{"slug": "obra-superpowers", "name": "obra/superpowers", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 4, "commenters": 4, "warners": 0, "score": 2.893, "rising": -1.31, "first": "2026-02-21", "latest": "2026-07-24", "why": "I found things to take more time and intervene more but the result of it has been that I have found it to work better.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 1, 0, 2, 0, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I found things to take more time and intervene more but the result of it has been that I have found it to work better.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/obra/superpowers", "official_url": "https://github.com/obra/superpowers", "pricing": "", "aliases": ["obra/superpowers", "obra superpowers", "Obra Superpowers"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 777105970, "item_id": 48569123, "url": "https://news.ycombinator.com/item?id=48569123", "by": "Imustaskforhelp", "date": "2026-06-17", "stance": "recommend", "quote": "I found things to take more time and intervene more but the result of it has been that I have found it to work better.", "excerpt": "I have been trying out GLM 5.2 and I am really impressed by it for the most part. To all people on Hackernews, I am curious as to what agent harness are you using it with. Previously I was using opencode and then I switched to using Opencode + obra/superpowers and creating custom skill.md themselves for it. I found things to take more time and intervene more but the result of it has been that I have found it to work ", "context": "", "use_case": "agent skills with opencode", "switched_from": "opencode", "story": "GLM-5.2 is the new leading open weights model on Artificial Analysis"}, {"id": 764513713, "item_id": 47782107, "url": "https://news.ycombinator.com/item?id=47782107", "by": "mschwarz", "date": "2026-04-15", "stance": "recommend", "quote": "test driven dev approach from obra superpowers", "excerpt": "Day to day I run a dev pod (implementor + qa + frontend design), a review pod doing adversarial review with one Claude and one Codex, and an orchestrator pair. I think the best flex here to illustrate real work being done is so far the longest single rig I've kept running continuously was about 4 days, so that means a large implementation spec being executed with test driven dev approach from obra superpowers + indep", "context": "", "use_case": "TDD skill pack for agents", "switched_from": "", "story": "Show HN: OpenRig \u2013 agent harness that runs Claude Code and Codex as one system"}, {"id": 762872208, "item_id": 47679513, "url": "https://news.ycombinator.com/item?id=47679513", "by": "abustamam", "date": "2026-04-07", "stance": "recommend", "quote": "I use a plug-in called Obra Superpowers.", "excerpt": "I give it freedom but with the predefined restrictions. I use a plug-in called Obra Superpowers. Whenever I want to start on a block of work, whether it's a ticket or if I just want to tackle tech debt, I start with the brainstorm command. I say something vague like \"implement X\" or \"last time i tried to vibe code Y, Z happened. I don't want that to happen again. Let's improve the harness.\" It'll ask follow questions", "context": "", "use_case": "Spec-driven AI coding workflow", "switched_from": "", "story": "The Cult of Vibe Coding Is Insane"}, {"id": 753714000, "item_id": 47107125, "url": "https://news.ycombinator.com/item?id=47107125", "by": "deevus", "date": "2026-02-21", "stance": "recommend", "quote": "This is what I do with the obra/superpowers[0] set of skills.", "excerpt": "This is what I do with the obra/superpowers[0] set of skills. 1. Use brainstorming to come up with the plan using the Socratic method 2. Write a high level design plan to file 3. I review the design plan 4. Write an implementation plan to file. We've already discussed this in detail, so usually it just needs skimming. 5. Use the worktree skill with subagent driven development skill 6. Agent does the work using subage", "context": "", "use_case": "Planning and execution agent skills", "switched_from": "", "story": "How I use Claude Code: Separation of planning and execution"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["agent skills", "agent skills with opencode", "tdd skill pack for agents", "spec-driven ai coding workflow", "planning and execution agent skills"], "compared": [{"slug": "opencode", "name": "OpenCode", "co": 2, "switched_from": 1, "switched_to": 0}, {"slug": "oh-my-pi", "name": "oh-my-pi", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49033767", "title": "Ask HN: Any Good Pi.dev Setups?