Automates task execution using a PRD-driven loop to ensure all acceptance criteria are verified before completion.
Install
mkdir -p .claude/skills/ralph-jmstar85 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18432" && unzip -o skill.zip -d .claude/skills/ralph-jmstar85 && rm skill.zipInstalls to .claude/skills/ralph-jmstar85
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.
PRD-driven persistence loop until task completion with verification. Activate when user says: ralph, don't stop, must complete, finish this, keep going until done.Key capabilities
- →Maintain a persistence loop until task completion
- →Generate a PRD scaffold with task-specific acceptance criteria
- →Implement stories by delegating to an executor
- →Verify acceptance criteria with fresh evidence
- →Mark stories complete and track progress
- →Perform mandatory cleanup pass and regression re-verification
How it works
The skill maintains a persistence loop that reads from a PRD, picks the highest-priority incomplete story, implements it, and verifies its acceptance criteria. It iterates until all stories pass and are reviewer-verified.
Inputs & outputs
When to use ralph
- →Execute complex features with multiple sub-tasks
- →Manage long-running development goals
- →Verify code requirements against a PRD
- →Maintain state across multiple coding iterations
About this skill
Ralph
Ralph is a PRD-driven persistence loop that keeps working on a task until ALL user stories have passes: true and are reviewer-verified.
When to Use
- Task requires guaranteed completion with verification
- Work may span multiple iterations and needs persistence
- Task benefits from structured PRD-driven execution
When NOT to Use
- Full autonomous pipeline → use
/omg-autopilot - Explore or plan before committing → use
/plan - Quick one-shot fix → delegate to @executor
Flags
--no-prd: Skip PRD generation, work in legacy mode (for trivial fixes)--no-deslop: Skip the mandatory post-review cleanup pass
Steps
1. PRD Setup (first iteration)
- Check if
.omg/prd.jsonexists viaomg_read_prd - If none exists, generate a PRD scaffold with task-specific acceptance criteria
- CRITICAL: Replace generic criteria with specific, testable ones
- Initialize progress tracking
2. Pick Next Story
- Read PRD via
omg_read_prd - Select highest-priority story with
passes: false
3. Implement Current Story
- Delegate to @executor at appropriate complexity level
- If sub-tasks are discovered, add as new stories to PRD
4. Verify Acceptance Criteria
- For EACH criterion, verify with fresh evidence
- Run relevant checks (test, build, lint, typecheck)
- If any criterion NOT met, continue working
5. Mark Story Complete
- Set
passes: trueviaomg_update_story - Record progress in
progress.txt
6. Check PRD Completion
- Call
omg_check_completion - If NOT all complete, loop to Step 2
- If ALL complete, proceed to verification
7. Reviewer Verification
- @verifier checks against specific acceptance criteria from PRD
- @architect reviews for architectural soundness
7.5 Mandatory Cleanup Pass
- Unless
--no-deslop, run/ai-slop-cleaneron changed files only
7.6 Regression Re-verification
- Re-run all tests after cleanup pass
- Only proceed after regression tests pass
8. Completion
- On approval: run
/cancelfor clean exit - On rejection: fix issues, re-verify, loop back
Execution Policy
- Fire independent tasks simultaneously
- Run builds/tests in background
- Deliver full implementation: no scope reduction, no partial completion
Checklist
- All PRD stories have
passes: true - Acceptance criteria are task-specific (not generic)
- All requirements met (no scope reduction)
- Fresh test output shows all tests pass
- Reviewer verification passed
- Cleanup pass completed (or
--no-deslop) - Post-cleanup regression tests pass
When not to use it
- →A quick one-shot fix is needed
Limitations
- →The skill is not for full autonomous pipelines.
- →The skill is not for exploration or planning before committing.
- →The skill is not for quick one-shot fixes.
How it compares
This skill provides a PRD-driven persistence loop with mandatory verification and cleanup passes, ensuring guaranteed task completion and quality, unlike a simple task execution that might not include these checks.
Compared to similar skills
ralph side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ralph (this skill) | 0 | 3mo | No flags | Advanced |
| linear | 10 | 1mo | No flags | Beginner |
| zapier-workflows | 11 | 8mo | Review | Beginner |
| attio-skill-generator | 7 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jmstar85
View all by jmstar85 →You might also like
linear
lobehub
Linear issue management guide. Use when working with Linear issues, creating issues, updating status, or adding comments. Triggers on Linear issue references (LOBE-xxx), issue tracking, or project management tasks. Requires Linear MCP tools to be available.
zapier-workflows
davila7
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
attio-skill-generator
kesslerio
Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.
automation-brainstorm
MacroMan5
Interactive workflow design advisor for Power Automate, n8n, Make, Zapier and other platforms. Guides users through planning automation workflows with smart questions about triggers, actions, data flow, and error handling. Uses research sub-agent to find best practices and generates detailed implementation plan. Triggers when user mentions "create workflow", "build flow", "design automation", "need ideas for", or describes workflow requirements without having a complete design.
daily-briefing
anthropics
Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".
jira
davila7
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.