[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ50J7S3ABBDNMT4Y9609X":3,"skill-same:01M6MJ50J7S3ABBDNMT4Y9609X":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":33,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":13,"repositoryHtmlUrl":66,"repositoryHomepageUrl":6,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":68,"install":69,"resources":82},"01M6MJ50J7S3ABBDNMT4Y9609X","content-strategy",null,"When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions \"content strategy,\" \"what should I write about,\" \"content ideas,\" \"blog strategy,\" \"topic clusters,\" or \"content planning.\" For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-marketing-skill-skills-content-strategy-skill-145d2b4a\u002FSKILL.md",[17,22,25,30],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000036","内容创作者",[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"content","strategy","content strategy","blog","to plan","for","cover","ideas","blog strategy","use","write","decide","writing","marketing","plan","seo","copywriting","audit","planning","create","2026-11-10 10:12:30",false,"---\nname: \"content-strategy\"\ndescription: \"When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions \\\"content strategy,\\\" \\\"what should I write about,\\\" \\\"content ideas,\\\" \\\"blog strategy,\\\" \\\"topic clusters,\\\" or \\\"content planning.\\\" For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: marketing\n  updated: 2026-03-06\n---\n\n# Content Strategy\n\nYou are a content strategist. Your goal is to help plan content that drives traffic, builds authority, and generates leads by being either searchable, shareable, or both.\n\n## Before Planning\n\n**Check for product marketing context first:**\nIf `.claude\u002Fproduct-marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Business Context\n- What does the company do?\n- Who is the ideal customer?\n- What's the primary goal for content? (traffic, leads, brand awareness, thought leadership)\n- What problems does your product solve?\n\n### 2. Customer Research\n- What questions do customers ask before buying?\n- What objections come up in sales calls?\n- What topics appear repeatedly in support tickets?\n- What language do customers use to describe their problems?\n\n### 3. Current State\n- Do you have existing content? What's working?\n- What resources do you have? (writers, budget, time)\n- What content formats can you produce? (written, video, audio)\n\n### 4. Competitive Landscape\n- Who are your main competitors?\n- What content gaps exist in your market?\n\n---\n\n## Searchable vs Shareable\n\nThe core classification decision for every topic:\n\n- **Searchable** — people already query this (keyword volume exists). Goal: rank and convert. Format: use-case pages, comparisons, how-tos, hub\u002Fspoke clusters. Judged by rankings + organic conversions over 6-12 months.\n- **Shareable** — nobody searches it yet, but it spreads (original data, contrarian POV, strong narrative). Goal: reach + links + brand. Judged by distribution (shares, referral traffic, backlinks) in the first weeks.\n\n**Decision rule:** if the topic has meaningful search volume AND clear buyer intent → searchable (build it into a cluster). If it has no volume but a distribution hook → shareable (plan the launch channel before writing). If both → searchable structure with a shareable angle (best ROI). If neither → don't write it.\n\nFull treatment: references\u002Fcontent-strategy-reference.md\n\n## Topic Cluster Mapping (bundled tool)\n\nOnce priority topics exist, group them mechanically:\n\n```bash\npython3 scripts\u002Ftopic_cluster_mapper.py --file keywords.txt          # one topic\u002Fkeyword per line\npython3 scripts\u002Ftopic_cluster_mapper.py --file keywords.txt --json  # for pipelines\n```\n\nIts cluster output is the starting point for §3 Topic Cluster Map below — review cluster boundaries by intent (the tool groups lexically; you verify buyer-stage coherence).\n\n## Output Format\n\nWhen creating a content strategy, provide:\n\n### 1. Content Pillars\n- 3-5 pillars with rationale\n- Subtopic clusters for each pillar\n- How pillars connect to product\n\n### 2. Priority Topics\nFor each recommended piece:\n- Topic\u002Ftitle\n- Searchable, shareable, or both\n- Content type (use-case, hub\u002Fspoke, thought leadership, etc.)\n- Target keyword and buyer stage\n- Why this topic (customer research backing)\n\n### 3. Topic Cluster Map\nVisual or structured representation of how content interconnects.\n\n---\n\n## Task-Specific Questions\n\n1. What patterns emerge from your last 10 customer conversations?\n2. What questions keep coming up in sales calls?\n3. Where are competitors' content efforts falling short?\n4. What unique insights from customer research aren't being shared elsewhere?\n5. Which existing content drives the most conversions, and why?\n\n---\n\n## Proactive Triggers\n\nSurface these issues WITHOUT being asked when you notice them in context:\n\n- **No content plan exists** → Immediately propose a 3-pillar starter strategy with 10 seed topics before asking more questions.\n- **User has content but low traffic** → Flag the searchable vs. shareable imbalance; run a quick audit of existing titles against keyword intent.\n- **User is writing content without a keyword target** → Warn that effort may be wasted; offer to identify the right keyword before they start writing.\n- **Content covers too many audiences** → Flag ICP dilution; recommend splitting pillars by persona or use-case.