byagentsope· 48 skills
Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing assertion) and the user wants the agent to converge to "green" on its own. Framework-agnostic — wraps Aider's --auto-lint/--auto-test, an OpenHands SWE-Bench loop, a manual LangGraph cycle, or Claude Code's bash tool just the same.
$npx -y skills add agentsope/skillalchemy --skill agentsop-test-fix-loopInstalls into the current project.
Run `npx skills use "https://github.com/agentsope/skillalchemy" --skill "agentsope/skillalchemy/agentsop-test-fix-loop"` 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/agentsope/skillalchemy" that are relevant to the current task. Run `npx skills add "https://github.com/agentsope/skillalchemy"` and select the relevant skills, then follow their instructions.