{"slug": "shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat", "title": "Shall We? – A pre-engineering sanity check for AI-era feature bloat", "summary": "A new open-source skill called 'Shall We?' has been released to help developers and product managers evaluate whether a feature or product idea is worth building before any code is written. The skill, which implements the Agent Skills standard and works with AI coding agents like Claude Code and Cursor, asks structured questions across business value, market demand, complexity, and risk to deliver a verdict of yes, no, or later. It aims to combat feature bloat during the current AI hype cycle by forcing a pre-engineering sanity check.", "body_md": "\n\n```\n███████╗ ██╗  ██╗  █████╗  ██╗      ██╗         ██╗    ██╗ ███████╗ ██████╗ \n██╔════╝ ██║  ██║ ██╔══██╗ ██║      ██║         ██║    ██║ ██╔════╝ ╚════██╗\n███████╗ ███████║ ███████║ ██║      ██║         ██║ █╗ ██║ █████╗       ██╔╝\n╚════██║ ██╔══██║ ██╔══██║ ██║      ██║         ██║███╗██║ ██╔══╝      ╚═╝  \n███████║ ██║  ██║ ██║  ██║ ███████╗ ███████╗    ╚███╔███╔╝ ███████╗    ██╗  \n╚══════╝ ╚═╝  ╚═╝ ╚═╝  ╚═╝ ╚══════╝ ╚══════╝     ╚══╝╚══╝  ╚══════╝    ╚═╝\n```\n\nA skill that helps you decide whether an idea is worth building — before you build it.\n\nImplements the [Agent Skills](https://agentskills.io) open standard. Works with Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenAI Codex, and [any other compatible agent](https://agentskills.io/clients).\n\nWe're in an AI hype cycle where everyone wants to build everything, just because they can. Features get shipped because they're technically possible. Products get started because the demo looked good. Nobody stops to ask the uncomfortable question.\n\n**Shall we, though?**\n\nThis skill is the uncomfortable question. It was inspired by two characters who've been fighting this battle from different angles:\n\n- The\n**caveman**([grugbrain.dev](https://grugbrain.dev)) — who's been saying*no*to complexity since before it was cool, and whose club has saved more codebases than any design pattern - The\n**ponytail**— the architect who's seen enough hype cycles to know that most ideas aren't bad, they're just badly timed, badly scoped, or solving the wrong problem\n\n`shall-we`\n\nthinks like both of them, but operates one level higher: at the PM layer, where the decision to build (or not) is still cheap. It asks the questions that should happen before any code is written, any ticket is created, any design doc is started.\n\n- Restates your idea to confirm it understood correctly\n- Asks one question at a time — only what it needs to know\n- Stops early if a deal-breaker surfaces\n- Delivers a structured verdict:\n\n```\n## Verdict: YES / NO / LATER\n\n**Why:** ...\n\n**Strengths:**\n- ...\n\n**Concerns:**\n- ...\n\n**What would need to be true for a YES:**\n- ...\n```\n\nThe four lenses: **business value**, **market demand**, **complexity**, and **risk**.\n\n```\n/plugin marketplace add Tacsiazuma/shall-we\n/plugin install shall-we@shall-we\n```\n\nThen invoke with `/shall-we`\n\n.\n\n```\ngemini skills install https://github.com/Tacsiazuma/shall-we.git --consent\n```\n\nClone the skill into Cursor's skill directory:\n\n```\ngit clone https://github.com/Tacsiazuma/shall-we.git /tmp/shall-we\ncp -r /tmp/shall-we/skills/shall-we ~/.cursor/skills/shall-we\n```\n\nCursor picks it up automatically — no restart needed.\n\nCopy the skill into your project:\n\n```\nmkdir -p .agents/skills\ngit clone https://github.com/Tacsiazuma/shall-we.git /tmp/shall-we\ncp -r /tmp/shall-we/skills/shall-we .agents/skills/shall-we\nmkdir -p ~/.agents/skills\ngit clone https://github.com/Tacsiazuma/shall-we.git /tmp/shall-we\ncp -r /tmp/shall-we/skills/shall-we ~/.agents/skills/shall-we\n```\n\nThe skill lives at `skills/shall-we/SKILL.md`\n\nin this repo. Copy or symlink that directory wherever your agent looks for skills. See [agentskills.io/clients](https://agentskills.io/clients) for agent-specific paths.\n\n```\n.\n├── skills/\n│   └── shall-we/\n│       └── SKILL.md       # agentskills.io standard skill\n├── .claude-plugin/\n│   └── marketplace.json   # Claude Code marketplace manifest\n└── plugins/\n    └── shall-we/\n        └── .claude-plugin/\n            └── plugin.json\n```\n\n", "url": "https://wpnews.pro/news/shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat", "canonical_source": "https://github.com/Tacsiazuma/shall-we", "published_at": "2026-06-21 11:37:07+00:00", "updated_at": "2026-06-21 12:07:37.649600+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-agents"], "entities": ["Claude Code", "Cursor", "GitHub Copilot", "Gemini CLI", "OpenAI Codex", "Agent Skills", "Tacsiazuma", "Shall We?"], "alternates": {"html": "https://wpnews.pro/news/shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat", "markdown": "https://wpnews.pro/news/shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat.md", "text": "https://wpnews.pro/news/shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat.txt", "jsonld": "https://wpnews.pro/news/shall-we-a-pre-engineering-sanity-check-for-ai-era-feature-bloat.jsonld"}}