Menu
Autonomous task completion loop with PRD tracking and persistent progress memory
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/CleanExpo/Unite-Group --skill ralph-wiggumThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
| name | ralph-wiggum |
| category | workflow |
| version | 2.0.0 |
| description | Autonomous task completion loop with PRD tracking and persistent progress memory |
| author | Unite Group (ported from NodeJS-Starter-V1, adapted for Next.js-only stack) |
| priority | 2 |
| auto_load | false |
| triggers | ["ralph","autonomous","loop","prd","overnight"] |
| requires | ["verification-first","context-partitioning"] |
| context | fork |
A simple, powerful pattern for autonomous multi-iteration development:
plans/prd.json โ JSON file with user stories, each with a passes booleanplans/progress.txt โ Append-only LLM memory between iterationsNamed after Ralph Wiggum from The Simpsons โ simple but effective.
"Me fail English? That's unpossible!" โ Ralph Wiggum
| Problem | Solution |
|---|---|
| LLMs lose context between sessions | progress.txt persists learnings |
| Tendency to declare victory | Verification gate blocks false completion |
| No structured task state | prd.json machine-readable task list |
| Complex orchestration overhead | Simple loop, no LangGraph needed |
plans/prd.json){
"project": "Unite-Group Nexus",
"version": "1.0.0",
"user_stories": [
{
"id": "US-001",
"epic": "Social",
"title": "Persona avatar upload",
"description":
| Field | Purpose |
|---|---|
passes | Only true after verification gate passes |
priority | Execution order: critical > high > medium > low |
depends_on | Story IDs that must pass first |
acceptance_criteria | Specific, verifiable requirements |
attempt_count | Tracks failed attempts โ escalate at 3 |
plans/progress.txt)Append-only. The LLM reads this at the start of each iteration to learn from previous failures.
# Ralph Progress Log
# Project: Unite-Group Nexus
# Created: 20/03/2026
---
## Session 1: 20/03/2026 10:30 AEST
**Task**: US-001 โ Persona avatar upload
**Status**: IN_PROGRESS
### Work Done
- Added file input to SocialPersonasManager.tsx
- Wired to Supabase Storage upload
### Issues Encountered
- Type error: `File | null` not assignable โ needs explicit null check
### Learnings
- Supabase Storage path must include founder_id: `avatars/${founderId}/${personaId}`
- Use `useState<File | null>(null)` not `useState(null)` for file state
### Next Steps
1. Fix null check on file input handler
2. Run Tier A verification
---
## Session 2: 20/03/2026 11:00 AEST
**Task**: US-001 โ Persona avatar upload
**Status**: COMPLETED
### Work Done
- Fixed null check
- All Tier A verification passed
### Learnings
- Supabase Storage public URL: `supabase.storage.from('avatars').getPublicUrl(path).data.publicUrl`
### Next Steps
- Move to US-002
ALL must pass before marking passes: true:
pnpm run type-check # TypeScript โ always required
pnpm run lint # ESLint โ always required
pnpm vitest run # Unit tests โ if verification.unit_tests: true
pnpm build # Build โ if verification.build: true
E2E (Playwright) is run manually or via CI only โ not in the loop by default.
Iteration N:
1. All stories passed? โ EXIT (done)
2. Find highest-priority unpassed story (respect depends_on)
3. Read progress.txt โ load learnings from previous attempts
4. Produce context manifest (context-partitioning skill)
5. Implement per acceptance criteria
6. Run verification pipeline
7. PASS โ set passes: true โ git commit โ append to progress.txt
FAIL โ increment attempt_count โ record issue โ append to progress.txt
8. Next iteration
| Condition | Action |
|---|---|
attempt_count >= 3 | Stop โ record blocker โ skip to next story โ flag for human review |
| Dependency not yet passed | Skip story โ work on next available |
| Verification tool fails (not code) | Record as infra blocker โ do not increment attempt_count |
# Via slash command
/ralph run 50 # Max 50 iterations
# Manual: provide this prompt to Claude Code
"Read plans/prd.json and plans/progress.txt.
Find the highest-priority unpassed story.
Implement it, verify it, update both files.
Repeat until all stories pass or you reach {N} iterations."
Previous learnings prevent repeating the same mistake across sessions.
Creates safe checkpoints โ a failed story doesn't undo previous work.
# Commit format
git commit -m "feat(US-001): persona avatar upload"
All implementations follow en-AU defaults automatically via the pre-response hook:
For stories requiring 3+ agents, Ralph delegates to the Harness instead of implementing directly:
Story requires frontend + database + API changes
โ Ralph creates manifest per context-partitioning skill
โ Dispatches to Agent Harness (AGENT_HARNESS.md)
โ Harness returns structured result
โ Ralph runs verification gate
โ Ralph updates prd.json and progress.txt
.claude/skills/custom/verification-first/SKILL.md.claude/skills/custom/context-partitioning/SKILL.mdThe authoritative environment-variable registry for the Unite-Group Nexus. Use whenever adding, reading, renaming, or debugging an env var or secret โ new integration config, a `process.env.X` read, an auth/OAuth wiring, a cron secret, a "which variable holds this" question, or a "works locally but not in prod" symptom. Also use before pinning any variable name in code, and when reconciling the two credential planes (Vercel prod vs the local hermes fleet). Prevents the `APIFY_API_KEY` vs `APIFY_API_TOKEN` class of drift.
Create, verify, and promote Supabase schema changes via database branches. Every schema change/migration must be validated on a Supabase database branch before prod (see CLAUDE.md line 44).
Verify production Supabase schema before shipping code that touches it. Use BEFORE writing or reviewing ANY code that reads or writes a Supabase table in the Nexus โ new queries, inserts, updates, CHECK-constrained values, RLS-dependent reads, cron data access โ even one-line changes and even when the table "obviously" exists. Also use immediately when a query fails with "column does not exist", when inserts appear to succeed but produce no rows, or when generated TypeScript types disagree with runtime behaviour.
Based on SOC occupation classification
