{"slug": "spec-kit", "name": "spec-kit", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 4, "commenters": 10, "warners": 3, "score": 1.559, "rising": -1.31, "first": "2025-11-15", "latest": "2026-09-17", "why": "I recommend you look up https://github.com/github/spec-kit. It\u2019s a project out of Microsoft/Github that encodes a rigorous spec-then-implement multi pass workflow.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 1, "compare": 2, "warn": 3}, "spark": [0, 0, 1, 0, 1, 0, 0, 2, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I recommend you look up https://github.com/github/spec-kit. It\u2019s a project out of Microsoft/Github that encodes a rigorous spec-then-implement multi pass workflow.", "icon": true, "domain": null, "github_repo": "github.com/github/spec-kit", "official_url": "https://github.com/github/spec-kit", "pricing": "", "aliases": ["spec-kit", "Spec Kit", "SpecKit", "Spec-Kit"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 776731344, "item_id": 48545709, "url": "https://news.ycombinator.com/item?id=48545709", "by": "shironnnn_", "date": "2026-06-15", "stance": "recommend", "quote": "I use SpecKit to create a very detailed plan with a high amount of specificity", "excerpt": "I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant. The paid products have an ", "context": "", "use_case": "spec-driven planning", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 774641328, "item_id": 48415083, "url": "https://news.ycombinator.com/item?id=48415083", "by": "itake", "date": "2026-06-05", "stance": "recommend", "quote": "spec driven dev (https://github.com/github/spec-kit)", "excerpt": "virgin project: 1/ spec driven dev (https://github.com/github/spec-kit) 2/ then degrade to multiple sessions (no worktrees) debugging various problems until its done On UI Design (MacOS, Web): 1/ AI does a first pass. Try to give it style guidance on my own (colors, style, etc). 2/ Prompt ChatGPT.com with screenshots and ask for recommendations on how to make it better. 3/ Codex the changes (with minor edits) 4/ loop", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 755437232, "item_id": 47214827, "url": "https://news.ycombinator.com/item?id=47214827", "by": "frank00001", "date": "2026-03-01", "stance": "recommend", "quote": "Sounds like the spec driven approach. You should take a look at this", "excerpt": "Sounds like the spec driven approach. You should take a look at this https://github.com/github/spec-kit", "context": "", "use_case": "spec-driven AI development", "switched_from": "", "story": "If AI writes code, should the session be part of the commit?"}, {"id": 744672931, "item_id": 46542058, "url": "https://news.ycombinator.com/item?id=46542058", "by": "mattarm", "date": "2026-01-08", "stance": "recommend", "quote": "I recommend you look up https://github.com/github/spec-kit. It\u2019s a project out of Microsoft/Github that encodes a rigorous spec-then-implement multi pass workflow.", "excerpt": "Yeah, the online Gemini app is not good for long lived conversations that build up a body of decisions. The context window gets too large and things drop. What I\u2019ve learned is that once you reach that point you\u2019ve got to break that problem down into smaller pieces that the AI can work productively with. If you\u2019re about to start with Gemini-cli I recommend you look up https://github.com/github/spec-kit. It\u2019s a project", "context": "", "use_case": "structured AI coding workflow", "switched_from": "", "story": "Opus 4.5 is going to change everything"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 795781856, "item_id": 49736366, "url": "https://news.ycombinator.com/item?id=49736366", "by": "loveparade", "date": "2026-09-17", "stance": "warn", "quote": "I used speckit quite a bit before and I've had mixed results at best.", "excerpt": "That's what I thought too. I used speckit quite a bit before and I've had mixed results at best. You are just moving ambiguity and code review from one place to another without really gaining anything.", "context": "", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 735011713, "item_id": 45938232, "url": "https://news.ycombinator.com/item?id=45938232", "by": "qudat", "date": "2025-11-15", "stance": "warn", "quote": "I think spec-kit is an interesting idea but too heavy handed.", "excerpt": "I\u2019ve done spec driven development using a bunch of markdown files. That works fine but what I have found really works is using beads: https://github.com/steveyegge/beads I\u2019m letting the agent help me draft the specs anyway and