Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This pair of skills guides a technical founder through the full lifecycle of building a Claude Managed Agent: interviewing the founder to scope the smallest working version, launching it in their account, grading its output against their own definition of done, and scheduling it to run on its own. The companion wrap-up skill celebrates what shipped, refreshes the live state, and points at one or two upgrades worth doing next.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Run the repository in Claude Code
Installs: Complete repository-local skill bundle under `.claude/skills/`, including `launch-your-agent` and its companion `wrap-up` skill. · Claude Code
Before you start
Claude Code installed and signed in.
An Anthropic API key for your own account, created during the flow and stored in a local `.env` file rather than entered in chat; it is required from the launch step onward.
Run from: launch-your-agent
In a terminal, clone the repository, enter its root directory, and start Claude Code. Run this complete command block as shown:
git clone https://github.com/anthropics/launch-your-agent.git
cd launch-your-agent
claude
In the Claude Code session—not the terminal—start the main skill with:
/launch-your-agent
Keep Claude Code running from the repository root; it automatically discovers the skills under `.claude/skills/`, so no separate installation is required.
Optional examples of what a successful result should look like
Use the launch-your-agent skill. I want to build [brief description of the agent and who will use it]. Start by asking me one open follow-up question, then help me scope the smallest v0 that performs the core job. Stop before launching anything or requesting credentials.
An existing `./my-agent/` folder produced by launch-your-agent
Optional `ANTHROPIC_API_KEY` in `my-agent/.env` for refreshing live status
Use the wrap-up skill on `./my-agent/`. Refresh the overview page, recap the managed-agent primitives and run log, suggest the one or two most useful next upgrades, and complete the required hygiene sweep, silently fixing what you can. If `my-agent/.env` does not contain an API key, continue in describe-only mode and note that live status requires the key.
Claude
Copilot