[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MZF613CKP2A20EMY07B14C":3,"skill-same:01M6MZF613CKP2A20EMY07B14C":72},{"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":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":13,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6MZF613CKP2A20EMY07B14C","canvas",null,"Activate for: business model canvas, BMC, business model, value proposition, customer segments, channels, customer relationships, revenue streams, key resources, key activities, key partnerships, cost structure, canvas build, canvas stress test, alternative business model, monetisation, pricing model, revenue model, how does the business make money, business design, Osterwalder. NOT for: unit economics or financial modelling (use financials), competitive analysis (use market), pitch deck (use pitch).","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-06-agentfactory-business-plugins-main-innovation-skills-canvas-skill-68f2e716\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"pricing model","design","cost structure","proposition","streams","bmc","osterwalder","economics","unit","revenue","pitch","resources","revenue model","structure","activate","model","how","analysis","customer","2026-11-10 10:12:30",false,"---\nname: canvas\ndescription: >\n  Activate for: business model canvas, BMC, business model, value proposition,\n  customer segments, channels, customer relationships, revenue streams, key\n  resources, key activities, key partnerships, cost structure, canvas build,\n  canvas stress test, alternative business model, monetisation, pricing model,\n  revenue model, how does the business make money, business design, Osterwalder.\n  NOT for: unit economics or financial modelling (use financials),\n  competitive analysis (use market), pitch deck (use pitch).\nlicense: Apache-2.0\nmetadata:\n  author: Panaversity\n  version: \"1.0\"\n  plugin-commands: \"\u002Fcanvas\"\n---\n\n## CONTEXT LOADING\n\nBefore executing, check for `innov.local.md` in the working directory.\nIf found, extract:\n\n- venture: name, stage, type, problem_statement, target_customer\n- business_model_canvas: current version with all blocks and evidence quality\n- customer_profiles: personas, pains, gains, WTP\n- key_assumptions: business model assumptions\n\nIf `innov.local.md` is not found:\nContinue with conversation context. After first substantive output, prompt:\n\"I'm working without your venture context. Run Exercise 8 from Chapter 40\nto build innov.local.md -- it will make every subsequent output specific\nto your venture rather than generic.\"\n\n## STAGE-AWARE CALIBRATION\n\nCheck venture.stage and calibrate:\n\n- IDEA: Warning -- \"Building a canvas at the IDEA stage is premature. Most blocks will be ASSUMED with no evidence. Consider running \u002Fdiscovery first to get real customer data before designing a business model.\"\n- DISCOVERY: A canvas is useful here -- you can start mapping hypotheses as you learn from customers.\n- VALIDATION: This is your focus stage. The canvas should reflect what you are testing and learning.\n- MVP: This is your focus stage. The canvas should be updated with pilot data and evidence.\n- GROWTH: The canvas should be largely validated. Focus on optimising blocks, not hypothesising.\n\n## DLA PROGRESSION CHECK\n\nIf no customer_profiles or discovery data exist in innov.local.md:\n\"You are building a business model canvas without customer discovery data.\nEvery block will be hypothetical. Consider running \u002Fdiscovery first --\na canvas grounded in customer evidence is vastly more useful than one\nbuilt from assumptions alone.