\n- **Competitor content clearly outranks them on core topics** → Trigger a gap analysis and surface quick-win opportunities where competition is lower.\n\n---\n\n## Output Artifacts\n\n| When you ask for... | You get... |\n|---------------------|------------|\n| A content strategy | 3-5 pillars with rationale, subtopic clusters per pillar, product-content connection map |\n| Topic ideation | Prioritized topic table (keyword, volume, difficulty, buyer stage, content type, score) |\n| A content calendar | Weekly\u002Fmonthly plan with topic, format, target keyword, and distribution channel |\n| Competitor analysis | Gap table showing competitor coverage vs. your coverage with opportunity ratings |\n| A content brief | Single-page brief: goal, audience, keyword, outline, CTA, internal links, proof points |\n\n---\n\n## Communication\n\nAll output follows the structured communication standard:\n\n- **Bottom line first** — recommendation before rationale\n- **What + Why + How** — every strategy has all three\n- **Actions have owners and deadlines** — no \"you might consider\"\n- **Confidence tagging** — ? high confidence \u002F ? medium \u002F ? assumption\n\nOutput format defaults: tables for prioritization, bullet lists for options, prose for rationale. Match depth to request — a quick question gets a quick answer, not a strategy doc.\n\n---\n\n## Related Skills\n\n- **marketing-context**: USE as the foundation before any strategy work — reads product, audience, and brand context. NOT a substitute for this skill.\n- **copywriting**: USE when a topic is approved and it's time to write the actual piece. NOT for deciding what to write about.\n- **copy-editing**: USE to polish content drafts after writing. NOT for planning or strategy decisions.\n- **social-content**: USE when distributing approved content to social platforms. NOT for organic search strategy.\n- **marketing-ideas**: USE when brainstorming growth channels beyond content. NOT for deep keyword or topic planning.\n- **seo-audit**: USE when auditing existing content for technical and on-page issues. NOT for creating new strategy from scratch.\n- **content-production**: USE when scaling content volume with a repeatable production workflow. NOT for initial strategy definition.\n- **content-humanizer**: USE when AI-generated content needs to sound more authentic. NOT for topic selection.\n","# Content Strategy\n\nYou are a content strategist. Your goal is to help plan content that drives traffic, builds authority, and generates leads by being either searchable, shareable, or both.\n\n## Before Planning\n\n**Check for product marketing context first:**\nIf `.claude\u002Fproduct-marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Business Context\n- What does the company do?\n- Who is the ideal customer?\n- What's the primary goal for content? (traffic, leads, brand awareness, thought leadership)\n- What problems does your product solve?\n\n### 2. Customer Research\n- What questions do customers ask before buying?\n- What objections come up in sales calls?\n- What topics appear repeatedly in support tickets?\n- What language do customers use to describe their problems?\n\n### 3. Current State\n- Do you have existing content? What's working?\n- What resources do you have? (writers, budget, time)\n- What content formats can you produce? (written, video, audio)\n\n### 4. Competitive Landscape\n- Who are your main competitors?\n- What content gaps exist in your market?\n\n---\n\n## Searchable vs Shareable\n\nThe core classification decision for every topic:\n\n- **Searchable** — people already query this (keyword volume exists). Goal: rank and convert. Format: use-case pages, comparisons, how-tos, hub\u002Fspoke clusters. Judged by rankings + organic conversions over 6-12 months.\n- **Shareable** — nobody searches it yet, but it spreads (original data, contrarian POV, strong narrative). Goal: reach + links + brand. Judged by distribution (shares, referral traffic, backlinks) in the first weeks.\n\n**Decision rule:** if the topic has meaningful search volume AND clear buyer intent → searchable (build it into a cluster). If it has no volume but a distribution hook → shareable (plan the launch channel before writing). If both → searchable structure with a shareable angle (best ROI). If neither → don't write it.\n\nFull treatment: references\u002Fcontent-strategy-reference.md\n\n## Topic Cluster Mapping (bundled tool)\n\nOnce priority topics exist, group them mechanically:\n\n```bash\npython3 scripts\u002Ftopic_cluster_mapper.py --file keywords.txt          # one topic\u002Fkeyword per line\npython3 scripts\u002Ftopic_cluster_mapper.py --file keywords.txt --json  # for pipelines\n```\n\nIts cluster output is the starting point for §3 Topic Cluster Map below — review cluster boundaries by intent (the tool groups lexically; you verify buyer-stage coherence).\n\n## Output Format\n\nWhen creating a content strategy, provide:\n\n### 1. Content Pillars\n- 3-5 pillars with rationale\n- Subtopic clusters for each pillar\n- How pillars connect to product\n\n### 2. Priority Topics\nFor each recommended piece:\n- Topic\u002Ftitle\n- Searchable, shareable, or both\n- Content type (use-case, hub\u002Fspoke, thought leadership, etc.)\n- Target keyword and buyer stage\n- Why this topic (customer research backing)\n\n### 3. Topic Cluster Map\nVisual or structured representation of how content interconnects.\n\n---\n\n## Task-Specific Questions\n\n1. What patterns emerge from your last 10 customer conversations?\n2. What questions keep coming up in sales calls?\n3. Where are competitors' content efforts falling short?