By Triippz
Universal AI development workflow: spec-driven development, TDD, debugging, code review, verification, and workflow automation for all projects
This file provides guidance to AI coding agents when working with code in this repository.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Audit async code for race conditions, deadlocks, resource leaks, and cancellation safety
Explore a design idea collaboratively before implementation
Debug a problem using structured reproduce-isolate-hypothesize-verify-fix
This file provides guidance to AI coding agents when working with code in this repository.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Architecture compliance reviewer that validates module boundaries and dependency direction
Code quality reviewer that checks SOLID principles, readability, and maintainability
Structured debugging agent that follows reproduce-isolate-hypothesize-verify-fix methodology
Triggered when coordinating multi-agent work on large features requiring file ownership
Audit async code for correctness, performance, and safety across Rust (Tokio), Dart/Flutter, Python (asyncio/Celery), Go (goroutines), and TypeScript (Deno/Node). Use when writing, reviewing, or debugging async code, or when user mentions race conditions, deadlocks, cancellation, or async patterns.
Triggered when exploring a new feature, design decision, or technical approach before implementation
Triggered when running architecture, code quality, and security review on code changes
Triggered when investigating and fixing a bug using structured methodology
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Personal AI development utilities — a plugin factory and workflow toolkit for Claude Code. Generates self-contained, stack-tailored plugins from project profiles with full conformance enforcement.
# install dependencies
npm install
# generate a plugin from a profile
node scripts/generate.js --profile profiles/nuv.json
# install into a project
node scripts/install-plugin.js --plugin generated/nuv-superpowers --target ~/PersonalDevelopment/nuvcard
# check for drift
node scripts/doctor.js --target ~/PersonalDevelopment/nuvcard
# repair drifted files
node scripts/repair.js --target ~/PersonalDevelopment/nuvcard --source generated/nuv-superpowers
# validate all schemas
node scripts/validate-schemas.js
All commands support --dry-run (preview without writing), --json (machine-readable output), and --help.
Each profile defines a project's tech stack, review thresholds, and conventions.
| Profile | Stack | Description |
|---|---|---|
nuv | Deno, Hono, HTMX, Supabase, Tailwind | NUVCard digital profile SaaS |
See docs/factory/profile-guide.md for the full field reference and how to create new profiles.
| Command | Purpose |
|---|---|
generate | Profile + templates → self-contained plugin |
generate --update | Propagate template changes to existing plugin |
install-plugin | Plugin → project repo (idempotent, skip_if_exists, deep-merge) |
doctor | Detect drift between installed and expected state |
repair | Fix drifted/missing files from source |
validate-schemas | CI schema validation for all structured files |
brainstorm → write-plan → tdd → execute-plan → review → verify → finish
For complex features: /spec (spec-driven development) → /execute-plan → /review → /verify → /finish
This repo enforces semantic commit messages via hook:
type: [scope] description
Allowed types: feat, fix, perf, build, ci, docs, refactor, test
Examples:
feat: [factory] add new review agent template
fix: [hooks] resolve gateguard session timeout
docs: [factory] update profile guide with new fields
Versioning follows semantic versioning. Commit types map to version bumps:
feat → minor versionfix → patch versionfeat! or BREAKING CHANGE in body → major versionnpm test # all 184 Node.js tests
make test # all bats tests (hooks + installer)
node scripts/validate-schemas.js # schema validation
| Document | Description |
|---|---|
| architecture | System overview, data flow, components, design principles |
| getting started | Step-by-step first use guide |
| profile guide | Field reference, thresholds, creating profiles |
| agent catalog | All agents with model tiers, dispatch rules |
| review process | Full pipeline: dispatch → scoring → auto-fix |
| skills catalog | All workflow skills with commands and phases |
| hook system | Profile gating, GateGuard, dispatcher |
| schema reference | All 7 JSON schemas with examples |
| troubleshooting | Common issues with symptoms, causes, fixes |
Private repository. All rights reserved.
npx claudepluginhub triippz/ai-jesus-team --plugin core-superpowersHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.