byagno-agi· 11 skills
Autonomous hardening loop for an existing agent — derive probes from the agent's INSTRUCTIONS, run them against the live container, judge responses, edit the agent file, and re-probe until it reliably does what its instructions say. No user input needed. Use to harden an agent against its stated intent; to make a concrete change instead, use extend-agent.
$npx -y skills add agno-agi/agent-platform-railway --skill improve-agentInstalls into the current project.
Run `npx skills use "https://github.com/agno-agi/agent-platform-railway" --skill "agno-agi/agent-platform-railway/improve-agent"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/agno-agi/agent-platform-railway" that are relevant to the current task. Run `npx skills add "https://github.com/agno-agi/agent-platform-railway"` and select the relevant skills, then follow their instructions.