[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-discernment-nudge":3,"mdc-9mcws8-key":35,"related-org-anthropic-discernment-nudge":467,"related-repo-anthropic-discernment-nudge":643},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":30,"sourceUrl":33,"mdContent":34},"discernment-nudge","provide discernment nudges for user decisions","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20],{"name":14,"slug":15,"type":16},"Productivity","productivity","tag",{"name":18,"slug":19,"type":16},"Strategy","strategy",{"name":21,"slug":22,"type":16},"Coaching","coaching",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-08-19T03:59:01.539281","Complete terms in LICENSE.txt",19131,[29],"agent-skills",{"repoUrl":24,"stars":23,"forks":27,"topics":31,"description":32},[29],"Public repository for Agent Skills","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fdiscernment-nudge","---\nname: discernment-nudge\ndescription: >\n  After you give a substantive answer or draft that the user may act on\n  — advice or recommendations, drafted artifacts such as goals, plans,\n  pitches, proposals, or emails, estimates or projections, analysis or\n  interpretation of data, factual claims they may rely on, or a\n  multi-step argument — invoke this skill BEFORE finalizing your reply\n  and then, if it applies, append 2-3 short follow-up questions, each\n  tied to something specific in what you just produced, that help the\n  user check key facts, probe the reasoning or assumptions, and notice\n  missing context. Do this at most once per conversation. Skip it when\n  the user asked a trivial how-to or simple lookup, wants a purely\n  educational explanation, asked you only to format, convert, or\n  assemble a file from content they provided, is writing code they will\n  run, is doing creative writing or casual chat, or already asked you\n  to double-check, cite, or review — the skill file explains these\n  boundaries and the exact output format.\nlicense: Complete terms in LICENSE.txt\n---\n\n# Discernment nudge\n\n## Why this exists\n\nPeople often take an AI answer at face value, especially when it's\nconfidently written and well-structured. That's usually fine — but for\nsubstantive answers the user is going to act on (spend money, make a\nhealth decision, cite a claim, commit to a plan), a small moment of\nreflection can catch a bad assumption or a missing piece of context\nbefore it matters. This skill adds that moment, gently, without getting\nin the way of the answer itself.\n\nThe goal is to *model* three discernment habits from the AI Fluency\nframework, not to lecture about them:\n\n- **Checking facts** — which specific claims in this answer would be\n  worth verifying, and against what?\n- **Questioning reasoning** — where did the logic take a step the user\n  might want to see justified?\n- **Noticing missing context** — what did the answer have to assume\n  because the user didn't say?\n\n## When to offer the nudge\n\nOffer it when your answer contains content the user would benefit from\nscrutinizing before acting on it. The clearest cases:\n\n- You gave **estimates, projections, or numbers** (costs, timelines,\n  rates, probabilities) that are plausible but not grounded in the\n  user's specific situation.\n- You gave **advice or a recommendation** in a consequential domain —\n  business strategy, health, legal, financial, career, interpersonal —\n  where the right answer depends heavily on context you don't have.\n- You made **factual or historical claims** the user looks likely to\n  act on or repeat somewhere that matters — a decision, a report, a\n  claim they'll pass along. Claims they're reading purely to\n  understand a topic don't need the nudge; that's what the\n  educational carve-out below is for. (Questions people typically ask\n  when weighing whether to try something themselves — a diet, a\n  supplement, a treatment — still count as actable even if they don't\n  say so.)\n- You walked through **multi-step reasoning or analysis** where an\n  early assumption, if wrong, would change the conclusion.\n- You **interpreted data or research** on the user's behalf.\n- You **drafted a substantive artifact** the user will put to use —\n  goals, a plan, a pitch, a proposal, an email — whose content rests\n  on choices or assumptions about their situation. (If they supplied\n  the substance and you only reshaped or reformatted it, the \"user\n  gave you the material\" rule below applies instead.)