seanrreid

AI/Prompt Engineer agent for BodyCount. Owns nutrition parsing prompts, diary generation, pattern detection logic, meal memory resolution, and tone enforcement. Use when designing prompts, tuning AI output quality, or working on any LLM-powered feature.

API Engineer agent for BodyCount. Owns the Hono backend, D1 schema/migrations, Better Auth integration, OpenRouter integration, and Telegram webhook handler. Use when building backend routes, database operations, or service integrations.

This skill should be used when the user asks to "brainstorm this idea", "help me shape this into a product", "let's figure out how to build this", "turn this into something real", "help me scope this", "what should the MVP look like", "let's work through the details", "generate a PRD", or presents a concept they want to develop into a buildable product. Often follows the inspire skill. Turns Claude into a focused product thinking partner who helps developers shape ideas into clear, buildable plans through collaborative conversation.

Design Engineer agent for BodyCount. Owns the web diary UI, Telegram bot conversation UX, layout, typography, and responsive design. Use when working on user-facing interfaces, conversation flows, or visual design decisions.

DevOps/Infra Engineer agent for BodyCount. Owns Cloudflare Workers deployment, D1 provisioning, wrangler config, Telegram webhook setup, cron triggers, and monitoring. Use when setting up infrastructure, configuring deployment, or managing environment/secrets.

This skill should be used when the user asks to "inspire me", "help me figure out what to build", "brainstorm an app idea", "I have a vague idea", "help me think through this concept", "what should I build", "riff on this idea", or shares any app idea, feature concept, problem needing a technical solution, or half-formed notion they want to explore creatively. Turns Claude into a lateral thinking partner who generates unexpected sparks and pushes past obvious solutions.

Product Manager agent for BodyCount. Orchestrates tasks across the team, sequences work, manages blockers, and tracks milestone progress. Use when you need to plan work, assign tasks, check project status, or make scope decisions.

QA Engineer + Tone Auditor agent for BodyCount. Owns functional testing, edge case coverage, code review, and AI output tone auditing. Use when testing features, reviewing code quality, auditing AI responses for tone violations, or validating end-to-end flows.

End-of-session wrap-up for a RAD project. Gathers the session's commits, updates any plan statuses that changed, appends a dated progress note, outputs a session summary, and flags uncommitted work. Run before ending a work session.

Session startup ritual for a RAD project. Reads CLAUDE.md, guards against working on the default branch, reports plans by status (reading rad/ branch tips), optionally triages open issues, and asks what to focus on. Run at the start of a work session.

Design a context-engineered agent architecture for a new project using the Research → Plan → Implement (RPI) methodology. Use when starting a new project, designing an agent system, or when the user asks to plan an agent architecture, brainstorm agents, or scaffold a multi-agent workflow.

Behavioral Economics assessment of web applications. Navigates a running app like a real user via Chrome DevTools, discovers flows, and produces a scored BE assessment report with prioritized recommendations. Use when assessing UX flows, onboarding, feature design, defaults, and user journeys through a behavioral economics lens. WHEN - behavioral economics assessment, BE audit, UX behavioral review, friction analysis, dark pattern check, assess app behavior, score user flows

Review agent designs against Anthropic's best practices from "Building Effective Agents" (Dec 2024). Evaluates necessity, simplicity, tool design, system prompts, transparency, stopping conditions, human oversight, error handling, architecture match, and modern tool integration. Use when reviewing agent code, agent configs, SKILL.md files, or agent architecture descriptions.

Design a context-engineered agent architecture for a new project using the Research → Plan → Implement (RPI) methodology. Use when starting a new project, designing an agent system, or when the user asks to plan an agent architecture, brainstorm agents, or scaffold a multi-agent workflow.

Design a context-engineered agent architecture for a new project using the Research → Plan → Implement (RPI) methodology. Use when starting a new project, designing an agent system, or when the user asks to plan an agent architecture, brainstorm agents, or scaffold a multi-agent workflow.