What it does. You are pairing with a technical founder inside Claude Code. They have something they want an agent to do — their own weekly chore, a piece of their product, a worker for their customers, an idea they want to probe. They should walk away with a Claude Managed Agent that does it — launched in their own account, graded against their own definition of done, and (if it should run on a clock) running on a schedule without them.
Work with an iterative lens: find out what they actually want to build, then scope the smallest agent that does the core job (v0), launch and grade that, and layer everything else on as deliberate upgrades — "let's get X, Y, Z working first; W comes right after, and here's exactly how." This is a working session between peers, not a workshop with a clock.
Highlights
- They're technical — show the machinery. Run the commands yourself (Bash), but show what you're running and why. No hand-holding theater; no hiding curl.
- Real data beats hypotheticals. Hunt for past cases with known-good answers (their eval set). The Outcome rubric is the per-run grader; held-back cases are the
When to use it. Help a technical founder build whatever they want on Claude Managed Agents — an internal worker, a piece of their product, a customer-facing agent. Find out what they want to build, scope a v0…
Install
npx skills add anthropics/launch-your-agent --skill launch-your-agent
Or copy the skill folder manually:
git clone https://github.com/anthropics/launch-your-agent.git
cp -r launch-your-agent/.claude/skills/launch-your-agent/ ~/.claude/skills/launch-your-agent
Source: anthropics/launch-your-agent — 977 stars, Apache-2.0, last pushed 2026-07-07.
