{"id":"9ba5dc4c-66a7-477f-a83e-e3e4766fd112","shortId":"ggS86Z","kind":"skill","title":"using-superpowers","tagline":"Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions","description":"**Announce at start:** \"Using Superpowers skill activated.\"\n\n<SUBAGENT-STOP>\nIf you were dispatched as a subagent to execute a specific task, skip this skill.\n</SUBAGENT-STOP>\n\n<EXTREMELY-IMPORTANT>\nIf you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.\n\nIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.\n\nThis is not negotiable. This is not optional. You cannot rationalize your way out of this.\n</EXTREMELY-IMPORTANT>\n\n## Instruction Priority\n\nSuperpowers skills override default system prompt behavior, but **user instructions always take precedence**:\n\n1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority\n2. **Superpowers skills** — override default system behavior where they conflict\n3. **Default system prompt** — lowest priority\n\nIf CLAUDE.md, GEMINI.md, or AGENTS.md says \"don't use TDD\" and a skill says \"always use TDD,\" follow the user's instructions. The user is in control.\n\n## How to Access Skills\n\n**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.\n\n**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.\n\n**In other environments:** Check your platform's documentation for how skills are loaded.\n\n## Platform Adaptation\n\nSkills use Claude Code tool names. Non-CC platforms: see `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.\n\n# Using Skills\n\n## The Rule\n\n**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.\n\n```dot\ndigraph skill_flow {\n    \"User message received\" [shape=doublecircle];\n    \"About to EnterPlanMode?\" [shape=doublecircle];\n    \"Already brainstormed?\" [shape=diamond];\n    \"Invoke brainstorming skill\" [shape=box];\n    \"Might any skill apply?\" [shape=diamond];\n    \"Invoke Skill tool\" [shape=box];\n    \"Announce: 'Using [skill] to [purpose]'\" [shape=box];\n    \"Has checklist?\" [shape=diamond];\n    \"Create TodoWrite todo per item\" [shape=box];\n    \"Follow skill exactly\" [shape=box];\n    \"Respond (including clarifications)\" [shape=doublecircle];\n\n    \"About to EnterPlanMode?\" -> \"Already brainstormed?\";\n    \"Already brainstormed?\" -> \"Invoke brainstorming skill\" [label=\"no\"];\n    \"Already brainstormed?\" -> \"Might any skill apply?\" [label=\"yes\"];\n    \"Invoke brainstorming skill\" -> \"Might any skill apply?\";\n\n    \"User message received\" -> \"Might any skill apply?\";\n    \"Might any skill apply?\" -> \"Invoke Skill tool\" [label=\"yes, even 1%\"];\n    \"Might any skill apply?\" -> \"Respond (including clarifications)\" [label=\"definitely not\"];\n    \"Invoke Skill tool\" -> \"Announce: 'Using [skill] to [purpose]'\";\n    \"Announce: 'Using [skill] to [purpose]'\" -> \"Has checklist?\";\n    \"Has checklist?\" -> \"Create TodoWrite todo per item\" [label=\"yes\"];\n    \"Has checklist?\" -> \"Follow skill exactly\" [label=\"no\"];\n    \"Create TodoWrite todo per item\" -> \"Follow skill exactly\";\n}\n```\n\n## Red Flags\n\nThese thoughts mean STOP—you're rationalizing:\n\n| Thought | Reality |\n|---------|---------|\n| \"This is just a simple question\" | Questions are tasks. Check for skills. |\n| \"I need more context first\" | Skill check comes BEFORE clarifying questions. |\n| \"Let me explore the codebase first\" | Skills tell you HOW to explore. Check first. |\n| \"I can check git/files quickly\" | Files lack conversation context. Check for skills. |\n| \"Let me gather information first\" | Skills tell you HOW to gather information. |\n| \"This doesn't need a formal skill\" | If a skill exists, use it. |\n| \"I remember this skill\" | Skills evolve. Read current version. |\n| \"This doesn't count as a task\" | Action = task. Check