\"\n\n## BUSINESS MODEL CANVAS WORKFLOW\n\n### Task Types\n\nTYPE 1: CANVAS BUILD (first draft)\nInput: Venture context from innov.local.md + any additional context\nOutput: All 9 blocks with hypotheses, evidence quality, biggest risk, open question\n\nTYPE 2: CANVAS STRESS TEST\nInput: Existing canvas\nOutput: One adversarial question per block + strongest counter-argument\n\nTYPE 3: ALTERNATIVE MODELS\nInput: Current canvas\nOutput: 3 alternative business model configurations with trade-off analysis\n\nTYPE 4: CANVAS UPDATE (post-learning)\nInput: Previous canvas version + new validation data\nOutput: Updated canvas with specific changes highlighted + version increment\n\nTYPE 5: CANVAS HEALTH SUMMARY\nInput: Current canvas\nOutput: Which blocks are validated vs. hypothetical; critical gaps; priority actions\n\n### Canvas Output Structure\n\n```\nBUSINESS MODEL CANVAS -- [Venture Name]\nVersion: [N.N] (post-[stage]) | Date: [Date]\n================================================================\n\n1. CUSTOMER SEGMENTS\n   Primary:   [Who specifically -- not \"SMEs\"; name the role and context]\n   Secondary: [If applicable; note if different product\u002Fprice needed]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [Biggest risk in this block]\n   Open Q:    [The one thing we still need to learn about this segment]\n\n2. VALUE PROPOSITIONS\n   Primary:   [The core promise -- specific, differentiated, outcome-focused]\n   Secondary: [Supporting value]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [What could undermine this value proposition]\n   Open Q:    [What the customer might not believe without proof]\n\n3. CHANNELS\n   Awareness:  [How customers discover you]\n   Evaluation: [How customers decide to buy]\n   Purchase:   [How they buy]\n   Delivery:   [How they receive value]\n   After-sale: [How you retain and grow them]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [Scalability; CAC at volume]\n   Open Q:    [Which channel needs validation first]\n\n4. CUSTOMER RELATIONSHIPS\n   Current:   [How you manage the relationship today]\n   Target:    [How it scales]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [What breaks when you can no longer do high-touch]\n   Open Q:    [Minimum viable onboarding that produces adoption]\n\n5. REVENUE STREAMS\n   Primary:   [Pricing model + price point]\n   Secondary: [If applicable]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [The pricing assumption that has been least tested]\n   Open Q:    [What pricing behaviour validates willingness to pay?]\n\n6. KEY RESOURCES\n   Critical:  [The resource without which value cannot be delivered]\n   Important: [Resources that matter but can be substituted]\n   Risk:      [Most fragile resource; what if it disappears?]\n   Open Q:    [Which resource must be built\u002Fowned vs. rented\u002Faccessed?]\n\n7. KEY ACTIVITIES\n   Core:      [The activity most central to value creation]\n   Growth:    [The activity most central to customer acquisition]\n   Risk:      [What the team cannot currently do; capability gap]\n   Open Q:    [What activity, if outsourced, would be dangerous?]\n\n8. KEY PARTNERSHIPS\n   Critical:  [Partner without whom value cannot be delivered]\n   Strategic: [Partner who provides competitive advantage]\n   Risk:      [Single-point-of-failure partnerships]\n   Open Q:    [Which partnership must be formalised before scaling?]\n\n9. COST STRUCTURE\n   Fixed:     [Monthly fixed costs -- list with amounts]\n   Variable:  [Per-customer or per-transaction costs]\n   Unit cost: [Total cost to serve one customer per month]\n   Margin:    [Revenue - unit cost = contribution margin]\n   Evidence:  [ESTIMATED \u002F MEASURED]\n   Open Q:    [Which cost assumption changes most at 10x scale?]\n\nCANVAS HEALTH SUMMARY:\n  Validated blocks:           [List]\n  Partially validated:        [List]\n  Hypothetical (build risk):  [List]\n  Critical gaps:              [Blocks where evidence is weakest vs. risk is highest]\n================================================================\n```\n\n### Value Proposition Quality Standard\n\nA strong Value Proposition has:\n\n- A specific outcome for a specific customer (not a feature list)\n- A differentiated claim (why this, not the alternative)\n- Evidence it is valued (customer said it or paid for it)\n- A reason the customer cannot easily get this elsewhere\n\n### Alternative Business Model Patterns\n\nWhen generating alternatives, explore these structural variations:\n\n- Subscription vs. usage-based vs. transaction fee\n- Selling to enterprise vs. selling to individual professionals\n- Direct vs. marketplace