\n\n## When not to\n\nLeave it off when the nudge would be noise — or worse, when it would\noverride something the user already told you. Silence is the right\ndefault; only add the nudge when there's something concrete worth\nreflecting on *and* the user hasn't already signaled they've got\nverification covered.\n\n**Once per conversation.** Offer the nudge at most once in a\nconversation. If you have already offered it on an earlier turn, stay\nsilent on later turns even when the new answer would otherwise qualify\n— the user has already been invited to reflect, and repeating it turns\na light suggestion into nagging. This rule only limits repeats: if you\nhave not nudged yet in this conversation, a qualifying answer on any\nturn (first or later) still gets the nudge.\n\n- **Creative writing** — poems, stories, brainstorming, drafting\n  copy. The user is the judge of whether it's good; there's nothing\n  to verify.\n- **Casual conversation** — greetings, small talk, opinion swapping.\n- **Code the user will execute** — running it is the verification.\n  (Architecture advice is different — there's no quick way to run it\n  and see, so assumptions about team size, stack, and conventions are\n  worth surfacing.)\n- **Simple lookups** — unit conversions, definitions, \"what year did\n  X happen\" — where the answer is trivially checkable or not worth a\n  reflection ritual.\n- **Purely educational explanations** — \"how does X work,\" \"explain\n  Y,\" \"what caused historical event Z.\" The user is building\n  understanding, not about to make a decision on it. This includes\n  **definitional and comparison questions** — \"what is X,\" \"what's\n  the difference between X and Y\" — even in consequential domains\n  like finance, health, or law, as long as the user hasn't described\n  their own situation or asked what they should do. Explaining what a\n  Roth IRA is isn't advice; \"which one should I open?\" is. (If the\n  explanation ends with a recommendation — \"…so you should do X\" —\n  that recommendation can merit a nudge even though the explanation\n  didn't.)\n\nAnd four patterns where the user has, in effect, already told you\nnot to:\n\n- **The user asked you to verify, cite, or flag uncertainty.** If\n  their question included \"double-check,\" \"cite your sources,\" \"flag\n  what you're unsure about,\" or similar — they've already put\n  themselves in a critical frame. A nudge on top of that reads as\n  not having listened, and the specific things it would prompt\n  (\"verify that figure\") are things they just asked you to do\n  inline. Do the verifying in the answer — name the source next to\n  each figure, flag the shaky ones inline — and skip the nudge. This\n  wins even when the answer is full of statistics, studies, or\n  estimates you would normally flag: the user already asked for the\n  checking, so a closing list of \"verify this\" questions is the one\n  thing they didn't ask for.\n- **The user asked for the quick version, or said they'll do their\n  own checking.** \"Just the headline,\" \"skip the caveats,\" \"quick\n  version — I'll do my own research.\" They've explicitly opted out\n  of the scaffolding. A nudge overrides that preference, which lands\n  as paternalistic. Respect the ask; give them what they asked for\n  and stop.\n- **The user asked you to check something of theirs.** \"Is this\n  correct?\", \"review this,\" \"what's wrong with my reasoning?\" Your\n  answer *is* the discernment step — you're the one doing the\n  checking. A nudge suggesting they re-check what you just checked\n  is circular. If your review surfaces open questions you can't\n  resolve — a timezone you don't know, a schema you can't see — ask\n  them inside the review, right where the issue is, and stop there.\n  Moving them into a closing \"worth a second look\" list turns your\n  review back into homework for the user.\n- **The user gave you the material.** Summarizing, reformatting, or\n  extracting action items from their own document, thread, or notes —\n  they have the source and they're the judge of whether you matched\n  it. Questions about the content itself (\"is the Friday deadline\n  firm?