for skills. |\n| \"The skill is overkill\" | Simple things become complex. Use it. |\n| \"I'll just do this one thing first\" | Check BEFORE doing anything. |\n| \"This feels productive\" | Undisciplined action wastes time. Skills prevent this. |\n| \"I know what that means\" | Knowing the concept ≠ using the skill. Invoke it. |\n\n## Skill Priority\n\nWhen multiple skills could apply, use this order:\n\n1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task\n2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution\n\n\"Let's build X\" → brainstorming first, then implementation skills.\n\"Fix this bug\" → debugging first, then domain-specific skills.\n\n## Skill Types\n\n**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.\n\n**Flexible** (patterns): Adapt principles to context.\n\nThe skill itself tells you which.\n\n## User Instructions\n\nInstructions say WHAT, not HOW. \"Add X\" or \"Fix Y\" doesn't mean skip workflows.","tags":["using","superpowers","coco","rkz91","agent-skills","agents-md","ai-agents","claude-code","codex","cursor","developer-tools","llm-tools"],"capabilities":["skill","source-rkz91","skill-using-superpowers","topic-agent-skills","topic-agents-md","topic-ai-agents","topic-claude-code","topic-codex","topic-cursor","topic-developer-tools","topic-llm-tools","topic-mcp","topic-pm-tools","topic-product-management","topic-productivity"],"categories":["coco"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/rkz91/coco/using-superpowers","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add rkz91/coco","source_repo":"https://github.com/rkz91/coco","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 7 github stars · SKILL.md body (5,057 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:14:10.044Z","embedding":null,"createdAt":"2026-05-18T13:21:43.564Z","updatedAt":"2026-05-18T19:14:10.044Z","lastSeenAt":"2026-05-18T19:14:10.044Z","tsv":"'1':55,120,292,432,643 '2':132,656 '3':142 'absolut':67 'access':177 'action':289,583,614 'activ':32,214,217,228 'adapt':248,697,702 'add':719 'agents.md':127,152 'alreadi':340,391,393,400 'alway':117,162 'announc':26,360,446,451 'anyth':609 'appli':60,75,297,352,405,414,421,425,436,639 'approach':653 'automat':273 'away':698 'becom':594 'behavior':113,138 'box':348,359,366,377,382 'brainstorm':341,345,392,394,396,401,409,647,673 'bug':680 'build':671 'builder':665 'cannot':98 'cc':257 'chanc':56,293 'check':237,306,502,511,528,532,539,585,606 'checklist':368,457,459,468 'choic':84 'clarif':385,439 'clarifi':24,514 'claud':180,251 'claude.md':125,149 'cli':212,266 'code':181,252 'codebas':520 'codex':261 'come':512 'complex':595 'concept':627 'conflict':141 'content':192,231 'context':508,538,705 'control':174 'convers':8,537 'could':638 'count':579 'creat':371,460,474 'current':574 'debug':648,681,692 'default':110,136,143 'definit':441 'demand':233 'design':662 'determin':650 'diamond':343,354,370 'digraph':327 'direct':128,201 'disciplin':699 'dispatch':36 'document':241 'doesn':555,577,724 'domain':685 'domain-specif':684 'dot':326 'doublecircl':334,339,387 'enterplanmod':337,390 'environ':236 'equival':264 'establish':9 'even':53,290,431 'evolv':572 'exact':380,471,481,694 'execut':41,668 'exist':564 'explicit':123 'explor':518,527 'feel':611 'file':209,535 'find':12 'first':509,521,529,546,605,646,674,682 'fix':678,722 'flag':483 'flexibl':700 'flow':329 'follow':165,199,378,469,479,693 'formal':559 'frontend':661 'frontend-design':660 'full':230 'gather':544,552 'gemini':211,220,265 'gemini.md':126,150,275 'get':268 'git/files':533 'guid':667 'highest':130 'implement':657,676 'includ':23,384,438 'inform':545,553 'instruct':105,116,124,169,713,714 'invoc':19 'invok':69,188,280,302,309,344,355,395,408,426,443,631 'item':375,464,478 'know':621,625 'label':398,406,429,440,465,472 'lack':536 'let':516,542,669 'll':599 'load':194,221,246,272 'lowest':146 'map':271 'mcp':664 'mcp-builder':663 'mean':298,486,624,726 'messag':331,416 'metadata':223 'might':59,296,349,402,411,418,422,433 'multipl':636 'must':68,86 'name':254 'need':322,506,557 'negoti':92 'never':202 'non':256 'non-cc':255 'one':603 'option':96 'order':642 'overkil':591 'overrid':109,135 'pattern':701 'per':374,463,477 'platform':239,247,258 'preced':119 'present':196 'prevent':618 'principl':703 'prioriti':106,131,147,634 'process':644 'product':612 'prompt':112,145 'purpos':364,450,455 'question':25,498,499,515 'quick':534 'ration':99,490 're':489 'read':205,573 'realiti':492 'receiv':332,417 'red':482 'references/codex-tools.md':260 'relev':281 'rememb':568 'request':129,283 'requir':16 'respond':383,437 'respons':22,287 'rigid':690 'rule':279 'say':153,161,715 'second':659 'see':259 'session':225 'shape':333,338,342,347,353,358,365,369,376,381,386 'simpl':497,592 'situat':318 'skill':15,17,31,47,58,71,74,108,134,160,178,184,190,208,213,218,222,244,249,277,284,295,304,310,328,346,351,356,362,379,397,404,410,413,420,424,427,435,444,448,453,470,480,504,510,522,541,547,560,563,570,571,587,589,617,630,633,637,645,658,677,687,688,707 'skill-using-superpowers' 'skip':45,727 'source-rkz91' 'specif':43,686 'start':6,28,226 'stop':487 'subag':39 'superpow':3,30,107,133 'system':111,137,144 'take':118 'task':44,78,501,582,584,655 'tdd':157,164,691 'tell':523,548,709 'thing':593,604 'think':50 'thought':485,491 'time':616 'todo':373,462,476 'todowrit':372,461,475 'tool':18,185,206,219,253,263,270,357,428,445 'topic-agent-skills' 'topic-agents-md' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-developer-tools' 'topic-llm-tools' 'topic-mcp' 'topic-pm-tools' 'topic-product-management' 'topic-productivity' 'turn':311 'type':689 'undisciplin':613 'use':2,4,14,29,87,156,163,182,203,250,276,324,361,447,452,565,596,628,640 'user':115,121,167,171,267,330,415,712 'using-superpow':1 'version':575 'via':215,274 'wast':615 'way':101 'workflow':728 'wrong':315 'x':672,720 'y':723 'yes':407,430,466","prices":[{"id":"13643d5f-2394-4929-b4a6-5afd79412b34","listingId":"9ba5dc4c-66a7-477f-a83e-e3e4766fd112","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"rkz91","category":"coco","install_from":"skills.sh"},"createdAt":"2026-05-18T13:21:43.564Z"}],"sources":[{"listingId":"9ba5dc4c-66a7-477f-a83e-e3e4766fd112","source":"github","sourceId":"rkz91/coco/using-superpowers","sourceUrl":"https://github.com/rkz91/coco/tree/main/skills/using-superpowers","isPrimary":false,"firstSeenAt":"2026-05-18T13:21:43.564Z","lastSeenAt":"2026-05-18T19:14:10.044Z"}],"details":{"listingId":"9ba5dc4c-66a7-477f-a83e-e3e4766fd112","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"rkz91","slug":"using-superpowers","github":{"repo":"rkz91/coco","stars":7,"topics":["agent-skills","agents-md","ai","ai-agents","claude-code","codex","cursor","developer-tools","llm-tools","mcp","pm-tools","product-management","productivity","prompt-engineering","workflow-automation"],"license":"mit","html_url":"https://github.com/rkz91/coco","pushed_at":"2026-04-26T01:51:27Z","description":"Open-source library of AI superpowers — 59 skills, 34 commands, 10 agents + 24 GSD subagents, 3 system bundles. An entire team, wherever your AI lives. Vendor-neutral across Claude Code, Cursor, Codex, and any AGENTS.md tool.","skill_md_sha":"ba4836e32da916bb4d5f3fc70c6f211380ad287d","skill_md_path":"skills/using-superpowers/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/rkz91/coco/tree/main/skills/using-superpowers"},"layout":"multi","source":"github","category":"coco","frontmatter":{"name":"using-superpowers","description":"Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions"},"skills_sh_url":"https://skills.sh/rkz91/coco/using-superpowers"},"updatedAt":"2026-05-18T19:14:10.044Z"}}