docs: clarify agent loop skill selection and terminology by kr4chinin · Pull Request #6 · humanlayer/skills · GitHub
Skip to content

docs: clarify agent loop skill selection and terminology - #6

Open
kr4chinin wants to merge 1 commit into
humanlayer:mainfrom
kr4chinin:docs/clarify-agent-loop-skills
Open

docs: clarify agent loop skill selection and terminology#6
kr4chinin wants to merge 1 commit into
humanlayer:mainfrom
kr4chinin:docs/clarify-agent-loop-skills

Conversation

@kr4chinin

Copy link
Copy Markdown

Summary

  • explain when to choose build-iterated-agentic-loop versus design-control-loop
  • make the selection boundary visible in README, plugin metadata, and both skill entrypoints
  • use goal, checker, selector, agent, external changes, and regression gate throughout design-control-loop while keeping control-theory names as an optional mapping
  • update the example, prompt, memory, runner, and workflow templates to use the same plain-language vocabulary

Validation

  • both skill directories pass skill-creator quick_validate.py
  • marketplace and plugin JSON files parse successfully
  • workflow-template.yml parses successfully
  • git diff --check passes
  • legacy control-theory terms remain only in the optional mapping section

Closes #2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

design-control-loop vs build-iterated-agentic-loop?

1 participant