arc-kit
Enterprise architecture governance for Claude Code and other AI coding assistants. 76 commands draft requirements, business cases and design reviews.
- 2.3k
- JavaScript
- 22 h ago
Enterprise architecture governance for Claude Code and other AI coding assistants. 76 commands draft requirements, business cases and design reviews.
Zero-config goal-to-tasks engine for Claude Code (the Atlas engine). Graded PRD validation, dependency-ordered task graph, evidence-gated execution.
The Wasp Nest: a plugin marketplace of AI coding agents, skills, and workflows for Claude Code, Codex, Cursor, ZCode, and Cowork, with PRDs, shared contracts, and verified delivery.
The definitive guide to Spec-Driven Development: build software with AI agents, from method to production code. Book in EN + pt-BR with a ready-to-use SDD kit for Claude Code.
Governance-enforced Requirements Engineering für KRITIS, NIS2 und DORA. Claude-Skill mit EARS, Gherkin, STRIDE, F-Stufen und Phase Gates.
Forge of Thought is an AI cognitive extension: a workshop where your idea is forged into a decision you can stand behind. You and the AI elicit the idea together until it is whole, reviewers that never saw the conversation attack it, and who decided what and why is recorded. Runs in Claude Code.
Same-case examples and evidence comparing AI coding planning and specification frameworks.
Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host supports orchestration. 17 MCP tools · 1,503 tests.
Build professional, standards-aligned Product Requirements Documents through guided questionnaires -- no technical knowledge needed.
RENAR — стандарт инженерии требований для AI-нативной разработки | Requirements Engineering & Normative Adaptive Regulation (RU/EN, CC BY-SA 4.0)
Interactive benchmark for evaluating LLMs on clarifying ambiguous code requirements. Paper: arXiv:2607.00711
AI requirements intake — plain words in, code-ready requirements out. Deterministic orchestrator (LLM proposes, code decides), question budget, five quality gates, backend-aware enrichment, learning ledgers. Local-first: mock/Ollama/any OpenAI-compatible endpoint.
Seal intent into execution-ready plans. GORE-traced, evidence-grounded planning for AI coding agents.
Evidence-grounded scope intelligence agent that detects ambiguity, contradictions, and cumulative scope drift, cites approved project evidence, and keeps every consequential change behind human review.