Runs tasks through local scripts (Ralph) with injected design-doc context and queue state.

Install

mkdir -p .claude/skills/ralph-loop-jamesaphoenix && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13591" && unzip -o skill.zip -d .claude/skills/ralph-loop-jamesaphoenix && rm skill.zip

Installs to .claude/skills/ralph-loop-jamesaphoenix

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.
147 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Dispatch tasks using `scripts/ralph.sh`
  • →Scope task processing to either the full repo queue or a single design document
  • →Inject current task JSON into the runtime
  • →Inject linked design-doc markdown for the current task
  • →Inject a snapshot of all tasks in the current Ralph scope

How it works

The skill executes `scripts/ralph.sh` to process tasks, either from the global queue or scoped to a design document. It injects task-specific JSON, linked design-doc markdown, and a queue snapshot into the runtime for each dispatched task.

Inputs & outputs

You give it
A request to run Ralph, optionally specifying `--all-tasks` or `--design-doc <name>` and a `--runtime`.
You get back
Dispatched tasks, potentially with new follow-up tasks or reordered work, and injected context for the runtime.

When to use ralph-loop

  • →Dispatch tasks in design-doc mode
  • →Run full repo queue tasks
  • →Automate task workflow execution

About ralph-loop

This skill executes the `ralph.sh` script to process tasks. It allows scoping to either the full repo queue or specific design docs, injecting necessary task data for the agent runtime.

Run Ralph against either the full repo queue or tasks linked to one design doc, with injected task/spec/queue context for Codex or Claude runtimes.

When not to use it

  • →When the user does not want to dispatch work through `scripts/ralph.sh`
  • →When tasks are not explicitly attached to design documents for design-doc mode
  • →When the user wants to merge PRs directly

Limitations

  • →Ralph scopes by the linked design doc name, not by filename guesses
  • →If a non-trivial task is missing its paired PRD/design docs, follow-up work or blocking is needed
  • →Ralph may create follow-up tasks with `tx add` and subtasks with `tx add ... --parent <task-id>`

How it compares

This skill automates the dispatching of tasks through a `ralph.sh` script with specific scoping and context injection, providing a structured workflow for task management compared to manual task execution.

Compared to similar skills

ralph-loop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ralph-loop (this skill)07moReviewIntermediate
bazel-build-optimization146moNo flagsAdvanced
github-workflow-automation116moReviewAdvanced
wolf-scripts-core51yReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry