[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GHW350SSC1FPKXJVP7T92":3,"skill-same:01M79GHW350SSC1FPKXJVP7T92":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M79GHW350SSC1FPKXJVP7T92","ui-ux",null,"Apply UX psychology to design, critique, or redesign product screens and flows (onboarding, forms, signup walls, upgrades, pricing, conversion moments). Uses six evidence-backed principles: smart defaults, goal-gradient progress, reciprocity, IKEA\u002Fendowment ownership, loss aversion, and contrast\u002Fanchoring — with ethical anti-dark-pattern guardrails. Use when the user says \"UI\u002FUX\", \"UX psychology\", \"critique this screen\", \"improve conversion\", \"onboarding UX\", \"signup wall\", \"pricing screen\", \"upgrade modal\", \"design this flow\", \"\u002Fui-ux\", or wants before\u002Fafter product UI recommendations grounded in how people actually decide.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fui-ux\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ui-ux\ndescription: >\n  Apply UX psychology to design, critique, or redesign product screens and flows\n  (onboarding, forms, signup walls, upgrades, pricing, conversion moments). Uses six\n  evidence-backed principles: smart defaults, goal-gradient progress, reciprocity,\n  IKEA\u002Fendowment ownership, loss aversion, and contrast\u002Fanchoring — with ethical\n  anti-dark-pattern guardrails. Use when the user says \"UI\u002FUX\", \"UX psychology\",\n  \"critique this screen\", \"improve conversion\", \"onboarding UX\", \"signup wall\",\n  \"pricing screen\", \"upgrade modal\", \"design this flow\", \"\u002Fui-ux\", or wants\n  before\u002Fafter product UI recommendations grounded in how people actually decide.\nwhen-to-use: >\n  Product UI\u002FUX review or design work where decision psychology, conversion, or\n  retention matters more than pure visual polish. Screens, Figma\u002Fexport descriptions,\n  app flows, web forms, paywalls, checkouts.\nargument-hint: \"\u003Cscreen\u002Fflow description, screenshot path, or URL> [critique|redesign|checklist]\"\nmetadata:\n  short-description: \"UX psychology for screens: defaults, progress, reciprocity, ownership, loss, contrast\"\n  source: \"uxpeak — The UX Psychology Behind Apps People Can't Stop Using (https:\u002F\u002Fyoutu.be\u002F2TlIg3VokY8)\"\n  principles-ref: \"references\u002Fprinciples.md\"\n---\n\n# UI\u002FUX (Psychology-First Product Design)\n\n## Purpose\n\nHelp the user **design, critique, or redesign** product UI so the next action feels\nobvious, valuable, and worth completing. Visual polish alone is not the goal.\n**Decision psychology** is the goal.\n\nApps fail more often from ignoring how people decide than from ugly pixels.\n\n## Core Contract\n\n1. Ground every recommendation in one or more of the **six principles** below.\n2. Prefer concrete **before → after** screen changes over abstract advice.\n3. Prefer **one primary action** per moment of friction.\n4. Use psychology to **reduce confusion and build trust**, never to deceive.\n5. If the user only wants visual style (colors, type, glassmorphism), say so and\n   either narrow to psychology or defer — this skill owns **behavioral UX**, not\n   pure aesthetic art direction.\n\n## Six Principles (Quick Map)\n\n| # | Principle | User-job shift | Primary surfaces |\n|---|-----------|----------------|------------------|\n| 1 | **Smart defaults** | Fill from scratch → scan & adjust | Forms, filters, booking, settings |\n| 2 | **Goal-gradient (never start at 0%)** | Standing still → already in motion | Onboarding, checklists, profiles |\n| 3 | **Reciprocity (value before wall)** | Hostage → gift then invite | Results gates, signup walls, freemium |\n| 4 | **IKEA + endowment (invest first)** | Disposable form → something that's mine | Pre-auth setup, personalization |\n| 5 | **Loss aversion + status quo** | Pitch to ignore → cost of inaction | Upgrades, storage limits, renewals |\n| 6 | **Contrast \u002F anchoring** | Absolute price shock → relative fit | Pricing, add-ons, protection plans |\n\nFull before\u002Fafter rules, study anchors, and anti-patterns:\n`references\u002Fprinciples.md` (read when applying in depth or when the user wants sources).\n\n## Modes\n\nInfer mode from the request; default to **critique** if ambiguous.\n\n| Mode | When | Output emphasis |\n|------|------|-----------------|\n| **critique** | Existing screen\u002Fflow | Friction inventory + ranked principle hits |\n| **redesign** | User wants a better version | Concrete before→after changes + copy + layout notes |\n| **checklist** | Audit many screens \u002F ship readiness | Pass\u002Ffail per principle with one fix each |\n| **design-from-scratch** | New flow, no UI yet | Ordered flow + key screens using the six principles |\n\n## Workflow\n\n### 1. Load the target\n\n- Read attached screenshots\u002Fimages with `read_file` (multimodal).\n- Read local design files, HTML\u002FReact screens, or copy docs.\n- If only a verbal description is given, restate the assumed screen layout before advising.\n- Do **not** invent product data the user never provided; mark assumptions explicitly.\n\n### 2. Name the decision moment\n\nIn one sentence:\n\n> User is deciding whether to **[action]** after **[context]**, with **[stakes]**.\n\nExamples: \"continue onboarding\", \"create account\", \"upgrade now\", \"add protection plan\".\n\n### 3. Map friction to principles\n\nFor each blocking moment, ask:\n\n1. Are they forced to invent answers we already know? → **defaults**\n2. Does progress start at zero or feel endless? → **goal-gradient**\n3. Are we asking before giving anything real? → **reciprocity**\n4. Is there nothing yet that feels *theirs*? → **IKEA \u002F endowment**\n5. Is the CTA a gain pitch with a free \"maybe later\"? → **loss aversion**\n6. Is a cost shown without a controlled first number? → **contrast**\n\nSkip principles that do not apply. Do not force all six onto every screen.\n\n### 4. Propose changes (smallest that move behavior)\n\nFor each high-impact issue:\n\n- **Principle:** name it\n- **Current:** what the UI does now\n- **Change:** exact UI\u002Fcopy\u002Fstructure change\n- **Why it works:** one sentence in behavioral terms\n- **Risk \u002F ethics check:** any dark-pattern edge?\n\nPrefer **one decisive redesign** over ten micro-nits when conversion is the goal.\n\n### 5. Ethics gate (mandatory)\n\nReject or rewrite any recommendation that:\n\n- Fakes urgency, scarcity, progress, results, or social proof\n- Locks already-earned value behind a surprise wall after implying it was free\n- Uses loss framing for harm (fear, shame) without a truthful stake\n- Pre-selects paid plans, dark-pattern checkboxes, or hard-to-find dismiss controls\n- Mislabels secondary actions to guilt the user (\"No, I hate saving money\")\n\nAllowed: honest defaults, real partial value, real progress, real cost of inaction,\ntransparent relative pricing.\n\nIf the user's request is manipulative, refuse the dark version and offer an ethical\nequivalent that still uses the principle.\n\n## Output Shape\n\nUse this structure unless the user asks for a different format:\n\n```markdown\n# UI\u002FUX Review: \u003Cscreen or flow name>\n\n## Decision moment\n\u003Cone sentence>\n\n## What's working\n- ...\n\n## Friction → principle map\n| Moment | Principle | Severity (H\u002FM\u002FL) | Fix in one line |\n|--------|-----------|------------------|-----------------|\n\n## Recommended redesign (before → after)\n### 1. \u003Cchange title>\n- **Before:** ...\n- **After:** ...\n- **Principle:** ...\n- **Copy (if needed):** \"...\"\n\n## Primary CTA & secondary\n- Primary: ...\n- Secondary: ... (honest, not a guilt trap)\n\n## Ethics check\n- Pass \u002F concerns + mitigations\n\n## Optional next probe\n- One measurement or A\u002FB that would falsify whether the change helped\n```\n\nFor **checklist** mode, use a six-row table (principle \u002F status \u002F evidence \u002F fix).