PolymathWizard

BHIL AI First Development Toolkit — AI skill for Claude Code

AI community

A production-grade methodology repository for building AI-native applications using iterative sprints, where AI coding agents are primary implementors and humans are architects, reviewers, and decisio.

How to install BHIL AI First Development Toolkit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open PolymathWizard/BHIL-AI-First-Development-Toolkit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What BHIL AI First Development Toolkit does

Alternatives in AI

Codex Plugin — 's /codex:adversarial-review command 9.6k ★
Paca — AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday 1.8k ★
Claude Skill Web Clone — Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code 969 ★

README

BHIL AI-First Development Toolkit

**Human-Directed. AI-Enabled. Commercially Tested.**

*"The bottleneck in AI-assisted development is not code generation. It is specification quality."*

**Optimized for:** Claude Code · RuFlo (Agentics Foundation) · RuVector · Solo practitioners building LLM-powered apps

What this toolkit is

This is not a collection of disconnected templates. It is a **cohesive methodology system** where every artifact is designed to feed the next in a traceable, machine-actionable chain:

PRD (what) → SPEC (how) → ADR (why) → TASK (steps) → CODE → REVIEW → DEPLOY
     ↑                                                                      |
     └──────────────────── Sprint Retrospective ────────────────────────────┘

Each sprint produces all artifacts. Each artifact carries traceability IDs linking it to its parents and children. Claude Code reads the chain. RuFlo orchestrates agents across it. RuVector maintains persistent memory across sessions.

Repository structure

/
├── README.md                          ← You are here
├── CLAUDE.md                          ← Claude Code project configuration
├── AGENTS.md                          ← Cross-tool agent context (symlink)
│
├── guides/                            ← How and why — narrative documentation
│   ├── 00-getting-started.md          ← 5-minute setup
│   ├── 01-methodology-overview.md     ← Core philosophy and principles
│   ├── 02-artifact-chain.md           ← How artifacts connect and flow
│   ├── 03-sprint-workflow.md          ← Sprint execution step-by-step
│   ├── 04-context-management.md       ← Preventing context fragmentation
│   ├── 05-ai-native-patterns.md       ← LLM-specific documentation patterns
│   ├── 06-solo-practitioner.md        ←