skills/ralph-feedback-batch-protocol/SKILL.md
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.
npx skillsauth add arisng/github-copilot-fc ralph-feedback-batch-protocolInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when a Ralph-v2 workflow is at rest and a human provides structured feedback for a new iteration.
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 |
When feedback is detected for iteration N+1:
PREVIOUS_STATE = metadata.yaml.orchestrator.state.iteration = N+1.metadata.yaml:
orchestrator.state: REPLANNINGorchestrator.previous_state: <PREVIOUS_STATE>iteration: <N+1>knowledge-promotion fast path or the full replanning pipeline.devops
Programmatically create tldraw whiteboards and visualize them with a self-hosted tldraw instance. Create boards with shapes, text, and connectors, then deploy to a self-hosted server for collaborative editing and gallery management.
tools
Execute Google Cloud Platform operations using the gcloud CLI (and gsutil/bq where applicable). Use when the user wants to: authenticate with GCP, manage GCP resources, deploy applications, configure projects or IAM, view logs, run SQL/BigQuery, or interact with any GCP service from the command line. Triggers on phrases like "gcloud", "Google Cloud CLI", "deploy to GCP", "create a VM", "Cloud Run", "GKE cluster", "Cloud Storage bucket", "set GCP project", "service account", "Cloud Functions", "App Engine deploy", or any request to manage Google Cloud resources via command line.
testing
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
development
Session-scoped git commit orchestrator that commits only current-session changes and leaves unrelated dirty worktree edits untouched. Inherits git-atomic-commit for atomic grouping and commit message execution, and git-commit-scope-constitution for scope governance and validation. Use when asked to commit this session only or isolate commits from mixed worktree state.