Agent skill · software engineering · aiskillstore
backend-ralph-plan
Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects. Generates PLAN.md (task index), task files, and RALPH-PROMPT.md (the actual prompt for ralph-loop). Use for rigorous, iterative implementation requiring quality gates and verification.
Why this skill is useful
Adds a structured planning and execution framework for Django backend projects that includes specific task management and quality control processes.
What it needs
Requires bash installed locally. About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Backend RALPH Plan Skill Purpose This skill creates two deliverables: 1. PLAN.md - Structured task index with quality tracking 2. RALPH-PROMPT.md - The prompt fed to /ralph-wiggum:ralph-loop The key insight: Ralph works by feeding the same prompt repeatedly. Claude sees its previous work in files/git and iterates. RALPH-PROMPT.md becomes that prompt, instructing Claude to work through tasks with strict quality gates. When to Use Backend Django features requiring rigorous quality control Multi-task implementations needing iterative, autonomous execution When you want continuous regression testing between tasks Projects where you'll walk away and let Ralph complete the work When NOT to Use Quick prototypes or exploratory code Frontend projects (create frontend-ralph-plan if needed) Simple tasks that don't need iteration Plans where human judgment is needed at each step The Two-Step Process Step 1: This skill creates the plan Step 2: Run the plan That's it. This command: 1. Reads RALPH-PROMPT.md 2. Extracts the completion promise 3. Invokes /ralph-wiggum:ralph-loop automatically Optional: /plan-directory:run <slug> --max-iterations 50 Required Inputs Input Required Description ------- ---------- ------------- Plan title Yes Human-readable name Plan slug Yes Directory name, kebab-case Task list Yes Tasks with names and scopes Django app path Yes e.g., optimosurveys/ Module path Yes e.g., digest/ Test filter Yes Pytest -k filter Tooling Configuration Input Default Description ------- --------- ------------- Lint command ruff check Prefix with .bin/ if needed Format command ruff format Type check ty Or mypy, pyright Test command pytest Test config e.g., --dc=TestLocalApp Django command django Coverage target 90 Minimum percentage Max iterations 100 Ralph loop limit Task Granularity Guidelines Right-sized tasks for Ralph: Task Size Checklist Items Good For ----------- ----------------- ---------- Too small 1-2 Overhead exceeds value Ideal 4-8 Clear scope, achievable in one …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/backend-ralph-plan