ralph-loop
- Repo stars 2,914
- Author updated Live
- Author repo ralph-orchestrator
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @mikeyobrien · no license declared
- Token usage
- Moderate
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: ralph-loop
description: Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to ope…
category: engineering
runtime: no special runtime
---
# ralph-loop output preview
## PART A: Task fit
- Use case: Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Use This Skill For / Workflow / Guardrails” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.”.
- **02** When the source has headings, the agent prioritizes “Use This Skill For / Workflow / Guardrails” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Use This Skill For / Workflow / Guardrails”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: ralph-loop
description: Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to ope…
category: engineering
source: mikeyobrien/ralph-orchestrator
---
# ralph-loop
## When to use
- Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `r…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Use This Skill For / Workflow / Guardrails” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "ralph-loop" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Use This Skill For / Workflow / Guardrails
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, run shell commands, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Ralph Loop
Use this skill to operate Ralph loops from the outside.
Use This Skill For
- Starting or continuing a Ralph run with the right
-cand-Hinputs - Inspecting loop state, worktrees, logs, history, and diffs
- Resuming a hook-suspended loop
- Merging or discarding completed worktree loops
- Debugging unexpected loop behavior with current diagnostics files
Workflow
- Start with
ralph loops listorralph loops list --jsonto establish the current state. - If the user wants execution, run
ralph run ...with the right core config and hats source. - If the loop is stuck or suspicious, inspect
logs,history, anddiffbefore changing state. - If the loop is suspended, read
.ralph/suspend-state.jsonand useralph loops resume <id>. - If a loop is queued or in
needs-review, inspect the diff first, then usemerge,process,retry, ordiscardas appropriate. - Use diagnostics when you need detailed evidence about hats, events, tool calls, parse errors, or performance.
Guardrails
- Prefer the CLI over direct edits to
.ralphstate files. - Treat tasks and memories as the canonical runtime systems; do not center scratchpad as the primary state model.
- Inspect diffs before merging.
- Only remove lock or queue artifacts when the underlying process is confirmed dead.
- Manual edits under
.ralph/are last-resort recovery steps and should be called out explicitly when used.
Read These References When Needed
- For command recipes and operator flows:
references/commands.md - For diagnostics files and suspend-state details:
references/diagnostics.md
Decide Fit First
ralph runor `ralph loops…Design Intent
How To Use It
Boundaries And Review