I found that the agent is a lot more focused when it can traverse a task tree using beads. It\u2019s the one spec or planning tool that I find really helps get things done without a bunch of interve", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Spec-Driven Development: The Waterfall Strikes Back"}, {"id": 734974800, "item_id": 45935925, "url": "https://news.ycombinator.com/item?id=45935925", "by": "thomascountz", "date": "2025-11-15", "stance": "warn", "quote": "I found the many many hours\u2014tweaking, asking, correcting,  analyzing, adapting, refining, reshaping, etc\u2014before getting to see any code challenging.", "excerpt": "I just tried an experiment using Spec-Kit from GitHub to build a CLI tool. Perhaps the scope of the tool doesn't align itself with Spec-Driven Development, but I found the many many hours\u2014tweaking, asking, correcting, analyzing, adapting, refining, reshaping, etc\u2014before getting to see any code challenging. As would be the case with Waterfall today, the lack of iterative end-to-end feedback is foreign and frustrating ", "context": "", "use_case": "spec-driven development of a CLI tool", "switched_from": "", "story": "Spec-Driven Development: The Waterfall Strikes Back"}]}], "who": [], "tags": [], "use_cases": ["spec-driven development", "spec-driven ai development", "spec-driven ai coding", "structured ai app building", "spec-driven planning", "structured ai coding workflow"], "compared": [{"slug": "superpowers", "name": "Superpowers", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "beads", "name": "Beads", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gemini", "name": "Gemini", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=45935763", "title": "Spec-Driven Development: The Waterfall Strikes Back", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49734264", "title": "OpenSpec \u2013 A lightweight and configurable AI spec framework", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49378768", "title": "Show HN: Huzzah \u2013 a novel approach to coding with AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49022930", "title": "Show HN: A primer for non-coders to design software via structured AI dialogue", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48542100", "title": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48413629", "title": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)", "mentions": 1}], "sentiment_by_month": {"2025-11": {"warn": 2, "neutral": 1}, "2025-12": {}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 2}, "2026-07": {"compare": 1}, "2026-08": {"compare": 1}, "2026-09": {"warn": 1}, "2026-10": {}}, "quotes": [{"id": 795781856, "item_id": 49736366, "url": "https://news.ycombinator.com/item?id=49736366", "by": "loveparade", "date": "2026-09-17", "stance": "warn", "quote": "I used speckit quite a bit before and I've had mixed results at best.", "excerpt": "That's what I thought too. I used speckit quite a bit before and I've had mixed results at best. You are just moving ambiguity and code review from one place to another without really gaining anything.", "context": "", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 790111088, "item_id": 49381943, "url": "https://news.ycombinator.com/item?id=49381943", "by": "kurtis_reed", "date": "2026-08-20", "stance": "compare", "quote": "How is it different from https://github.com/github/spec-kit?", "excerpt": "How is it different from https://github.com/github/spec-kit?", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "Show HN: Huzzah \u2013 a novel approach to coding with AI"}, {"id": 784408432, "item_id": 49025527, "url": "https://news.ycombinator.com/item?id=49025527", "by": "prabhanjana_c", "date": "2026-07-23", "stance": "compare", "quote": "structured app building with let us say https://github.com/github/spec-kit", "excerpt": "Interesting. Still wondering how this is different from a structured app building with let us say https://github.com/github/spec-kit, or using some skills from https://github.com/obra/superpowers. Will try it out.", "context": "", "use_case": "structured AI app building", "switched_from": "", "story": "Show HN: A primer for non-coders to design software via structured AI dialogue"}, {"id": 776731344, "item_id": 48545709, "url": "https://news.ycombinator.com/item?id=48545709", "by": "shironnnn_", "date": "2026-06-15", "stance": "recommend", "quote": "I use SpecKit to create a very detailed plan with a high amount of specificity", "excerpt": "I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant. The paid products have an ", "context": "", "use_case": "spec-driven planning", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 774641328, "item_id": 48415083, "url": "https://news.ycombinator.com/item?id=48415083", "by": "itake", "date": "2026-06-05", "stance": "recommend", "quote": "spec driven dev (https://github.com/github/spec-kit)", "excerpt": "virgin project: 1/ spec driven dev (https://github.com/github/spec-kit) 2/ then degrade to multiple sessions (no worktrees) debugging various problems until its done On UI Design (MacOS, Web): 1/ AI does a first pass. Try to give it style guidance on my own (colors, style, etc). 