Agent skill
ralph-build
Run Ralph autonomous build loop. Use when user asks to "ralph build", "run build loop", or needs to process subtasks autonomously. Executes iterations against a subtasks.json queue.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/ralph-build
SKILL.md
Ralph Build
Execute the Ralph autonomous build loop to process subtasks from a queue.
Usage
/ralph-build [options]
Options
| Option | Description |
|---|---|
--subtasks <path> |
Path to subtasks.json file (will prompt if not provided) |
-i, --interactive |
Pause between iterations for user review |
-p, --print |
Output the prompt without executing (dry run) |
--validate-first |
Run pre-build validation before starting the loop |
--max-iterations <n> |
Maximum retry attempts per subtask (default: 3) |
Workflow
1. Determine Subtasks Path
If --subtasks is not provided, prompt the user:
"Which subtasks.json file should I use? Provide the path or I'll look for
docs/planning/milestones/*/subtasks.json"
2. Print Mode (-p)
If print mode is requested:
- Output the full prompt content that would be sent to Claude
- Do NOT execute any iterations
- Exit after printing
3. Validate First (--validate-first)
If validate-first is requested:
- Run pre-build validation prompt on the next subtask
- If validation fails, report the issue and stop
- If validation passes, proceed to build
4. Execute Build Loop
For each iteration, follow the ralph-iteration workflow:
@context/workflows/ralph/building/ralph-iteration.md
5. Interactive Mode (-i)
After each completed iteration:
- Display summary of what was done
- Prompt: "Continue to next subtask? [Y/n]"
- Wait for user confirmation before proceeding
- User can abort the loop at any time
6. Max Iterations (--max-iterations)
If a subtask fails repeatedly:
- Track retry count per subtask
- Stop after
max-iterationsfailures on the same subtask - Report the failure and suggest next steps
CLI Equivalent
This skill provides the same functionality as:
aaa ralph build [options]
References
- Iteration prompt: @context/workflows/ralph/building/ralph-iteration.md
- Pre-build validation: @context/workflows/ralph/building/pre-build-validation.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?