vs. platform\n- Free + premium vs. paid only vs. free forever\n- Product-led growth vs. sales-led growth\n- Build vs. partner vs. white-label\n\n## FINANCIAL REASONING STANDARD\n\nFor Revenue Streams and Cost Structure blocks:\n\n- Unit economics first: ensure the unit economics work before projecting revenue\n- If LTV:CAC \u003C 3, flag as a serious concern in the canvas\n- Churn is the most dangerous assumption: if churn is ASSUMED, flag it\n- Always show contribution margin calculation in Cost Structure\n\n## ASSUMPTION TRACKING\n\nAfter any canvas output:\n\n- Surface which blocks have changed and what evidence supports the change\n- Identify the most critical untested assumption across all 9 blocks\n- Propose innov.local.md updates for any changed blocks\n- Always distinguish between ASSUMED, ANECDOTAL, and VALIDATED evidence\n\n## NEVER DO THESE\n\n- NEVER leave a canvas block empty -- if you don't know: write your assumption\n  and mark it ASSUMED; an empty block is a hidden risk\n- NEVER mark a block VALIDATED without customer payment or sustained usage data\n- NEVER produce a canvas without a health summary showing which blocks\n  are validated vs. hypothetical -- this is what tells you where to focus\n- NEVER accept \"We'll figure out monetisation later\" -- Revenue Streams and\n  Cost Structure must be at least hypothesised from Day 1\n\nALL OUTPUTS REQUIRE REVIEW BY A QUALIFIED PROFESSIONAL BEFORE USE IN BUSINESS DECISIONS.\n","## CONTEXT LOADING\n\nBefore executing, check for `innov.local.md` in the working directory.\nIf found, extract:\n\n- venture: name, stage, type, problem_statement, target_customer\n- business_model_canvas: current version with all blocks and evidence quality\n- customer_profiles: personas, pains, gains, WTP\n- key_assumptions: business model assumptions\n\nIf `innov.local.md` is not found:\nContinue with conversation context. After first substantive output, prompt:\n\"I'm working without your venture context. Run Exercise 8 from Chapter 40\nto build innov.local.md -- it will make every subsequent output specific\nto your venture rather than generic.\"\n\n## STAGE-AWARE CALIBRATION\n\nCheck venture.stage and calibrate:\n\n- IDEA: Warning -- \"Building a canvas at the IDEA stage is premature. Most blocks will be ASSUMED with no evidence. Consider running \u002Fdiscovery first to get real customer data before designing a business model.\"\n- DISCOVERY: A canvas is useful here -- you can start mapping hypotheses as you learn from customers.\n- VALIDATION: This is your focus stage. The canvas should reflect what you are testing and learning.\n- MVP: This is your focus stage. The canvas should be updated with pilot data and evidence.\n- GROWTH: The canvas should be largely validated. Focus on optimising blocks, not hypothesising.\n\n## DLA PROGRESSION CHECK\n\nIf no customer_profiles or discovery data exist in innov.local.md:\n\"You are building a business model canvas without customer discovery data.\nEvery block will be hypothetical. Consider running \u002Fdiscovery first --\na canvas grounded in customer evidence is vastly more useful than one\nbuilt from assumptions alone.\"\n\n## BUSINESS MODEL CANVAS WORKFLOW\n\n### Task Types\n\nTYPE 1: CANVAS BUILD (first draft)\nInput: Venture context from innov.local.md + any additional context\nOutput: All 9 blocks with hypotheses, evidence quality, biggest risk, open question\n\nTYPE 2: CANVAS STRESS TEST\nInput: Existing canvas\nOutput: One adversarial question per block + strongest counter-argument\n\nTYPE 3: ALTERNATIVE MODELS\nInput: Current canvas\nOutput: 3 alternative business model configurations with trade-off analysis\n\nTYPE 4: CANVAS UPDATE (post-learning)\nInput: Previous canvas version + new validation data\nOutput: Updated canvas with specific changes highlighted + version increment\n\nTYPE 5: CANVAS HEALTH SUMMARY\nInput: Current canvas\nOutput: Which blocks are validated vs. hypothetical; critical gaps; priority actions\n\n### Canvas Output Structure\n\n```\nBUSINESS MODEL CANVAS -- [Venture Name]\nVersion: [N.N] (post-[stage]) | Date: [Date]\n================================================================\n\n1. CUSTOMER