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 this skill

Ralph Loop

Use when the user wants to dispatch work through scripts/ralph.sh and needs to choose between the global queue and a single design-doc slice.

Modes

  • Global queue: ./scripts/ralph.sh --all-tasks
  • Design-doc scope: ./scripts/ralph.sh --design-doc <name>

If neither flag is passed, Ralph defaults to the global queue. Use --design-doc <name> when the user wants the current task selection and injected queue snapshot limited to tasks linked to that design doc.

What Ralph Injects

For every dispatched task, Ralph writes and injects:

  • current task JSON
  • linked design-doc markdown for the current task
  • all tasks in the current Ralph scope

In --all-tasks mode, that queue snapshot is the repo-wide task list. In --design-doc <name> mode, that queue snapshot is filtered to tasks whose linkedDocs include that design doc.

Required Setup

Attach specs to tasks explicitly before running Ralph in design-doc mode:

tx doc attach <task-id> <prd-doc> --type implements
tx doc attach <task-id> <design-doc> --type references

Ralph scopes by the linked design doc name, not by filename guesses.

Practical Commands

Run against the full queue:

./scripts/ralph.sh --runtime codex --all-tasks
./scripts/ralph.sh --runtime claude --all-tasks

Run against one design doc:

./scripts/ralph.sh --runtime codex --design-doc auth-flow-design
./scripts/ralph.sh --runtime claude --design-doc auth-flow-design

Expectations During Execution

  • Ralph may create follow-up tasks with tx add and subtasks with tx add ... --parent <task-id>.
  • Ralph may reorder work with tx update <id> --score <n> or tx bulk score <n> <id...>.
  • If a non-trivial task is missing its paired PRD/design docs, create docs follow-up work or block the task before large implementation proceeds.

Verification

After changing Ralph behavior, prefer these tests:

bunx --bun vitest run test/integration/ralph-script.test.ts test/integration/ralph-context-bundle-e2e.test.ts

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)04moReviewIntermediate
bazel-build-optimization142moNo flagsAdvanced
github-workflow-automation112moReviewAdvanced
wolf-scripts-core59moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry