Talk Marsden Agent Desktops
Use when the user asks about Luke Marsden's talk "Giving Every Agent Its Own Desktop: Lessons from Dogfooding HelixML" — including questions about HelixML, giving each agent its own GPU-accelerated desktop, spec-driven development with plan/implement phases, scaling agents by task vs by org-shape, centralized vs per-developer agent infrastructure, forking Zed for remote control, ZFS-cloned Docker-in-Docker dev environments, mixing local models (Llama 3.1) with frontier models (Claude Opus), the "snake eating its own tail" dogfooding approach, self-improving companies, or applying his design op
Install
npx skills add jscraik/Agent-Skills --skill talk-marsden-agent-desktopsgit clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Plugins/aidevcon/skills/talk-marsden-agent-desktops ~/.claude/skills/talk-marsden-agent-desktopsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Giving Every Agent Its Own Desktop: Lessons from Dogfooding HelixML — Luke Marsden Luke Marsden (CEO, Helix; ex-ClusterHQ, ex-Dotscience, former Kubernetes SIG cluster-lifecycle lead) argues that all information work is becoming agent management, starting with software engineering. He lays out an opinionated design space for systems that run agents on the server — give each *agent* its own computer (not each human), keep an IDE, scale by task, drive everything through a plan-then-implement spec flow, and dogfood the whole thing until "the snake eats its own tail." He demos HelixML, where Kanban tasks spin up GPU-accelerated streaming Linux desktops, each running a forked Zed IDE, with multiplayer human-in-the-loop spec review and in-browser QA. ## Grounding rules — MUST follow when answering 1. Before answering any specific question, read `outline.md` to locate the relevant section, then read that section of `transcript.md`. 2. When attributing words, **quote short, non-sensitive excerpts** from `transcript.md`. Never put quotation marks around paraphrased content. 3. If a claim isn't in `transcript.md`, say "the talk doesn't address this" — do not infer positions from outside knowledge. 4. Cite by transcript line range whenever possible.
Details
- Skill name
talk-marsden-agent-desktops- Repository
- jscraik/Agent-Skills
- Path
Plugins/aidevcon/skills/talk-marsden-agent-desktops/SKILL.md- License
- Apache-2.0
- Repo updated
- 16 November 2026
FAQ
What does the Talk Marsden Agent Desktops skill do?
Use when the user asks about Luke Marsden's talk "Giving Every Agent Its Own Desktop: Lessons from Dogfooding HelixML" — including questions about HelixML, giving each agent its own GPU-accelerated desktop, spec-driven development with plan/implement phases, scaling agents by task vs by org-shape, centralized vs per-developer agent infrastructure, forking Zed for remote control, ZFS-cloned Docker-in-Docker dev environments, mixing local models (Llama 3.1) with frontier models (Claude Opus), the "snake eating its own tail" dogfooding approach, self-improving companies, or applying his design op
How do I install the Talk Marsden Agent Desktops skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill talk-marsden-agent-desktops. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Talk Marsden Agent Desktops popular?
It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.
Related skills
1password
9jscraik/Agent-Skills
Plan, diagnose, and validate 1Password CLI workflows. Use when tasks need op CLI sign-in, secret references, op run, op inject, item reads, env injection, or service-account secret access.
Agentation
9jscraik/Agent-Skills
Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are failing.
Agents Md
9jscraik/Agent-Skills
Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.
Talk Obstbaum Willoughby Vibes to Metrics
9jscraik/Agent-Skills
Use when the user asks about Simon Obstbaum and Rob Willoughby's AI Native DevCon talk on measuring AI agents, output evals versus trajectory evals, instrumentation, compliance, and skill activation metrics.
Talk Luebken Embedding Pi Coding Agent
9jscraik/Agent-Skills
Explains, summarizes, and turns Matthias Luebken's talk on embedding Pi-style coding agents into safe product-design artifacts: tool-contract sketches, guardrail checklists, session-record models, and malleable-software review plans. Use when the user asks about OpenClaw, Pi-style product agents, lifecycle guardrails, agent sessions, or design-level application of these primitives.
Talk Roberts AI Native Brownfield
9jscraik/Agent-Skills
Use when the user asks about Katie Roberts''s talk "Stop Maintaining, Start Evolving: Applying AI-Native Practices to Brownfield Codebases" — including questions about using AI to build large complex systems (her ~350k-line Rust S3 clone experiment), test oracles, flaky tests with AI agents, why 100% test coverage is the wrong goal, human-in-the-loop AI coding, AI-assisted performance engineering, using the type system to enforce invariants, tracing as an AI debugging tool, or applying her approach to brownfield/legacy modernisation work.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.