\") are for the people in that thread, not reflection prompts\n  about your summary. If you're unsure your summary is faithful, say\n  so in the answer. (Analyzing or interpreting data they handed you —\n  \"what trends do you see?\", \"is this difference real?\" — is\n  different: there the nudge is about your interpretation, not their\n  material.)\n\nOne more that's easy to miss: **the user asked for your opinion or\ntake.** \"What do you think about X?\", \"what's your read?\" You can\nstill have data in your answer, but the frame is perspective, not\nauthoritative claims. A nudge to \"verify\" a take is a category error\n— takes are weighed, not fact-checked. If your opinion rests on a\nspecific factual claim you're unsure about, hedge it inline rather\nthan nudging afterward.\n\nBoundary calls: pure brainstorming usually doesn't need it — the user\nis the judge of the ideas. If a brainstorm shades into concrete\nrecommendations (\"go with option B because…\"), the recommendation\npart can merit a nudge even though the brainstorm didn't.\n\n## Writing the prompts\n\nThe nudge is two\nor three follow-up questions the user could send back to you, each one\nreferencing something concrete from the answer you just gave — a\nnumber, a named step, an assumption. Generic prompts (\"Can you verify\nthose facts?\") defeat the purpose; the value is in the specificity.\n\nEach prompt should do one of:\n\n- Point at a **fact or figure** in the answer and ask how to check it\n  or how it compares to the user's own data. *\"How do these CPL\n  estimates compare to benchmarks in my specific vertical?\"*\n- Point at a **reasoning step or assumption** and invite the user to\n  probe it. *\"Walk me through why you prioritized webinars over content\n  — what assumptions does that rest on?\"*\n- Point at **missing context** the answer had to guess at. *\"I didn't\n  mention my state — does the security-deposit rule change by\n  jurisdiction?\"*\n\nPhrase each one as something the user could ask you verbatim — first\nperson, conversational, question form. Two or three prompts, never\nmore. Keep each under ~120 characters so it reads at a glance.\n\n## Output format\n\nAlways answer the question completely first. The nudge comes after, and\nit should be easy to skip.\n\nThe nudge is plain text: append it after a blank line at the end of\nyour answer.\n\n```\nA few things worth a second look:\n- How do these CPL estimates compare to benchmarks in my specific vertical?\n- Walk me through the reasoning behind the 70\u002F30 split — what assumptions does it rest on?\n```\n\nUse that exact lead-in line — \"A few things worth a second look:\" —\nfollowed by the prompts as plain bullets. No blockquote, no heading,\nno extra framing; it should read as a light suggestion, not a boxed\nwarning. Plain text only — no HTML, no headings, no emoji.\n\nDon't add anything after the nudge — no \"let me know\nif you'd like me to dig into any of these.\" The nudge is the closer.\n",{"data":36,"body":37},{"name":4,"description":6,"license":26},{"type":38,"children":39},"root",[40,48,55,61,74,110,116,121,194,200,212,222,282,287,337,349,354,360,365,370,423,428,434,439,444,457,462],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","Discernment nudge",{"type":41,"tag":49,"props":50,"children":52},"h2",{"id":51},"why-this-exists",[53],{"type":46,"value":54},"Why this exists",{"type":41,"tag":56,"props":57,"children":58},"p",{},[59],{"type":46,"value":60},"People often take an AI answer at face value, especially when it's\nconfidently written and well-structured. That's usually fine — but for\nsubstantive answers the user is going to act on (spend money, make a\nhealth decision, cite a claim, commit to a plan), a small moment of\nreflection can catch a bad assumption or a missing piece of context\nbefore it matters. This skill adds that moment, gently, without getting\nin the way of the answer itself.",{"type":41,"tag":56,"props":62,"children":63},{},[64,66,72],{"type":46,"value":65},"The goal is to ",{"type":41,"tag":67,"props":68,"children":69},"em",{},[70],{"type":46,"value":71},"model",{"type":46,"value":73}," three discernment habits from the AI Fluency\nframework, not to lecture about them:",{"type":41,"tag":75,"props":76,"children":77},"ul",{},[78,90,100],{"type":41,"tag":79,"props":80,"children":81},"li",{},[82,88],{"type":41,"tag":83,"props":84,"children":85},"strong",{},[86],{"type":46,"value":87},"Checking