Technical Writing

Edit writing to adopt Paul Graham's exceptionally clear style for research and long-form content - concrete language, varied sentence rhythm, accessible formality, specific evidence. Use when user wants to rewrite content in PG's style or asks to "make this clearer" or "simplify research writing."

Write clean, consistent code following naming conventions, formatting standards, and DRY principles across all files. When writing or editing any code in any programming language (TypeScript, JavaScript, Python, etc.). When creating functions, variables, classes, or modules. When refactoring code to improve readability or reduce duplication. When implementing small, focused functions or removing dead code. When ensuring consistent indentation, naming patterns, and code structure. This skill applies universally to all code files regardless of their specific purpose.

Enhance writing quality by fixing grammar, improving sentence structure, maintaining consistent style, and strengthening prose. Use when editing chapters, improving readability, or polishing final drafts.

Convert experiment results to Markdown research notes and optionally update research state with evidence

This skill should be used when the user asks to "create a README", "write a README", "generate a README", "improve my README", "make my README better", "README best practices", or mentions needing project documentation. Provides guidance for creating excellent READMEs following patterns from awesome-readme.

NVIDIA API documentation for integrating NVIDIA services. Use for NVIDIA NIM (NVIDIA Inference Microservices), LLM APIs, visual models, multimodal APIs, retrieval APIs, healthcare APIs, and CUDA-X microservices integration.

Ansible automation and configuration management patterns. Use when writing Ansible playbooks, roles, or automating infrastructure configuration and deployment tasks.

Generate initial project planning documents (PVS, ADR, Tech Spec, Roadmap) from a project concept description. Use when starting a new project, when docs/planning/ contains placeholder files, or when user requests project planning document generation.

Create and manage database migrations following best practices for schema evolution and data integrity. When creating or modifying database migration files (migrations/*, *.migration.ts, migrate.ts). When working on schema changes, data migrations, or database version control. When implementing reversible migrations with up/down methods, managing indexes on large tables, or handling zero-downtime deployments. When writing migration scripts that alter database structure, add or remove tables, modify columns, or transform data.

Enforce strict TDD workflow for all development tasks. Use when implementing new features, fixing bugs, or refactoring code. Ensures comprehensive test coverage (unit, integration, e2e) before writing implementation code. Activates automatically for all coding tasks unless explicitly authorized to skip testing.

Testing guidelines for Bun/TypeScript projects using bun:test framework. Use when writing tests, creating test files, debugging test failures, setting up mocks, or reviewing test code. Triggers on *.test.ts files, test-related questions, mocking patterns, and coverage discussions.

Create Claude Code subagents from natural language requirements. Use when users want to create specialized AI subagents for Claude Code without manually writing the configuration. Handles agent creation for testing, code review, debugging, documentation, refactoring, and custom workflows. Generates .claude/agents/*.md files with appropriate YAML frontmatter and system prompts.

Expert guidance on Obsidian markdown syntax, editing features, and formatting. Use when helping with Obsidian note-taking, formatting, or markdown syntax.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Interactive AI agent development workflow orchestrator. Guides users through complete agent creation from brainstorming to production-ready implementation. Use when user wants to build a new AI agent, design an agentic system, scaffold an agent project, or needs help with agent architecture decisions. Supports three-phase workflow - design documentation, implementation scaffolding, and operations (deploy/observe/evaluate).

Builds content-focused websites with Astro using islands architecture, content collections, and multi-framework support. Use when creating static sites, blogs, documentation, marketing pages, or content-heavy applications with minimal JavaScript.

Write HashiCorp-compliant Terraform infrastructure code for Azure with automated style validation. Optimized for azurerm and azapi providers. Use when implementing Terraform resources, modules, or configurations. Triggers include "write terraform", "create tf module", "terraform code", "implement infrastructure as code", or working with .tf files. ALWAYS uses Terraform MCP tools to query provider documentation before implementation.

Use when working with Luban game configuration tool - covers schema definition, Excel data filling, code generation, polymorphic types, validators, localization, and roblox-ts integration. Provides indexed reference to complete Luban documentation by topic