic standards for hotfixes, and 100% test pass rate for all work.

Restarts WitchCityRope Docker DEVELOPMENT containers using the CORRECT procedure. Handles shutdown, rebuild with dev compose overlay, health checks, and compilation verification. Ensures environment is ready for development. SINGLE SOURCE OF TRUTH for dev container restart process. Uses -p witchcityrope-dev for isolation from test containers.

Create or update release notes for changes in the current branch using Reno, following dd-trace-py's conventions and the guidelines in docs/releasenotes.rst.

Build metrics collection pipelines using Prometheus, Grafana, and custom exporters

CC-DevFlow workflow router and agent recommender. Use when starting requirements, running flow commands, or asking about devflow processes.

Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architectur...

使用自定义动能理论分析 BTC 市场，多时间级别嵌套分析（2日线/1日/12h/6h/4h/2h/1h/30min），识别上涨线段、下跌线段、分立调控、单位调整周期、连续跳空背离、黄白线背离，生成包含详细属性判断的动能报告和交易信号。当用户询问 BTC 动能、线段状态、MACD 分析、周期判断、背离检测时自动激活。

Diagnose and repair selftest failures by running diagnostic commands and proposing fixes

Use when debugging social media API integrations - captures request/response cycles, identifies rate limit vs auth vs data errors, applies platform-specific quirks from integration patterns

Use when modifying billing, quotas, or cost control logic - validates tier limits match business model, prevents quota bypass, tests edge cases

Use when working with database queries, API endpoints, or workers - ensures organization_id context is preserved through entire request lifecycle, prevents data leaks between tenants

Use when modifying master prompt or user-facing input that feeds to OpenAI - validates injection defenses, tests adversarial inputs, prevents system prompt leakage

Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with new capabilities, revise agent configurations, analyze project requirements to identify specialized roles, or craft precise agent configurations with appropriate tool permissions and model tiers. When the user specify "Create or Update subagent [name]", this skill must be triggered.

Generate resident schedules respecting ACGME rules, institutional policies, and individual preferences. Orchestrates constraint propagation, optimization, and conflict resolution for medical residency program scheduling.

Proactive code health monitoring and quality gate enforcement. Use when validating code changes, reviewing PRs, or ensuring code meets quality standards before merging.

Review generated code for bugs, security issues, performance, and best practices. Use when reviewing Claude-generated code, checking for vulnerabilities, auditing implementation quality, or validating code changes before commit.

Understand agent context isolation and write effective prompts for spawned agents. Use when orchestrating multi-agent workflows to ensure subagents receive complete, self-contained context.

Docker development and container orchestration expertise. Use when creating Dockerfiles, docker-compose configurations, debugging container issues, optimizing images, or setting up isolated development environments. Integrates with CI/CD workflows and security scanning.

Production-grade FastAPI patterns for async APIs, SQLAlchemy 2.0, Pydantic v2, and robust error handling. Use when building API endpoints, handling database operations, implementing middleware, or optimizing performance.

Modern frontend development with Next.js 14, React 18, TailwindCSS, and TanStack Query. Use when building UI components, implementing pages, optimizing performance, or following Next.js App Router patterns.

Unified linting and auto-fix for Python (Ruff) and TypeScript (ESLint) in monorepo. Use when fixing lint errors, running pre-commit checks, or diagnosing persistent code quality issues. Orchestrates auto-fix first, then root-cause analysis.

Pull request review expertise with focus on context, quality gates, and team standards. Use when reviewing PRs, validating changes before merge, or generating PR descriptions. Works with gh CLI for GitHub integration.

Validate documentation requirements before creating a PR. Checks for scratchpad entries, CHANGELOG updates, tests, and plan files based on change type. Use before creating pull requests to ensure all documentation gates are satisfied.

Crisis response skill for production system failures. Integrates with MCP resilience tools to detect, diagnose, and respond to critical system failures. Use when production system shows signs of failure or during emergency situations.

Advanced pytest patterns for Python backend testing. Use when dealing with async tests, complex fixtures, mocking strategies, database testing, or debugging flaky tests. Complements test-writer with deeper patterns.

Generate a comprehensive resilience status report using all available MCP tools. Aggregates unified critical index, burnout Rt, early warnings, utilization, and defense levels into a single actionable dashboard.

Security-focused code audit for healthcare and military contexts. Use when reviewing authentication, authorization, data handling, HIPAA compliance, or OPSEC/PERSEC requirements. Essential for PHI handling and military medical residency schedules.

Create new skills with proper structure and YAML frontmatter. Use when building new slash command skills, ensuring consistent formatting, directory structure, and validation. Guides through the complete skill creation workflow.

Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.