2/ Prompt ChatGPT.com with screenshots and ask for recommendations on how to make it better. 3/ Codex the changes (with minor edits) 4/ loop", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 755437232, "item_id": 47214827, "url": "https://news.ycombinator.com/item?id=47214827", "by": "frank00001", "date": "2026-03-01", "stance": "recommend", "quote": "Sounds like the spec driven approach. You should take a look at this", "excerpt": "Sounds like the spec driven approach. You should take a look at this https://github.com/github/spec-kit", "context": "", "use_case": "spec-driven AI development", "switched_from": "", "story": "If AI writes code, should the session be part of the commit?"}, {"id": 744672931, "item_id": 46542058, "url": "https://news.ycombinator.com/item?id=46542058", "by": "mattarm", "date": "2026-01-08", "stance": "recommend", "quote": "I recommend you look up https://github.com/github/spec-kit. It\u2019s a project out of Microsoft/Github that encodes a rigorous spec-then-implement multi pass workflow.", "excerpt": "Yeah, the online Gemini app is not good for long lived conversations that build up a body of decisions. The context window gets too large and things drop. What I\u2019ve learned is that once you reach that point you\u2019ve got to break that problem down into smaller pieces that the AI can work productively with. If you\u2019re about to start with Gemini-cli I recommend you look up https://github.com/github/spec-kit. It\u2019s a project", "context": "", "use_case": "structured AI coding workflow", "switched_from": "", "story": "Opus 4.5 is going to change everything"}, {"id": 737264528, "item_id": 46079033, "url": "https://news.ycombinator.com/item?id=46079033", "by": "hmokiguess", "date": "2025-11-28", "stance": "neutral", "quote": "First I hear of spec-kit, that looks very promising, I\u2019m interested in trying it.", "excerpt": "First I hear of spec-kit, that looks very promising, I\u2019m interested in trying it. My approach is to combine beads with superpowers skills https://github.com/obra/superpowers I\u2019m wondering how does it compare to this, gonna give it a try, thanks!", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Beads \u2013 A memory upgrade for your coding agent"}, {"id": 735011713, "item_id": 45938232, "url": "https://news.ycombinator.com/item?id=45938232", "by": "qudat", "date": "2025-11-15", "stance": "warn", "quote": "I think spec-kit is an interesting idea but too heavy handed.", "excerpt": "I\u2019ve done spec driven development using a bunch of markdown files. That works fine but what I have found really works is using beads: https://github.com/steveyegge/beads I\u2019m letting the agent help me draft the specs anyway and I found that the agent is a lot more focused when it can traverse a task tree using beads. It\u2019s the one spec or planning tool that I find really helps get things done without a bunch of interve", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Spec-Driven Development: The Waterfall Strikes Back"}, {"id": 734974800, "item_id": 45935925, "url": "https://news.ycombinator.com/item?id=45935925", "by": "thomascountz", "date": "2025-11-15", "stance": "warn", "quote": "I found the many many hours\u2014tweaking, asking, correcting,  analyzing, adapting, refining, reshaping, etc\u2014before getting to see any code challenging.", "excerpt": "I just tried an experiment using Spec-Kit from GitHub to build a CLI tool. Perhaps the scope of the tool doesn't align itself with Spec-Driven Development, but I found the many many hours\u2014tweaking, asking, correcting, analyzing, adapting, refining, reshaping, etc\u2014before getting to see any code challenging. As would be the case with Waterfall today, the lack of iterative end-to-end feedback is foreign and frustrating ", "context": "", "use_case": "spec-driven development of a CLI tool", "switched_from": "", "story": "Spec-Driven Development: The Waterfall Strikes Back"}]}