NLP

Generate structured planning documentation for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs (DATABASE_SCHEMA, API_ENDPOINTS, UI_COMPONENTS, CRITICAL_WORKFLOWS). Use when: starting new Cloudflare Workers/React projects, adding major features to existing apps, breaking large work into manageable phases, or need verified planning before coding begins.

PROTOCOL skill for checkpoint-based context preservation using Serena MCP. Automatically creates checkpoints at wave boundaries and before PreCompact. Enables zero-context-loss multi-session work with structured metadata collection. Use this skill for ALL Shannon projects - checkpoints are mandatory, not optional.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Guide for creating effective Custom Mode prompts and examples for Superwhisper, an AI dictation app. Use when users want to create, improve, or understand Superwhisper custom mode instructions for processing dictated speech with context-awareness, and when users want to generate examples.

Drive autonomous IDE workflows including refactors, TODO cleanup, and context-aware command palette actions; use when asked to automate coding tasks inside the IDE.

[Design System] Lightweight brand guidelines enforcement for UI copy and visual motifs. Use when (1) checking UI labels/buttons/error messages against brand tone, (2) validating color usage in specific contexts, (3) ensuring reserved components are used correctly, (4) user asks to 'check brand guidelines', 'validate brand compliance', 'review copy tone', or 'enforce design rules'.

Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. The Skill follows Stitch best practices—short, directive prompts focused on screens, structure, and visual hierarchy with clear UI vocabulary, concise style cues, and one primary intent per prompt. Trigger when the user wants to prepare or improve prompts for Stitch.

Generate working Python/rclpy code examples for Physical AI & Humanoid Robotics textbook with tier-specific variants (Simulation/Jetson/Robot).

Scans DAPR projects for security issues including plain-text secrets, missing ACLs, insecure configurations, and security best practice violations. Automatically triggers on component file modifications.

Systematic verification of codebase context before code generation to prevent assumption bugs

CSS Container Queries with container units (cqi, cqw, cqh, cqb) combined with Utopia.fyi fluid scales for component-level responsiveness. Use when creating truly modular components that adapt to container size, implementing component-level fluid typography with cqi units, or building context-aware design systems. Extends Utopia philosophy from viewport-based to container-based fluidity.

Generate complete, production-ready MCP (Model Context Protocol) servers with automatic setup, configuration, and Claude Code integration

FLEXIBLE skill for North Star goal tracking with Serena MCP persistence. Parses vague goals into measurable criteria, tracks progress percentages, maintains goal history, integrates with wave execution. Prevents goal drift and context loss through structured storage. Essential for multi-session projects.

Fill PDF forms programmatically with data from JSON, CSV, or dictionaries. Support for text fields, checkboxes, and dropdowns. Batch filling available.

Loads project context, lists existing specs and changes, searches capabilities and requirements. Use when user asks about project state, existing specs, active changes, available capabilities, or needs context discovery. Triggers include "openspec context", "what specs exist", "show changes", "list capabilities", "project context", "find specs", "what's in the spec", "show me specs".

Automatic documentation memory system for AI agents. Ensures context is loaded at session start and documentation is updated after changes.

Railway deployment, CI/CD workflows, GitHub Actions, and smoke tests. Handles Railway configuration, GitHub Actions workflows, deployment automation, and health checks. Use when working with deployment, CI configuration, Railway setup, or infrastructure automation, or when user mentions Railway environments, GitHub Actions, deployment issues, CI failures, "Build failed" errors, smoke test errors, CI/CD pipelines, Docker configuration, or devops workflows.

Semantic and full-text search across indexed collections. Use when user mentions searching a collection, semantic search, vector search, knowledge base, or finding content in indexed code, markdown, or PDFs.

Track complex, multi-session work with dependency graphs using beads issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Context management specialist for multi-agent workflows and long-running tasks. Use when coordinating multiple agents, preserving context across sessions, or managing complex project state. Focuses on context compression and distribution.