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48567759", "title": "GLM-5.2 is the new leading open weights model on Artificial Analysis", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47772935", "title": "Show HN: OpenRig \u2013 agent harness that runs Claude Code and Codex as one system", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47664912", "title": "The Cult of Vibe Coding Is Insane", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47106686", "title": "How I use Claude Code: Separation of planning and execution", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {}, "2026-04": {"recommend": 2}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {"neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 784551090, "item_id": 49034443, "url": "https://news.ycombinator.com/item?id=49034443", "by": "Imustaskforhelp", "date": "2026-07-24", "stance": "neutral", "quote": "I sometimes use opencode + obra superpowers", "excerpt": "I use oh-my-pi which I can recommend. I sometimes use opencode + obra superpowers and sometimes maki.sh in general as well but especially so on my VPS's as its written in rust. So regarding your question of pi.dev, I personally find oh-my-pi decent.", "context": "", "use_case": "agent skills", "switched_from": "", "story": "Ask HN: Any Good Pi.dev Setups?"}, {"id": 777105970, "item_id": 48569123, "url": "https://news.ycombinator.com/item?id=48569123", "by": "Imustaskforhelp", "date": "2026-06-17", "stance": "recommend", "quote": "I found things to take more time and intervene more but the result of it has been that I have found it to work better.", "excerpt": "I have been trying out GLM 5.2 and I am really impressed by it for the most part. To all people on Hackernews, I am curious as to what agent harness are you using it with. Previously I was using opencode and then I switched to using Opencode + obra/superpowers and creating custom skill.md themselves for it. I found things to take more time and intervene more but the result of it has been that I have found it to work ", "context": "", "use_case": "agent skills with opencode", "switched_from": "opencode", "story": "GLM-5.2 is the new leading open weights model on Artificial Analysis"}, {"id": 764513713, "item_id": 47782107, "url": "https://news.ycombinator.com/item?id=47782107", "by": "mschwarz", "date": "2026-04-15", "stance": "recommend", "quote": "test driven dev approach from obra superpowers", "excerpt": "Day to day I run a dev pod (implementor + qa + frontend design), a review pod doing adversarial review with one Claude and one Codex, and an orchestrator pair. I think the best flex here to illustrate real work being done is so far the longest single rig I've kept running continuously was about 4 days, so that means a large implementation spec being executed with test driven dev approach from obra superpowers + indep", "context": "", "use_case": "TDD skill pack for agents", "switched_from": "", "story": "Show HN: OpenRig \u2013 agent harness that runs Claude Code and Codex as one system"}, {"id": 762872208, "item_id": 47679513, "url": "https://news.ycombinator.com/item?id=47679513", "by": "abustamam", "date": "2026-04-07", "stance": "recommend", "quote": "I use a plug-in called Obra Superpowers.", "excerpt": "I give it freedom but with the predefined restrictions. I use a plug-in called Obra Superpowers. Whenever I want to start on a block of work, whether it's a ticket or if I just want to tackle tech debt, I start with the brainstorm command. I say something vague like \"implement X\" or \"last time i tried to vibe code Y, Z happened. I don't want that to happen again. Let's improve the harness.\" It'll ask follow questions", "context": "", "use_case": "Spec-driven AI coding workflow", "switched_from": "", "story": "The Cult of Vibe Coding Is Insane"}, {"id": 753714000, "item_id": 47107125, "url": "https://news.ycombinator.com/item?id=47107125", "by": "deevus", "date": "2026-02-21", "stance": "recommend", "quote": "This is what I do with the obra/superpowers[0] set of skills.", "excerpt": "This is what I do with the obra/superpowers[0] set of skills. 1. Use brainstorming to come up with the plan using the Socratic method 2. Write a high level design plan to file 3. I review the design plan 4. Write an implementation plan to file. We've already discussed this in detail, so usually it just needs skimming. 5. Use the worktree skill with subagent driven development skill 6. Agent does the work using subage", "context": "", "use_case": "Planning and execution agent skills", "switched_from": "", "story": "How I use Claude Code: Separation of planning and execution"}]}