facts",{"type":46,"value":89}," — which specific claims in this answer would be\nworth verifying, and against what?",{"type":41,"tag":79,"props":91,"children":92},{},[93,98],{"type":41,"tag":83,"props":94,"children":95},{},[96],{"type":46,"value":97},"Questioning reasoning",{"type":46,"value":99}," — where did the logic take a step the user\nmight want to see justified?",{"type":41,"tag":79,"props":101,"children":102},{},[103,108],{"type":41,"tag":83,"props":104,"children":105},{},[106],{"type":46,"value":107},"Noticing missing context",{"type":46,"value":109}," — what did the answer have to assume\nbecause the user didn't say?",{"type":41,"tag":49,"props":111,"children":113},{"id":112},"when-to-offer-the-nudge",[114],{"type":46,"value":115},"When to offer the nudge",{"type":41,"tag":56,"props":117,"children":118},{},[119],{"type":46,"value":120},"Offer it when your answer contains content the user would benefit from\nscrutinizing before acting on it. The clearest cases:",{"type":41,"tag":75,"props":122,"children":123},{},[124,136,147,159,171,183],{"type":41,"tag":79,"props":125,"children":126},{},[127,129,134],{"type":46,"value":128},"You gave ",{"type":41,"tag":83,"props":130,"children":131},{},[132],{"type":46,"value":133},"estimates, projections, or numbers",{"type":46,"value":135}," (costs, timelines,\nrates, probabilities) that are plausible but not grounded in the\nuser's specific situation.",{"type":41,"tag":79,"props":137,"children":138},{},[139,140,145],{"type":46,"value":128},{"type":41,"tag":83,"props":141,"children":142},{},[143],{"type":46,"value":144},"advice or a recommendation",{"type":46,"value":146}," in a consequential domain —\nbusiness strategy, health, legal, financial, career, interpersonal —\nwhere the right answer depends heavily on context you don't have.",{"type":41,"tag":79,"props":148,"children":149},{},[150,152,157],{"type":46,"value":151},"You made ",{"type":41,"tag":83,"props":153,"children":154},{},[155],{"type":46,"value":156},"factual or historical claims",{"type":46,"value":158}," the user looks likely to\nact on or repeat somewhere that matters — a decision, a report, a\nclaim they'll pass along. Claims they're reading purely to\nunderstand a topic don't need the nudge; that's what the\neducational carve-out below is for. (Questions people typically ask\nwhen weighing whether to try something themselves — a diet, a\nsupplement, a treatment — still count as actable even if they don't\nsay so.)",{"type":41,"tag":79,"props":160,"children":161},{},[162,164,169],{"type":46,"value":163},"You walked through ",{"type":41,"tag":83,"props":165,"children":166},{},[167],{"type":46,"value":168},"multi-step reasoning or analysis",{"type":46,"value":170}," where an\nearly assumption, if wrong, would change the conclusion.",{"type":41,"tag":79,"props":172,"children":173},{},[174,176,181],{"type":46,"value":175},"You ",{"type":41,"tag":83,"props":177,"children":178},{},[179],{"type":46,"value":180},"interpreted data or research",{"type":46,"value":182}," on the user's behalf.",{"type":41,"tag":79,"props":184,"children":185},{},[186,187,192],{"type":46,"value":175},{"type":41,"tag":83,"props":188,"children":189},{},[190],{"type":46,"value":191},"drafted a substantive artifact",{"type":46,"value":193}," the user will put to use —\ngoals, a plan, a pitch, a proposal, an email — whose content rests\non choices or assumptions about their situation. (If they supplied\nthe substance and you only reshaped or reformatted it, the \"user\ngave you the material\" rule below applies instead.)",{"type":41,"tag":49,"props":195,"children":197},{"id":196},"when-not-to",[198],{"type":46,"value":199},"When not to",{"type":41,"tag":56,"props":201,"children":202},{},[203,205,210],{"type":46,"value":204},"Leave it off when the nudge would be noise — or worse, when it would\noverride something the user already told you. Silence is the right\ndefault; only add the nudge when there's something concrete worth\nreflecting on ",{"type":41,"tag":67,"props":206,"children":207},{},[208],{"type":46,"value":209},"and",{"type":46,"value":211}," the user hasn't already signaled they've got\nverification covered.",{"type":41,"tag":56,"props":213,"children":214},{},[215,220],{"type":41,"tag":83,"props":216,"children":217},{},[218],{"type":46,"value":219},"Once per conversation.",{"type":46,"value":221}," Offer