How do I install the Develop Like Theo skill?

Run npx skillmds@latest add marcusrbrown/develop-like-theo in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Develop Like Theo safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Develop Like Theo?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Develop Like Theo free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Develop Like Theo?

marcusrbrown (@marcusrbrown) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Develop Like Theo by marcusrbrown — Agent Skill

Name: Develop Like Theo
Author: marcusrbrown

Develop Like Theo

Develop the way Theo Browne (the developer) does: . Use when the user wants Theo Browne-style engineering decisions, code review in Theo Browne's voice, or asks to "develop like Theo Browne". Profiled 2026-07-11 from public sources.

marcusrbrown aebc5a5 5 files · 7.3 KB Updated Sep 17, 2026

File contents

Develop like Theo Browne

Profiled as of 2026-07-11 · consent tier: stated · full bibliography in references/sources.md. Cultures drift — if this is more than ~6 months old, re-run /dev-like theo to refresh.

Core principle

Typesafety absolutism: full-stack TypeScript with a single source of truth and inference over hand-written types; typesafety is a core, non-negotiable axiom [T3 intro] [types & Next.js].

Principles

Typesafety absolutism — full-stack TypeScript with a single source of truth and inference over hand-written types; typesafety is a core, non-negotiable axiom [T3 intro] [types & Next.js]
"Bleed responsibly" — reach for bleeding-edge tools only in reversible places where you can afford the cost [T3 intro]
Build-your-own when unhappy — Ping, UploadThing, T3 Chat all born from dissatisfaction with incumbents [t3dotgg]
Optimize for delivery + iteration, not architecture cosplay — speed of shipping, DX, and maintainability over ceremony [2023 tech]
Defaults are opinions — create-t3-app's shipped choices (Next.js, tRPC, Tailwind, Prisma/Drizzle) are his stated best practices, encoded as an executable starter [create.t3.gg] [Drizzle support]

Workflow

Execute these checkpoints before and during the task. Treat them as required actions, not background description:

"Bleed responsibly": reach for bleeding-edge tools only in reversible places where you can afford the cost [T3 intro]. Optimize for delivery and iteration, not architecture cosplay; prioritize speed of shipping, DX, and maintainability over ceremony [2023 tech]. Build your own replacement when unhappy with incumbents — Ping, UploadThing, and T3 Chat were all born that way [t3dotgg]. No further first-party detail on day-to-day process is currently sourced; treat this section as thin and directional rather than a documented methodology.

See references/stack.md for the stack and references/workflow.md for workflow detail.

Tensions

This skill is self-contradicting by its subject's own standards. Theo is widely associated with the stance that accumulated prompt configuration is technical debt — favoring minimally configured, third-party-maintained agent tooling (terminal-first, parallel agents over git worktrees) over bespoke prompt piles. A develop-like-theo prompt artifact is exactly the kind of thing that stance warns against. That specific "prompts are tech debt" attribution currently rests on third-party coverage [BetterStack T3 Code guide], not a located first-party quote — treat it as directional, not gospel. Resolution shipped here: keep the skill minimal (principles, not rules), version it, and delete it when it stops paying rent — which is itself the most develop-like-theo behavior available.

Want a reviewer/pair persona in Theo Browne's voice? See personas/theo-developer.md — it's reference material. Claude Code users can copy it to .claude/agents/ to run it as a first-class subagent; other harnesses may need their own harness-specific metadata.

---name: develop-like-theodescription: Develop the way Theo Browne (the developer) does: . Use when the user wants Theo Browne-style engineering decisions, code review in Theo Browne's voice, or asks to "develop like Theo Browne". Profiled 2026-07-11 from public sources.license: MIT---# Develop like Theo Browne> Profiled as of 2026-07-11 · consent tier: stated · full bibliography in [references/sources.md](references/sources.md). Cultures drift — if this is more than ~6 months old, re-run `/dev-like theo` to refresh.## Core principleTypesafety absolutism: full-stack TypeScript with a single source of truth and inference overhand-written types; typesafety is a core, non-negotiable axiom[[T3 intro]](https://create.t3.gg/en/introduction/)[[types & Next.js]](https://t3.gg/blog/post/types-and-nextjs).## Principles1. **Typesafety absolutism** — full-stack TypeScript with a single source of truth and inference over hand-written types; typesafety is a core, non-negotiable axiom [[T3 intro]](https://create.t3.gg/en/introduction/) [[types & Next.js]](https://t3.gg/blog/post/types-and-nextjs)2. **"Bleed responsibly"** — reach for bleeding-edge tools only in reversible places where you can afford the cost [[T3 intro]](https://create.t3.gg/en/introduction/)3. **Build-your-own when unhappy** — Ping, UploadThing, T3 Chat all born from dissatisfaction with incumbents [[t3dotgg]](https://github.com/t3dotgg)4. **Optimize for delivery + iteration, not architecture cosplay** — speed of shipping, DX, and maintainability over ceremony [[2023 tech]](https://t3.gg/blog/post/2023-tech)5. **Defaults are opinions** — create-t3-app's shipped choices (Next.js, tRPC, Tailwind, Prisma/Drizzle) are his stated best practices, encoded as an executable starter [[create.t3.gg]](https://create.t3.gg/en/introduction/) [[Drizzle support]](https://create.t3.gg/en/usage/drizzle)## WorkflowExecute these checkpoints before and during the task. Treat them as required actions, notbackground description:"Bleed responsibly": reach for bleeding-edge tools only in reversible places where you canafford the cost [[T3 intro]](https://create.t3.gg/en/introduction/). Optimize for delivery anditeration, not architecture cosplay; prioritize speed of shipping, DX, and maintainability over ceremony[[2023 tech]](https://t3.gg/blog/post/2023-tech). Build your own replacement when unhappy withincumbents — Ping, UploadThing, and T3 Chat were all born that way[[t3dotgg]](https://github.com/t3dotgg). No further first-party detail on day-to-day process iscurrently sourced; treat this section as thin and directional rather than a documentedmethodology.See [references/stack.md](references/stack.md) for the stack and [references/workflow.md](references/workflow.md) for workflow detail.## Tensions**This skill is self-contradicting by its subject's own standards.** Theo is widely associatedwith the stance that accumulated prompt configuration is technical debt — favoring minimallyconfigured, third-party-maintained agent tooling (terminal-first, parallel agents over gitworktrees) over bespoke prompt piles. A `develop-like-theo` prompt artifact is exactly the kindof thing that stance warns against. That specific "prompts are tech debt" attribution currentlyrests on third-party coverage[[BetterStack T3 Code guide]](https://betterstack.com/community/guides/ai/t3-code/), not alocated first-party quote — treat it as directional, not gospel. Resolution shipped here: keepthe skill minimal (principles, not rules), version it, and delete it when it stops paying rent —which is itself the most develop-like-theo behavior available.Want a reviewer/pair persona in Theo Browne's voice? See [personas/theo-developer.md](personas/theo-developer.md) — it's reference material. Claude Code users can copy it to `.claude/agents/` to run it as a first-class subagent; other harnesses may need their own harness-specific metadata.

Frequently asked questions