SEGMENTS\n   Primary:   [Who specifically -- not \"SMEs\"; name the role and context]\n   Secondary: [If applicable; note if different product\u002Fprice needed]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [Biggest risk in this block]\n   Open Q:    [The one thing we still need to learn about this segment]\n\n2. VALUE PROPOSITIONS\n   Primary:   [The core promise -- specific, differentiated, outcome-focused]\n   Secondary: [Supporting value]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [What could undermine this value proposition]\n   Open Q:    [What the customer might not believe without proof]\n\n3. CHANNELS\n   Awareness:  [How customers discover you]\n   Evaluation: [How customers decide to buy]\n   Purchase:   [How they buy]\n   Delivery:   [How they receive value]\n   After-sale: [How you retain and grow them]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [Scalability; CAC at volume]\n   Open Q:    [Which channel needs validation first]\n\n4. CUSTOMER RELATIONSHIPS\n   Current:   [How you manage the relationship today]\n   Target:    [How it scales]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [What breaks when you can no longer do high-touch]\n   Open Q:    [Minimum viable onboarding that produces adoption]\n\n5. REVENUE STREAMS\n   Primary:   [Pricing model + price point]\n   Secondary: [If applicable]\n   Evidence:  [ASSUMED \u002F ANECDOTAL \u002F VALIDATED]\n   Risk:      [The pricing assumption that has been least tested]\n   Open Q:    [What pricing behaviour validates willingness to pay?]\n\n6. KEY RESOURCES\n   Critical:  [The resource without which value cannot be delivered]\n   Important: [Resources that matter but can be substituted]\n   Risk:      [Most fragile resource; what if it disappears?]\n   Open Q:    [Which resource must be built\u002Fowned vs. rented\u002Faccessed?]\n\n7. KEY ACTIVITIES\n   Core:      [The activity most central to value creation]\n   Growth:    [The activity most central to customer acquisition]\n   Risk:      [What the team cannot currently do; capability gap]\n   Open Q:    [What activity, if outsourced, would be dangerous?]\n\n8. KEY PARTNERSHIPS\n   Critical:  [Partner without whom value cannot be delivered]\n   Strategic: [Partner who provides competitive advantage]\n   Risk:      [Single-point-of-failure partnerships]\n   Open Q:    [Which partnership must be formalised before scaling?]\n\n9. COST STRUCTURE\n   Fixed:     [Monthly fixed costs -- list with amounts]\n   Variable:  [Per-customer or per-transaction costs]\n   Unit cost: [Total cost to serve one customer per month]\n   Margin:    [Revenue - unit cost = contribution margin]\n   Evidence:  [ESTIMATED \u002F MEASURED]\n   Open Q:    [Which cost assumption changes most at 10x scale?]\n\nCANVAS HEALTH SUMMARY:\n  Validated blocks:           [List]\n  Partially validated:        [List]\n  Hypothetical (build risk):  [List]\n  Critical gaps:              [Blocks where evidence is weakest vs. risk is highest]\n================================================================\n```\n\n### Value Proposition Quality Standard\n\nA strong Value Proposition has:\n\n- A specific outcome for a specific customer (not a feature list)\n- A differentiated claim (why this, not the alternative)\n- Evidence it is valued (customer said it or paid for it)\n- A reason the customer cannot easily get this elsewhere\n\n### Alternative Business Model Patterns\n\nWhen generating alternatives, explore these structural variations:\n\n- Subscription vs. usage-based vs. transaction fee\n- Selling to enterprise vs. selling to individual professionals\n- Direct vs. marketplace vs. platform\n- Free + premium vs. paid only vs. free forever\n- Product-led growth vs. sales-led growth\n- Build vs. partner vs. white-label\n\n## FINANCIAL REASONING STANDARD\n\nFor Revenue Streams and Cost Structure blocks:\n\n- Unit economics first: ensure the unit economics work before projecting revenue\n- If LTV:CAC \u003C 3, flag as a serious concern in the canvas\n- Churn is the most dangerous assumption: if churn is ASSUMED, flag it\n- Always show