← Browse
agent-authoring-toolkit
brokenrobot-xyz ★ 0
A suite for authoring and iteratively improving Claude Code skills and subagents through structured two-pass reviews that produce computed verdicts and apply fixes autonomously. The reviewing skills assess artifact structure first, then perform detailed gap analysis, while the improving skills loop reviews and fixes until reaching an acceptable verdict or hitting a round cap.
Install
> /plugin marketplace add brokenrobot-xyz/agent-skills/tree/HEAD/plugins/agent-authoring-toolkit
> /plugin install agent-authoring-toolkit
Source: https://github.com/brokenrobot-xyz/agent-skills/tree/HEAD/plugins/agent-authoring-toolkit
What it's made of
6 agents · 32 skills
- Commands
- 0
- Agents
- 6
- Skills
- 32
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (brokenrobot-xyz).