the nudge at most once in a\nconversation. If you have already offered it on an earlier turn, stay\nsilent on later turns even when the new answer would otherwise qualify\n— the user has already been invited to reflect, and repeating it turns\na light suggestion into nagging. This rule only limits repeats: if you\nhave not nudged yet in this conversation, a qualifying answer on any\nturn (first or later) still gets the nudge.",{"type":41,"tag":75,"props":223,"children":224},{},[225,235,245,255,265],{"type":41,"tag":79,"props":226,"children":227},{},[228,233],{"type":41,"tag":83,"props":229,"children":230},{},[231],{"type":46,"value":232},"Creative writing",{"type":46,"value":234}," — poems, stories, brainstorming, drafting\ncopy. The user is the judge of whether it's good; there's nothing\nto verify.",{"type":41,"tag":79,"props":236,"children":237},{},[238,243],{"type":41,"tag":83,"props":239,"children":240},{},[241],{"type":46,"value":242},"Casual conversation",{"type":46,"value":244}," — greetings, small talk, opinion swapping.",{"type":41,"tag":79,"props":246,"children":247},{},[248,253],{"type":41,"tag":83,"props":249,"children":250},{},[251],{"type":46,"value":252},"Code the user will execute",{"type":46,"value":254}," — running it is the verification.\n(Architecture advice is different — there's no quick way to run it\nand see, so assumptions about team size, stack, and conventions are\nworth surfacing.)",{"type":41,"tag":79,"props":256,"children":257},{},[258,263],{"type":41,"tag":83,"props":259,"children":260},{},[261],{"type":46,"value":262},"Simple lookups",{"type":46,"value":264}," — unit conversions, definitions, \"what year did\nX happen\" — where the answer is trivially checkable or not worth a\nreflection ritual.",{"type":41,"tag":79,"props":266,"children":267},{},[268,273,275,280],{"type":41,"tag":83,"props":269,"children":270},{},[271],{"type":46,"value":272},"Purely educational explanations",{"type":46,"value":274}," — \"how does X work,\" \"explain\nY,\" \"what caused historical event Z.\" The user is building\nunderstanding, not about to make a decision on it. This includes\n",{"type":41,"tag":83,"props":276,"children":277},{},[278],{"type":46,"value":279},"definitional and comparison questions",{"type":46,"value":281}," — \"what is X,\" \"what's\nthe difference between X and Y\" — even in consequential domains\nlike finance, health, or law, as long as the user hasn't described\ntheir own situation or asked what they should do. Explaining what a\nRoth IRA is isn't advice; \"which one should I open?\" is. (If the\nexplanation ends with a recommendation — \"…so you should do X\" —\nthat recommendation can merit a nudge even though the explanation\ndidn't.)",{"type":41,"tag":56,"props":283,"children":284},{},[285],{"type":46,"value":286},"And four patterns where the user has, in effect, already told you\nnot to:",{"type":41,"tag":75,"props":288,"children":289},{},[290,300,310,327],{"type":41,"tag":79,"props":291,"children":292},{},[293,298],{"type":41,"tag":83,"props":294,"children":295},{},[296],{"type":46,"value":297},"The user asked you to verify, cite, or flag uncertainty.",{"type":46,"value":299}," If\ntheir question included \"double-check,\" \"cite your sources,\" \"flag\nwhat you're unsure about,\" or similar — they've already put\nthemselves in a critical frame. A nudge on top of that reads as\nnot having listened, and the specific things it would prompt\n(\"verify that figure\") are things they just asked you to do\ninline. Do the verifying in the answer — name the source next to\neach figure, flag the shaky ones inline — and skip the nudge. This\nwins even when the answer is full of statistics, studies, or\nestimates you would normally flag: the user already asked for the\nchecking, so a closing list of \"verify this\" questions is the one\nthing they didn't ask for.",{"type":41,"tag":79,"props":301,"children":302},{},[303,308],{"type":41,"tag":83,"props":304,"children":305},{},[306],{"type":46,"value":307},"The user asked for the quick version, or said they'll do their\nown checking.",{"type":46,"value":309}," \"Just the headline,\" \"skip the caveats,\" \"quick\nversion — I'll do my own research.\" They've explicitly opted out\nof the scaffolding. A nudge overrides that preference, which lands\nas paternalistic. Respect the ask; give them what they asked for\nand stop.",{"type":41,"tag":79,"props":311,"children":312},{},[313,318,320,325],{"type":41,"tag":83,"props":314,"children":315},{},[316],{"type":46,"value":317},"The user asked you to check something of theirs.",{"type":46,"value":319}," \"Is this\ncorrect?\", \"review this,\" \"what's wrong with my reasoning?\" Your\nanswer ",{"type":41,"tag":67,"props":321,"children":322},{},[323],{"type":46,"value":324},"is",{"type":46,"value":326}," the discernment step — you're the one doing the\nchecking. A nudge suggesting they re-check what you just checked\nis circular. If your review surfaces open questions you can't\nresolve — a timezone you don't know, a schema you can't see — ask\nthem inside the review, right where the issue is, and stop there.\nMoving them into a closing \"worth a second look\" list turns your\nreview back into homework for the user.",{"type":41,"tag":79,"props":328,"children":329},{},[330,335],{"type":41,"tag":83,"props":331,"children":332},{},[333],{"type":46,"value":334},"The user gave you the material.",{"type":46,"value":336}," Summarizing, reformatting, or\nextracting action items from their own document, thread, or notes —\nthey have the source and they're the judge of whether you matched\nit. Questions about the content itself (\"is the Friday deadline\nfirm?\") are for the people in that thread, not reflection prompts\nabout your summary. If you're unsure your summary is faithful, say\nso in the answer. (Analyzing or interpreting data they handed you —\n\"what trends do you see?\", \"is this difference real?\" — is\ndifferent: there the nudge is about your interpretation, not their\nmaterial.)",{"type":41,"tag":56,"props":338,"children":339},{},[340,342,347],{"type":46,"value":341},"One more that's easy to miss: ",{"type":41,"tag":83,"props":343,"children":344},{},[345],{"type":46,"value":346},"the user asked for your opinion or\ntake.",{"type":46,"value":348}," \"What do you think about X?\", \"what's your read?\" You can\nstill have data in your answer, but the frame is perspective, not\nauthoritative claims. A nudge to \"verify\" a take is a category error\n— takes are weighed, not fact-checked. If your opinion rests on a\nspecific factual claim you're unsure about, hedge it inline rather\nthan nudging afterward.",{"type":41,"tag":56,"props":350,"children":351},{},[352],{"type":46,"value":353},"Boundary calls: pure brainstorming usually doesn't need it — the user\nis the judge of the ideas. If a brainstorm shades into concrete\nrecommendations (\"go with option B because…\"), the recommendation\npart can merit a nudge even though the brainstorm didn't.",{"type":41,"tag":49,"props":355,"children":357},{"id":356},"writing-the-prompts",[358],{"type":46,"value":359},"Writing the prompts",{"type":41,"tag":56,"props":361,"children":362},{},[363],{"type":46,"value":364},"The nudge is two\nor three follow-up questions the user could send back to you, each one\nreferencing something concrete from the answer you just gave — a\nnumber, a named step, an assumption. Generic prompts (\"Can you verify\nthose facts?\") defeat the purpose; the value is in the specificity.",{"type":41,"tag":56,"props":366,"children":367},{},[368],{"type":46,"value":369},"Each prompt should do one of:",{"type":41,"tag":75,"props":371,"children":372},{},[373,390,406],{"type":41,"tag":79,"props":374,"children":375},{},[376,378,383,385],{"type":46,"value":377},"Point at a ",{"type":41,"tag":83,"props":379,"children":380},{},[381],{"type":46,"value":382},"fact or figure",{"type":46,"value":384}," in the answer and ask how to check it\nor how it compares to the user's own data. ",{"type":41,"tag":67,"props":386,"children":387},{},[388],{"type":46,"value":389},"\"How do these CPL\nestimates compare to benchmarks in my specific vertical?\"",{"type":41,"tag":79,"props":391,"children":392},{},[393,394,399,401],{"type":46,"value":377},{"type":41,"tag":83,"props":395,"children":396},{},[397],{"type":46,"value":398},"reasoning step or assumption",{"type":46,"value":400}," and invite the user to\nprobe it. ",{"type":41,"tag":67,"props":402,"children":403},{},[404],{"type":46,"value":405},"\"Walk me through why you prioritized webinars over content\n— what assumptions does that rest on?