Productivity

Unified documentation and context preservation: spec folder workflow (levels 1-3), template enforcement, validation, Spec Kit Memory with vector search, six-tier importance system, constitutional rules, checkpoint save/restore. Mandatory for all file modifications.

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Interactive wizard for creating, scaffolding, validating, and managing Claude Code skills

Extracts patterns, errors, and insights from operational logs using type-specific analysis templates

Run Nx generators with prioritization for workspace-plugin generators. Use this when generating code, scaffolding new features, or automating repetitive tasks in the monorepo.

Generates test mocks, stubs, and fixtures for testing (Jest, Vitest, pytest, etc.). Use when user asks to "create mock", "generate stub", "mock function", "test fixtures", or "mock API response".

Incremental content drafting skill that writes specific sections within existing scaffolds. Supports drafting 1 section at a time or batch-drafting multiple sections with user control. Each operation stays under 10k tokens to avoid context compacting.

Batch-generate chapter scaffolds (frontmatter + section structure) for the Agentic Coding Book. Auto-infers metadata from file paths, suggests tags/related/requirements, and creates part-appropriate section templates. Designed for batch scaffolding all ~50 chapters efficiently.

Build a JIT Modelfile that hardcodes current context into SYSTEM/TEMPLATE/PARAMETER and creates a temporary Ollama model. Use when you need a hyper-focused ephemeral model.

Generates detailed actionable conversion specifications from audit results for architectural migration

End-to-end planning, building, and testing of small-scale browser games in SvelteKit + TypeScript running in Docker, including scaffolding, game loop, input, UI, tests, and Docker dev/release setups. Use when a user asks to create or modify a SvelteKit game project, prototype a simple single-player game, or add tests. When requirements are unclear, ask clarifying questions and offer to choose defaults automatically if the user prefers. This skill uses SvelteKit+TS in Docker only (debug hot-reload + nginx release); do not switch stacks unless the user explicitly asks to change scope. Not for multiplayer, servers, or backend services.

Generate pivot tables from CSV/Excel with aggregations, filters, and automatic chart creation.

Analyze project stack and recommend skills. Auto-detects frameworks, activates generic ai-dev-kit skills, and optionally scaffolds project-specific skills in the target repo.

Generate code comments and docstrings. Use when user asks to "add comments", "document this code", "explain with comments", or "add docstrings".

Browse and view all available uxscii components including bundled templates, user components, and screens when user wants to see, list, browse, or search components

Scaffolds a new Python tool file in 'src/tools/' from a template. Use when asked to create a new agent tool.

Use when writing Vague (.vague) files that need realistic test data using faker generators for names, emails, addresses, dates, and more

Generates concise summaries of log content using type-specific summarization templates

Project-focused specification and task management system with 6 individual commands. Each command MUST be invoked separately and requires user approval before proceeding. Commands: /speckit.init, /speckit.plan, /speckit.tasks, /speckit.analyze, /speckit.clarify, /speckit.implement. NEVER chain commands automatically - each produces output that requires user review. Use /speckit.plan when user wants to create plans from specs. Use /speckit.tasks only AFTER user has approved plans.

Code standards and templates for Django models, views, forms, templates, and URLs in this World of Darkness application. Use when creating new models (characters, items, locations), implementing reference/lookup models (factions, clans, disciplines), building CRUD views, designing forms, setting up URL patterns, or ensuring gameline consistency. Triggers on file creation/editing in characters/, items/, locations/ apps or when implementing polymorphic inheritance patterns.