\n\nFor **design-from-scratch**, output:\n\n1. User job + success metric  \n2. Step sequence (ordered)  \n3. Key screens with principle tags  \n4. Empty states \u002F failure \u002F dismiss behavior  \n5. What *not* to add (complexity that reintroduces decision fatigue)\n\n## Working With Visuals\n\nWhen screenshots or mockups are present:\n\n1. Describe what you actually see (layout regions, hierarchy, CTAs) before advising.\n2. Point to specific UI regions (\"top progress bar\", \"blurred results panel\", \"footer dismiss\").\n3. Prefer overlay-style notes: *where* to change, not only *that* something should change.\n4. If generating a visual mock with image tools, keep labels legible and match the\n   product's existing visual language unless redesigning brand.\n\n## Related Skills\n\n- **playwright \u002F safari-browser** — observe live product behavior; this skill interprets UX intent.\n- **hyperframes \u002F imagegen** — produce motion or mock visuals *after* the behavioral design is set.\n- **user-story \u002F technical-task** — turn agreed UX changes into implementation work items.\n- **method-simplification** — compress overbuilt flows while preserving the conversion contract.\n\n## Success Criteria\n\n- Recommendations cite named principles, not vibes.\n- At least one concrete before→after per high-severity friction.\n- Ethics gate is explicit.\n- User can implement the top change without guessing copy or structure.\n- Unused principles are omitted, not shoehorned.\n\n## Invocation Examples\n\n- `\u002Fui-ux critique this onboarding screenshot`\n- `UI\u002FUX redesign our signup wall for the SEO analyzer`\n- `\u002Fui-ux checklist the upgrade modal in src\u002Fcomponents\u002FPaywall.tsx`\n- `Apply UX psychology to this checkout add-on pricing row`\n- `\u002Fskills ui-ux` then attach a flow description\n\n## Source Note\n\nPrinciples distilled from uxpeak's public lesson\n\"The UX Psychology Behind Apps People Can't Stop Using\"\n(https:\u002F\u002Fyoutu.be\u002F2TlIg3VokY8), expanded into an agent-operable workflow.\nTreat cited classic studies (jam choice, car-wash stamps, Kahneman loss aversion,\nCialdini reciprocity, IKEA effect, contrast effect) as **design heuristics with\nfamous anchors**, not as peer-reviewed claims re-verified in this skill file.\nWhen the user needs academic precision, flag uncertainty and offer to verify sources.\n","# UI\u002FUX (Psychology-First Product Design)\n\n## Purpose\n\nHelp the user **design, critique, or redesign** product UI so the next action feels\nobvious, valuable, and worth completing. Visual polish alone is not the goal.\n**Decision psychology** is the goal.\n\nApps fail more often from ignoring how people decide than from ugly pixels.\n\n## Core Contract\n\n1. Ground every recommendation in one or more of the **six principles** below.\n2. Prefer concrete **before → after** screen changes over abstract advice.\n3. Prefer **one primary action** per moment of friction.\n4. Use psychology to **reduce confusion and build trust**, never to deceive.\n5. If the user only wants visual style (colors, type, glassmorphism), say so and\n   either narrow to psychology or defer — this skill owns **behavioral UX**, not\n   pure aesthetic art direction.\n\n## Six Principles (Quick Map)\n\n| # | Principle | User-job shift | Primary surfaces |\n|---|-----------|----------------|------------------|\n| 1 | **Smart defaults** | Fill from scratch → scan & adjust | Forms, filters, booking, settings |\n| 2 | **Goal-gradient (never start at 0%)** | Standing still → already in motion | Onboarding, checklists, profiles |\n| 3 | **Reciprocity (value before wall)** | Hostage → gift then invite | Results gates, signup walls, freemium |\n| 4 | **IKEA + endowment (invest first)** | Disposable form → something that's mine | Pre-auth setup, personalization |\n| 5 | **Loss aversion + status quo** | Pitch to ignore → cost of inaction | Upgrades, storage limits, renewals |\n| 6 | **Contrast \u002F anchoring** | Absolute price shock → relative fit | Pricing, add-ons, protection plans |\n\nFull before\u002Fafter rules, study anchors, and anti-patterns:\n`references\u002Fprinciples.md` (read when applying in depth or when the user wants sources).