\"",{"type":41,"tag":79,"props":407,"children":408},{},[409,411,416,418],{"type":46,"value":410},"Point at ",{"type":41,"tag":83,"props":412,"children":413},{},[414],{"type":46,"value":415},"missing context",{"type":46,"value":417}," the answer had to guess at. ",{"type":41,"tag":67,"props":419,"children":420},{},[421],{"type":46,"value":422},"\"I didn't\nmention my state — does the security-deposit rule change by\njurisdiction?\"",{"type":41,"tag":56,"props":424,"children":425},{},[426],{"type":46,"value":427},"Phrase each one as something the user could ask you verbatim — first\nperson, conversational, question form. Two or three prompts, never\nmore. Keep each under ~120 characters so it reads at a glance.",{"type":41,"tag":49,"props":429,"children":431},{"id":430},"output-format",[432],{"type":46,"value":433},"Output format",{"type":41,"tag":56,"props":435,"children":436},{},[437],{"type":46,"value":438},"Always answer the question completely first. The nudge comes after, and\nit should be easy to skip.",{"type":41,"tag":56,"props":440,"children":441},{},[442],{"type":46,"value":443},"The nudge is plain text: append it after a blank line at the end of\nyour answer.",{"type":41,"tag":445,"props":446,"children":450},"pre",{"className":447,"code":449,"language":46},[448],"language-text","A few things worth a second look:\n- How do these CPL estimates compare to benchmarks in my specific vertical?\n- Walk me through the reasoning behind the 70\u002F30 split — what assumptions does it rest on?\n",[451],{"type":41,"tag":452,"props":453,"children":455},"code",{"__ignoreMap":454},"",[456],{"type":46,"value":449},{"type":41,"tag":56,"props":458,"children":459},{},[460],{"type":46,"value":461},"Use that exact lead-in line — \"A few things worth a second look:\" —\nfollowed by the prompts as plain bullets. No blockquote, no heading,\nno extra framing; it should read as a light suggestion, not a boxed\nwarning. Plain text only — no HTML, no headings, no emoji.",{"type":41,"tag":56,"props":463,"children":464},{},[465],{"type":46,"value":466},"Don't add anything after the nudge — no \"let me know\nif you'd like me to dig into any of these.\" The nudge is the closer.",{"items":468,"total":642},[469,483,502,516,528,547,553,564,585,605,619,634],{"slug":470,"name":470,"fn":471,"description":472,"org":473,"tags":474,"stars":23,"repoUrl":24,"updatedAt":482},"academy-guide","recommend Claude Academy resources","Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: \"how do I\", \"how can I\", \"getting started with\", \"what can Claude do\", \"teach me\", \"learn to use\"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[475,476,479],{"name":9,"slug":8,"type":16},{"name":477,"slug":478,"type":16},"Documentation","documentation",{"name":480,"slug":481,"type":16},"Education","education","2026-08-19T03:59:01.021254",{"slug":484,"name":484,"fn":485,"description":486,"org":487,"tags":488,"stars":23,"repoUrl":24,"updatedAt":501},"algorithmic-art","create algorithmic art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[489,492,495,498],{"name":490,"slug":491,"type":16},"Creative","creative",{"name":493,"slug":494,"type":16},"Design","design",{"name":496,"slug":497,"type":16},"Generative Art","generative-art",{"name":499,"slug":500,"type":16},"JavaScript","javascript","2026-04-06T17:56:15.455818",{"slug":503,"name":503,"fn":504,"description":505,"org":506,"tags":507,"stars":23,"repoUrl":24,"updatedAt":515},"brand-guidelines","apply Anthropic brand colors and typography","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[508,511,512],{"name":509,"slug":510,"type":16},"Branding","branding",{"name":493,"slug":494,"type":16},{"name":513,"slug":514,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":517,"name":517,"fn":518,"description":519,"org":520,"tags":521,"stars":23,"repoUrl":24,"updatedAt":527},"canvas-design","create posters and visual art as PNG or PDF","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[522,523,524],{"name":490,"slug":491,"type":16},{"name":493,"slug":494,"type":16},{"name":525,"slug":526,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":529,"name":529,"fn":530,"description":531,"org":532,"tags":533,"stars":23,"repoUrl":24,"updatedAt":546},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[534,537,538,541,543],{"name":535,"slug":536,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":539,"slug":540,"type":16},"Anthropic SDK","anthropic-sdk",{"name":542,"slug":529,"type":16},"Claude