skills.rest
camaluscamalusCommunity·1 Agent Skills Included

BHIL-AI-First-Development-Toolkit

Specification-driven sprint methodology for building LLM-powered applications

Structures AI-native app development through a traceable PRD, SPEC, ADR, and task artifact chain. Eliminates vague requirements, context loss between sessions, and undocumented model or prompt decisions. Provides sprint templates, evaluation suites, and guardrail specs so coding agents implement features with minimal human rework.
129|24
↗
npx skills add camalus/BHIL-AI-First-Development-Toolkit --all -g -y
Available:

Directs the agent to enforce the PRD-to-SPEC-to-ADR artifact chain, follow always/ask/never rules, manage context budgets, and route requests to the sprint, feature, and ADR skills.

All Skills in This Repository (1)

Pure Emerald Level Indicators
📦 In Repo
camaluscamalus

new-feature

Generate PRD, SPEC, and task artifacts with traceability IDs.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install BHIL AI-First Development Toolkit?▼

Run `npx skills add camalus/BHIL-AI-First-Development-Toolkit --all -g -y` in your terminal to install all skills globally.

What is AI-first development?▼

It is a workflow where coding agents implement features from precise written specifications while humans act as architects and reviewers. This toolkit provides the templates and sprint process to make that handoff reliable.

How do I write acceptance criteria for LLM features?▼

Use probabilistic bands instead of exact outputs, such as a 90% pass rate over 50 runs measured by an evaluation metric. The toolkit's templates and eval suite show exactly how to structure these criteria.

Does this toolkit work with Claude Code and Cursor?▼

Yes. The AGENTS.md file is vendor-neutral and works with Claude Code, Cursor, Devin, GitHub Copilot, and other compatible coding agents.

How do I prevent context loss between agent sessions?▼

Scope each session to one task and write a progress.md handoff file before closing. The toolkit's context management guide explains the 60% compaction rule and session sizing in detail.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills