{"id":"a29c854f-2227-45e4-9cf8-af1b73c2933a","shortId":"vJcHFE","kind":"skill","title":"using-superpowers","tagline":"Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding.","description":"> **⚠️ NON-NEGOTIABLE RULE**\n>\n> If you think there is even a 1% chance a skill might apply to your task, you **MUST** read the skill.\n>\n> **IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.**\n>\n> This is not negotiable. This is not optional. You cannot rationalize your way out of this.\n\n\n# Using Skills\n\n## The Rule\n\n**Check for skills BEFORE ANY RESPONSE.** This includes clarifying questions. Even 1% chance means invoke the Skill tool first.\n\n```dot\ndigraph skill_flow {\n    \"User message received\" [shape=doublecircle];\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    \"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\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 ≠ Permission to Skip Workflows\n\nYour human partner's specific instructions describe WHAT to accomplish, not HOW to accomplish it.\n\n**\"Add X\" or \"Fix Y\"** = the goal, NOT permission to skip brainstorming, TDD, debugging workflows, or other skill-defined processes.\n\n**Red flags indicating you're about to rationalize:**\n- \"The instruction was specific\" → Specific instructions need disciplined process, not shortcuts\n- \"This seems simple\" → Simple instructions trigger the most rationalizations\n- \"The workflow feels overkill\" → Workflows exist because simple tasks become complex\n\n**Why this matters:** Specific instructions mean clear requirements—this is exactly when structured workflows prevent mistakes and save time. Skipping process on \"simple\" tasks is how simple tasks become complex problems.","tags":["using","superpowers","agent","skills","library","codingcossack","agent-framework","agent-skills","agent-system","agent-workflow","agentic-workflow","ai-agents"],"capabilities":["skill","source-codingcossack","skill-using-superpowers","topic-agent-framework","topic-agent-skills","topic-agent-system","topic-agent-workflow","topic-agentic-workflow","topic-ai-agents","topic-anthropic","topic-claude","topic-claude-code","topic-claude-skills","topic-claude-skills-hub","topic-claude-skills-libary"],"categories":["agent-skills-library"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/CodingCossack/agent-skills-library/using-superpowers","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add CodingCossack/agent-skills-library","source_repo":"https://github.com/CodingCossack/agent-skills-library","install_from":"skills.sh"}},"qualityScore":"0.458","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 17 github stars · SKILL.md body (3,800 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":"2026-04-23T07:01:19.938Z","embedding":null,"createdAt":"2026-04-18T23:06:42.095Z","updatedAt":"2026-04-23T07:01:19.938Z","lastSeenAt":"2026-04-23T07:01:19.938Z","tsv":"'1':47,109,182,380 '2':393 'accomplish':464,468 'action':333,364 'adapt':434,439 'add':470 'announc':137,196,201 'anyth':359 'appli':52,64,129,171,175,186,376 'approach':390 'away':435 'becom':344,528,558 'box':136,143,154,159 'brainstorm':384,410,481 'bug':417 'build':408 'builder':402 'cannot':87 'chanc':48,110 'check':22,98,252,261,278,282,289,335,356 'checklist':145,207,209,218 'choic':73 'clarif':162,189 'clarifi':106,264 'clear':536 'codebas':270 'come':262 'complex':345,529,559 'context':258,288,442 'convers':20,287 'could':375 'count':329 'creat':148,210,224 'current':324 'debug':385,418,429,483 'defin':489 'definit':191 'describ':461 'design':399 'determin':387 'diamond':131,147 'digraph':118 'disciplin':12,436,506 'discoveri':9 'doesn':305,327 'domain':422 'domain-specif':421 'dot':117 'doublecircl':125,164 'enforc':7 'ensur':29 'even':45,108,181 'evolv':322 'exact':157,221,231,431,540 'execut':405 'exist':314,524 'explor':268,277 'feel':361,521 'file':285 'first':32,116,259,271,279,296,355,383,411,419 'fix':415,473 'flag':233,492 'flexibl':437 'flow':120 'follow':155,219,229,430 'formal':309 'frontend':398 'frontend-design':397 'gather':294,302 