\n\n## Modes\n\nInfer mode from the request; default to **critique** if ambiguous.\n\n| Mode | When | Output emphasis |\n|------|------|-----------------|\n| **critique** | Existing screen\u002Fflow | Friction inventory + ranked principle hits |\n| **redesign** | User wants a better version | Concrete before→after changes + copy + layout notes |\n| **checklist** | Audit many screens \u002F ship readiness | Pass\u002Ffail per principle with one fix each |\n| **design-from-scratch** | New flow, no UI yet | Ordered flow + key screens using the six principles |\n\n## Workflow\n\n### 1. Load the target\n\n- Read attached screenshots\u002Fimages with `read_file` (multimodal).\n- Read local design files, HTML\u002FReact screens, or copy docs.\n- If only a verbal description is given, restate the assumed screen layout before advising.\n- Do **not** invent product data the user never provided; mark assumptions explicitly.\n\n### 2. Name the decision moment\n\nIn one sentence:\n\n> User is deciding whether to **[action]** after **[context]**, with **[stakes]**.\n\nExamples: \"continue onboarding\", \"create account\", \"upgrade now\", \"add protection plan\".\n\n### 3. Map friction to principles\n\nFor each blocking moment, ask:\n\n1. Are they forced to invent answers we already know? → **defaults**\n2. Does progress start at zero or feel endless? → **goal-gradient**\n3. Are we asking before giving anything real? → **reciprocity**\n4. Is there nothing yet that feels *theirs*? → **IKEA \u002F endowment**\n5. Is the CTA a gain pitch with a free \"maybe later\"? → **loss aversion**\n6. Is a cost shown without a controlled first number? → **contrast**\n\nSkip principles that do not apply. Do not force all six onto every screen.\n\n### 4. Propose changes (smallest that move behavior)\n\nFor each high-impact issue:\n\n- **Principle:** name it\n- **Current:** what the UI does now\n- **Change:** exact UI\u002Fcopy\u002Fstructure change\n- **Why it works:** one sentence in behavioral terms\n- **Risk \u002F ethics check:** any dark-pattern edge?\n\nPrefer **one decisive redesign** over ten micro-nits when conversion is the goal.\n\n### 5. Ethics gate (mandatory)\n\nReject or rewrite any recommendation that:\n\n- Fakes urgency, scarcity, progress, results, or social proof\n- Locks already-earned value behind a surprise wall after implying it was free\n- Uses loss framing for harm (fear, shame) without a truthful stake\n- Pre-selects paid plans, dark-pattern checkboxes, or hard-to-find dismiss controls\n- Mislabels secondary actions to guilt the user (\"No, I hate saving money\")\n\nAllowed: honest defaults, real partial value, real progress, real cost of inaction,\ntransparent relative pricing.\n\nIf the user's request is manipulative, refuse the dark version and offer an ethical\nequivalent that still uses the principle.\n\n## Output Shape\n\nUse this structure unless the user asks for a different format:\n\n```markdown\n# UI\u002FUX Review: \u003Cscreen or flow name>\n\n## Decision moment\n\u003Cone sentence>\n\n## What's working\n- ...\n\n## Friction → principle map\n| Moment | Principle | Severity (H\u002FM\u002FL) | Fix in one line |\n|--------|-----------|------------------|-----------------|\n\n## Recommended redesign (before → after)\n### 1. \u003Cchange title>\n- **Before:** ...\n- **After:** ...\n- **Principle:** ...\n- **Copy (if needed):** \"...\"\n\n## Primary CTA & secondary\n- Primary: ...\n- Secondary: ... (honest, not a guilt trap)\n\n## Ethics check\n- Pass \u002F concerns + mitigations\n\n## Optional next probe\n- One measurement or A\u002FB that would falsify whether the change helped\n```\n\nFor **checklist** mode, use a six-row table (principle \u002F status \u002F evidence \u002F fix).\n\nFor **design-from-scratch**, output:\n\n1. User job + success metric  \n2. Step sequence (ordered)  \n3. Key screens with principle tags  \n4. Empty states \u002F failure \u002F dismiss behavior  \n5. What *not* to add (complexity that reintroduces decision fatigue)\n\n## Working With Visuals\n\nWhen screenshots or mockups are present:\n\n1. Describe what you actually see (layout regions, hierarchy, CTAs) before advising.