byguanyang· 61 skills
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
$npx -y skills add guanyang/open-agent-hub --skill harness-engineeringInstalls into the current project.
Run `npx skills use "https://github.com/guanyang/open-agent-hub" --skill "guanyang/open-agent-hub/harness-engineering"` 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/guanyang/open-agent-hub" that are relevant to the current task. Run `npx skills add "https://github.com/guanyang/open-agent-hub"` and select the relevant skills, then follow their instructions.