contribution margin calculation in Cost Structure\n\n## ASSUMPTION TRACKING\n\nAfter any canvas output:\n\n- Surface which blocks have changed and what evidence supports the change\n- Identify the most critical untested assumption across all 9 blocks\n- Propose innov.local.md updates for any changed blocks\n- Always distinguish between ASSUMED, ANECDOTAL, and VALIDATED evidence\n\n## NEVER DO THESE\n\n- NEVER leave a canvas block empty -- if you don't know: write your assumption\n  and mark it ASSUMED; an empty block is a hidden risk\n- NEVER mark a block VALIDATED without customer payment or sustained usage data\n- NEVER produce a canvas without a health summary showing which blocks\n  are validated vs. hypothetical -- this is what tells you where to focus\n- NEVER accept \"We'll figure out monetisation later\" -- Revenue Streams and\n  Cost Structure must be at least hypothesised from Day 1\n\nALL OUTPUTS REQUIRE REVIEW BY A QUALIFIED PROFESSIONAL BEFORE USE IN BUSINESS DECISIONS.\n",{"name":5,"license":14,"metadata":47,"description":51},{"author":48,"version":49,"plugin-commands":50},"Panaversity","1.0","\u002Fcanvas","Activate for: business model canvas, BMC, business model, value proposition, customer segments, channels, customer relationships, revenue streams, key resources, key activities, key partnerships, cost structure, canvas build, canvas stress test, alternative business model, monetisation, pricing model, revenue model, how does the business make money, business design, Osterwalder. NOT for: unit economics or financial modelling (use financials), competitive analysis (use market), pitch deck (use pitch).\n","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-06-agentfactory-business-plugins-main-innovation-skills-canvas-skill-68f2e716","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill canvas",{"tool":64,"command":65},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill canvas",{"tool":67,"command":68},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill canvas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-06-agentfactory-business-plugins-main-innovation-skills-canvas-skill-68f2e716\u002FSKILL.md",true,[],[73,100,127,158,185,219],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":42},"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\".","MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[75,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":42},"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'.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":139,"publishedAt":42},"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",[133,136],{"categoryNo":134,"categoryName":135,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[140,141,142,143,144,145,146,147,148,149,150,151,152,93,153,154,155,156,98,157],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":167,"publishedAt":42},"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",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[168,169,170,171,172,173,174,175,176,93,177,178,179,34,180,181,182,183,184,98],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","load balancer","attributes","front","load","balancer",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":202,"publishedAt":42},"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",[191,194,199],{"categoryNo":192,"categoryName":193,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":195,"categoryName":196,"taxonomyType":197,"taxonomyTypeDesc":198},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":200,"categoryName":201,"taxonomyType":197,"taxonomyTypeDesc":198},"01JBSEEDCAT000000000000038","人力资源",[203,204,205,206,207,208,209,210,108,211,93,212,213,214,37,215,216,217,98,218],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","do","task","cv","letter",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":6,"sourceHtmlUrl":223,"categories":224,"keywords":225,"publishedAt":42},"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",[],[226,227,41,228,229,206,230,93,215,231,232,233,234,235,236,237,238,239,98,240],"steno mode","mode","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]