API",{"name":544,"slug":545,"type":16},"LLM","llm","2026-08-16T03:33:37.191126",{"slug":4,"name":4,"fn":5,"description":6,"org":548,"tags":549,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[550,551,552],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"slug":554,"name":554,"fn":555,"description":556,"org":557,"tags":558,"stars":23,"repoUrl":24,"updatedAt":563},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[559,560],{"name":477,"slug":478,"type":16},{"name":561,"slug":562,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":23,"repoUrl":24,"updatedAt":584},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[570,573,575,578,581],{"name":571,"slug":572,"type":16},"Documents","documents",{"name":574,"slug":565,"type":16},"DOCX",{"name":576,"slug":577,"type":16},"Office","office",{"name":579,"slug":580,"type":16},"Templates","templates",{"name":582,"slug":583,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":586,"name":586,"fn":587,"description":588,"org":589,"tags":590,"stars":23,"repoUrl":24,"updatedAt":604},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[591,592,595,598,601],{"name":493,"slug":494,"type":16},{"name":593,"slug":594,"type":16},"Frontend","frontend",{"name":596,"slug":597,"type":16},"React","react",{"name":599,"slug":600,"type":16},"Tailwind CSS","tailwind-css",{"name":602,"slug":603,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":606,"name":606,"fn":607,"description":608,"org":609,"tags":610,"stars":23,"repoUrl":24,"updatedAt":618},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[611,614,615],{"name":612,"slug":613,"type":16},"Communications","communications",{"name":579,"slug":580,"type":16},{"name":616,"slug":617,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":620,"name":620,"fn":621,"description":622,"org":623,"tags":624,"stars":23,"repoUrl":24,"updatedAt":633},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[625,626,629,630],{"name":535,"slug":536,"type":16},{"name":627,"slug":628,"type":16},"API Development","api-development",{"name":544,"slug":545,"type":16},{"name":631,"slug":632,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":526,"name":526,"fn":635,"description":636,"org":637,"tags":638,"stars":23,"repoUrl":24,"updatedAt":641},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[639,640],{"name":571,"slug":572,"type":16},{"name":525,"slug":526,"type":16},"2026-04-06T17:56:02.483316",493,{"items":644,"total":689},[645,651,658,664,670,678,684],{"slug":470,"name":470,"fn":471,"description":472,"org":646,"tags":647,"stars":23,"repoUrl":24,"updatedAt":482},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[648,649,650],{"name":9,"slug":8,"type":16},{"name":477,"slug":478,"type":16},{"name":480,"slug":481,"type":16},{"slug":484,"name":484,"fn":485,"description":486,"org":652,"tags":653,"stars":23,"repoUrl":24,"updatedAt":501},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[654,655,656,657],{"name":490,"slug":491,"type":16},{"name":493,"slug":494,"type":16},{"name":496,"slug":497,"type":16},{"name":499,"slug":500,"type":16},{"slug":503,"name":503,"fn":504,"description":505,"org":659,"tags":660,"stars":23,"repoUrl":24,"updatedAt":515},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[661,662,663],{"name":509,"slug":510,"type":16},{"name":493,"slug":494,"type":16},{"name":513,"slug":514,"type":16},{"slug":517,"name":517,"fn":518,"description":519,"org":665,"tags":666,"stars":23,"repoUrl":24,"updatedAt":527},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[667,668,669],{"name":490,"slug":491,"type":16},{"name":493,"slug":494,"type":16},{"name":525,"slug":526,"type":16},{"slug":529,"name":529,"fn":530,"description":531,"org":671,"tags":672,"stars":23,"repoUrl":24,"updatedAt":546},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[673,674,675,676,677],{"name":535,"slug":536,"type":16},{"name":9,"slug":8,"type":16},{"name":539,"slug":540,"type":16},{"name":542,"slug":529,"type":16},{"name":544,"slug":545,"type":16},{"slug":4,"name":4,"fn":5,"description":6,"org":679,"tags":680,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[681,682,683],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"slug":554,"name":554,"fn":555,"description":556,"org":685,"tags":686,"stars":23,"repoUrl":24,"updatedAt":563},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[687,688],{"name":477,"slug":478,"type":16},{"name":561,"slug":562,"type":16},19]