'git/files':283 'goal':476 'guid':404 'human':456 'implement':394,413 'includ':105,161,188 'indic':493 'inform':295,303 'instruct':450,460,500,504,514,534 'invoc':11 'invok':112,132,176,193 'item':152,214,228 'label':179,190,215,222 'lack':286 'let':266,292,406 'll':349 'mandatori':14 'matter':532 'mcp':401 'mcp-builder':400 'mean':111,236,535 'messag':122,166 'meta':5 'meta-skil':4 'might':51,126,168,172,183 'mistak':545 'multipl':373 'must':57,75 'need':256,307,505 'negoti':38,81 'non':37 'non-negoti':36 'one':353 'option':85 'order':379 'overkil':341,522 'partner':457 'pattern':438 'per':151,213,227 'permiss':451,478 'prevent':368,544 'principl':440 'prioriti':371 'problem':560 'proceed':35 'process':381,490,507,550 'product':362 'purpos':141,200,205 'question':107,248,249,265 'quick':284 'ration':88,240,498,518 're':239,495 'read':58,323 'realiti':242 'receiv':123,167 'red':232,491 'relev':24 'rememb':318 'requir':537 'respond':160,187 'respons':28,103 'rigid':427 'rule':39,97 'save':547 'second':396 'seem':511 'shape':124,130,135,142,146,153,158,163 'shortcut':509 'simpl':247,342,512,513,526,552,556 'skill':6,8,25,31,50,60,63,95,100,114,119,128,133,139,156,170,174,177,185,194,198,203,220,230,254,260,272,291,297,310,313,320,321,337,339,367,370,374,382,395,414,424,425,444,488 'skill-defin':487 'skill-first':30 'skill-using-superpowers' 'skip':453,480,549 'source-codingcossack' 'specif':423,459,502,503,533 'start':18 'stop':237 'structur':542 'superpow':3 'task':55,67,251,332,334,392,527,553,557 'tdd':428,482 'tell':273,298,446 'thing':343,354 'think':42 'thought':235,241 'time':366,548 'todo':150,212,226 'todowrit':149,211,225 'tool':115,134,178,195 'topic-agent-framework' 'topic-agent-skills' 'topic-agent-system' 'topic-agent-workflow' 'topic-agentic-workflow' 'topic-ai-agents' 'topic-anthropic' 'topic-claude' 'topic-claude-code' 'topic-claude-skills' 'topic-claude-skills-hub' 'topic-claude-skills-libary' 'trigger':515 'type':426 'undisciplin':363 'use':2,16,76,94,138,197,202,315,346,377 'user':121,165,449 'using-superpow':1 'version':325 'wast':365 'way':90 'workflow':15,33,454,484,520,523,543 'x':409,471 'y':474 'yes':180,216","prices":[{"id":"06b23a57-8c62-4eef-8730-0d417f1e0766","listingId":"a29c854f-2227-45e4-9cf8-af1b73c2933a","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"CodingCossack","category":"agent-skills-library","install_from":"skills.sh"},"createdAt":"2026-04-18T23:06:42.095Z"}],"sources":[{"listingId":"a29c854f-2227-45e4-9cf8-af1b73c2933a","source":"github","sourceId":"CodingCossack/agent-skills-library/using-superpowers","sourceUrl":"https://github.com/CodingCossack/agent-skills-library/tree/main/skills/using-superpowers","isPrimary":false,"firstSeenAt":"2026-04-18T23:06:42.095Z","lastSeenAt":"2026-04-23T07:01:19.938Z"}],"details":{"listingId":"a29c854f-2227-45e4-9cf8-af1b73c2933a","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"CodingCossack","slug":"using-superpowers","github":{"repo":"CodingCossack/agent-skills-library","stars":17,"topics":["agent-framework","agent-skills","agent-system","agent-workflow","agentic-workflow","ai-agents","anthropic","claude","claude-code","claude-skills","claude-skills-hub","claude-skills-libary","code-review","codex","context-engineering","debugging","developer-workflow"],"license":null,"html_url":"https://github.com/CodingCossack/agent-skills-library","pushed_at":"2026-01-03T20:02:38Z","description":"Coding agent skills library for programming workflows | Claude Skills, Codex Skills | Forked from obra/superpower","skill_md_sha":"6239d2dc1db4076e7f6cd5b69d7e68ef5c9e9a9a","skill_md_path":"skills/using-superpowers/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/CodingCossack/agent-skills-library/tree/main/skills/using-superpowers"},"layout":"multi","source":"github","category":"agent-skills-library","frontmatter":{"name":"using-superpowers","description":"Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding."},"skills_sh_url":"https://skills.sh/CodingCossack/agent-skills-library/using-superpowers"},"updatedAt":"2026-04-23T07:01:19.938Z"}}