bychucksrq· 4 skills
Run behavioral benchmarks against the agent, detect failure patterns, generate guidance patches, apply them with auto-revert safety net. Implements the closed-loop self-improvement cycle from Hermes PR #6120, extended with GEPA-style evolutionary optimization and session mining.
$npx -y skills add chucksrq/awesome-hermes-skills --skill agentic-self-improvementInstalls into the current project.
Run `npx skills use "https://github.com/chucksrq/awesome-hermes-skills" --skill "chucksrq/awesome-hermes-skills/agentic-self-improvement"` 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/chucksrq/awesome-hermes-skills" that are relevant to the current task. Run `npx skills add "https://github.com/chucksrq/awesome-hermes-skills"` and select the relevant skills, then follow their instructions.