agent-plan-act-reflect

SKILLWorkflowcommunity
v0.0.0WenyuChiouMITUpdated 1mo agoSource →

Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from `agent-debate` (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
22Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorWenyuChiou
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from `agent-debate` (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.

Keywords
skillclaude