\n2. Point to specific UI regions (\"top progress bar\", \"blurred results panel\", \"footer dismiss\").\n3. Prefer overlay-style notes: *where* to change, not only *that* something should change.\n4. If generating a visual mock with image tools, keep labels legible and match the\n   product's existing visual language unless redesigning brand.\n\n## Related Skills\n\n- **playwright \u002F safari-browser** — observe live product behavior; this skill interprets UX intent.\n- **hyperframes \u002F imagegen** — produce motion or mock visuals *after* the behavioral design is set.\n- **user-story \u002F technical-task** — turn agreed UX changes into implementation work items.\n- **method-simplification** — compress overbuilt flows while preserving the conversion contract.\n\n## Success Criteria\n\n- Recommendations cite named principles, not vibes.\n- At least one concrete before→after per high-severity friction.\n- Ethics gate is explicit.\n- User can implement the top change without guessing copy or structure.\n- Unused principles are omitted, not shoehorned.\n\n## Invocation Examples\n\n- `\u002Fui-ux critique this onboarding screenshot`\n- `UI\u002FUX redesign our signup wall for the SEO analyzer`\n- `\u002Fui-ux checklist the upgrade modal in src\u002Fcomponents\u002FPaywall.tsx`\n- `Apply UX psychology to this checkout add-on pricing row`\n- `\u002Fskills ui-ux` then attach a flow description\n\n## Source Note\n\nPrinciples distilled from uxpeak's public lesson\n\"The UX Psychology Behind Apps People Can't Stop Using\"\n(https:\u002F\u002Fyoutu.be\u002F2TlIg3VokY8), expanded into an agent-operable workflow.\nTreat cited classic studies (jam choice, car-wash stamps, Kahneman loss aversion,\nCialdini reciprocity, IKEA effect, contrast effect) as **design heuristics with\nfamous anchors**, not as peer-reviewed claims re-verified in this skill file.\nWhen the user needs academic precision, flag uncertainty and offer to verify sources.\n",{"name":5,"metadata":24,"description":28,"when-to-use":29,"argument-hint":30},{"source":25,"principles-ref":26,"short-description":27},"uxpeak — The UX Psychology Behind Apps People Can't Stop Using (https:\u002F\u002Fyoutu.be\u002F2TlIg3VokY8)","references\u002Fprinciples.md","UX psychology for screens: defaults, progress, reciprocity, ownership, loss, contrast","Apply UX psychology to design, critique, or redesign product screens and flows (onboarding, forms, signup walls, upgrades, pricing, conversion moments). Uses six evidence-backed principles: smart defaults, goal-gradient progress, reciprocity, IKEA\u002Fendowment ownership, loss aversion, and contrast\u002Fanchoring — with ethical anti-dark-pattern guardrails. Use when the user says \"UI\u002FUX\", \"UX psychology\", \"critique this screen\", \"improve conversion\", \"onboarding UX\", \"signup wall\", \"pricing screen\", \"upgrade modal\", \"design this flow\", \"\u002Fui-ux\", or wants before\u002Fafter product UI recommendations grounded in how people actually decide.\n","Product UI\u002FUX review or design work where decision psychology, conversion, or retention matters more than pure visual polish. Screens, Figma\u002Fexport descriptions, app flows, web forms, paywalls, checkouts.\n","\u003Cscreen\u002Fflow description, screenshot path, or URL> [critique|redesign|checklist]","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fui-ux","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add zfifteen\u002Fskills-catalog --skill ui-ux",{"tool":44,"command":45},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill ui-ux",{"tool":47,"command":48},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill ui-ux","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fui-ux\u002FSKILL.md",true,[52],{"path":26,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"REFERENCE","参考文档",8554,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fui-ux\u002Freferences\u002Fprinciples.md",[58,65,72,79,88,95],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]