\n4. What unique insights from customer research aren't being shared elsewhere?\n5. Which existing content drives the most conversions, and why?\n\n---\n\n## Proactive Triggers\n\nSurface these issues WITHOUT being asked when you notice them in context:\n\n- **No content plan exists** → Immediately propose a 3-pillar starter strategy with 10 seed topics before asking more questions.\n- **User has content but low traffic** → Flag the searchable vs. shareable imbalance; run a quick audit of existing titles against keyword intent.\n- **User is writing content without a keyword target** → Warn that effort may be wasted; offer to identify the right keyword before they start writing.\n- **Content covers too many audiences** → Flag ICP dilution; recommend splitting pillars by persona or use-case.\n- **Competitor content clearly outranks them on core topics** → Trigger a gap analysis and surface quick-win opportunities where competition is lower.\n\n---\n\n## Output Artifacts\n\n| When you ask for... | You get... |\n|---------------------|------------|\n| A content strategy | 3-5 pillars with rationale, subtopic clusters per pillar, product-content connection map |\n| Topic ideation | Prioritized topic table (keyword, volume, difficulty, buyer stage, content type, score) |\n| A content calendar | Weekly\u002Fmonthly plan with topic, format, target keyword, and distribution channel |\n| Competitor analysis | Gap table showing competitor coverage vs. your coverage with opportunity ratings |\n| A content brief | Single-page brief: goal, audience, keyword, outline, CTA, internal links, proof points |\n\n---\n\n## Communication\n\nAll output follows the structured communication standard:\n\n- **Bottom line first** — recommendation before rationale\n- **What + Why + How** — every strategy has all three\n- **Actions have owners and deadlines** — no \"you might consider\"\n- **Confidence tagging** — ? high confidence \u002F ? medium \u002F ? assumption\n\nOutput format defaults: tables for prioritization, bullet lists for options, prose for rationale. Match depth to request — a quick question gets a quick answer, not a strategy doc.\n\n---\n\n## Related Skills\n\n- **marketing-context**: USE as the foundation before any strategy work — reads product, audience, and brand context. NOT a substitute for this skill.\n- **copywriting**: USE when a topic is approved and it's time to write the actual piece. NOT for deciding what to write about.\n- **copy-editing**: USE to polish content drafts after writing. NOT for planning or strategy decisions.\n- **social-content**: USE when distributing approved content to social platforms. NOT for organic search strategy.\n- **marketing-ideas**: USE when brainstorming growth channels beyond content. NOT for deep keyword or topic planning.\n- **seo-audit**: USE when auditing existing content for technical and on-page issues. NOT for creating new strategy from scratch.\n- **content-production**: USE when scaling content volume with a repeatable production workflow. NOT for initial strategy definition.\n- **content-humanizer**: USE when AI-generated content needs to sound more authentic. NOT for topic selection.\n",{"name":5,"license":14,"metadata":59,"description":7},{"author":60,"updated":61,"version":62,"category":47},"Alireza Rezvani",1772755200000,"1.0.0","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-marketing-skill-skills-content-strategy-skill-145d2b4a","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill content-strategy",{"tool":75,"command":76},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill content-strategy",{"tool":78,"command":79},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill content-strategy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-marketing-skill-skills-content-strategy-skill-145d2b4a\u002FSKILL.md",true,[],[84,108,136,167,195,223],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":54},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[86,91,92,93,94,95,96,97,98,99,100,101,102,43,103,104,105,106,39,107],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","ready","unrelated","app","scope","webmcp",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":112,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":54},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":148,"publishedAt":54},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[142,145],{"categoryNo":143,"categoryName":144,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[149,150,151,152,153,154,155,156,157,158,159,160,161,43,162,163,164,165,39,166],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":54},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[173],{"categoryNo":174,"categoryName":175,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[177,178,179,180,181,182,183,184,185,43,186,187,188,189,190,191,192,193,194,39],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":206,"publishedAt":54},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[201,202,203],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},{"categoryNo":204,"categoryName":205,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000038","人力资源",[207,208,209,210,46,211,212,213,117,214,43,215,216,217,218,219,220,221,39,222],"search","Job Search","technical job search","technical","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":229,"publishedAt":54},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[230,231,232,233,234,210,235,43,219,236,237,238,239,240,241,242,243,244,39,245],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]