Agent skill
ralph-feedback-batch-protocol
Ralph-v2 post-iteration feedback batch protocol for creating feedback directories, authoring feedbacks.md, and advancing a session into replanning. Use when processing human feedback after an iteration or resuming Ralph from feedback artifacts.
Install this agent skill to your Project
npx add-skill https://github.com/arisng/github-copilot-fc/tree/main/skills/ralph-feedback-batch-protocol
SKILL.md
Ralph Feedback Batch Protocol
Use this skill when a Ralph-v2 workflow is at rest and a human provides structured feedback for a new iteration.
Directory Layout
Feedback batches live at:
.ralph-sessions/<SESSION_ID>/iterations/<N+1>/feedbacks/<yyyyMMdd-HHmmss>/
Artifacts such as logs or screenshots should be stored beside feedbacks.md.
feedbacks.md Template
---
iteration: <N+1>
timestamp: <ISO8601>
previous_iteration: <N>
---
# Feedback Batch: <timestamp>
## Critical Issues
- [ ] **ISS-001**: Description
- Evidence: app.log, lines 45-60
- Suggested Fix: ...
## Quality Issues
- [ ] **Q-001**: Description
## New Requirements
- Feature X
## Artifacts Index
| File | Description |
|------|-------------|
| app.log | Server logs |
Orchestrator Transition Rules
When feedback is detected for iteration N+1:
- Record
PREVIOUS_STATE = metadata.yaml.orchestrator.state. - Set
iteration = N+1. - Update
metadata.yaml:orchestrator.state: REPLANNINGorchestrator.previous_state: <PREVIOUS_STATE>iteration: <N+1>
- Enter the replanning workflow.
- Let Planner decide whether to take the
knowledge-promotionfast path or the full replanning pipeline.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
fleet
Multi-iteration parallel subagent orchestrator for Kimi Code CLI with streamlined observability, automated documentation, and atomic commits. Use when orchestrating complex work across multiple subagents, enabling parallel execution, or when explicitly requesting fleet mode with '/flow:fleet'. Integrates diataxis documentation and git-atomic-commit workflow.
github-pages-deploy
Deploy a static HTML file or static site directory to GitHub Pages. Use when the user wants a durable GitHub-hosted URL for a static page, diagram, report, or generated site, and can provide GitHub authentication via GITHUB_TOKEN or GH_TOKEN.
Didn't find tool you were looking for?