[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGMB3R139ETYPZ7D8N0XF6":3,"skill-same:01M6MGMB3R139ETYPZ7D8N0XF6":84},{"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":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":13,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":69,"install":70,"resources":83},"01M6MGMB3R139ETYPZ7D8N0XF6","pricing-strategist",null,"Use when designing or revisiting product pricing — selecting a pricing model (subscription seat-based, usage-based, value-based, freemium, or hybrid), running Van Westendorp Price Sensitivity Meter analysis on WTP survey data, or designing Good\u002FBetter\u002FBest packaging tiers. Recommends a model and a price range with trade-offs, never a single number. For Commercial leads, Product Marketing, and CMOs at the pricing-design moment — not deal-by-deal discounting, not brand positioning.","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-gemini-skills-pricing-strategist-skill-00f6e383\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"pricing","pricing strategist","strategist","trade-offs","design","number","pricing model","CMOS","positioning","good","never","survey","saas-pricing","value-based-pricing","van-westendorp","wtp","packaging","model","analysis","code","2026-11-10 10:12:30",false,"---\nname: pricing-strategist\ndescription: \"Use when designing or revisiting product pricing — selecting a pricing model (subscription seat-based, usage-based, value-based, freemium, or hybrid), running Van Westendorp Price Sensitivity Meter analysis on WTP survey data, or designing Good\u002FBetter\u002FBest packaging tiers. Recommends a model and a price range with trade-offs, never a single number. For Commercial leads, Product Marketing, and CMOs at the pricing-design moment — not deal-by-deal discounting, not brand positioning.\"\nversion: 2.8.0\nauthor: claude-code-skills\nlicense: MIT\ntags: [commercial, pricing, packaging, wtp, van-westendorp, value-based-pricing, saas-pricing]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# pricing-strategist\n\n## Purpose\n\nHelp Commercial, Product Marketing, and CMO functions answer three questions at the pricing-design moment:\n\n1. **Which pricing model fits this product + customer + market?** (subscription seat-based, usage-based, value-based, freemium, hybrid)\n2. **What does the customer actually pay before it feels too expensive?** (Van Westendorp PSM on WTP survey responses)\n3. **How should we package this into tiers?** (Good \u002F Better \u002F Best — with anti-pattern detection)\n\nThe skill recommends **a model and a range**. The human picks the number, owns the trade-offs, and runs the GTM.\n\n## When to use\n\n- Launching a new SaaS \u002F API \u002F AI tool and choosing the first pricing model\n- Revisiting pricing after 18+ months of GTM data (model shift, not just price increase)\n- Designing or redesigning tier packaging (Good\u002FBetter\u002FBest, Bronze\u002FSilver\u002FGold)\n- You have Van Westendorp survey data and want the optimal price range\n- A board \u002F exec is asking \"what should we charge?\" and you need the structured answer\n- You suspect your packaging has anti-patterns (decoy tier, feature dump, no upgrade trigger)\n\n**Do not use for:**\n- Per-deal discount approval → `deal-desk`\n- Strategic CMO positioning, brand, category creation → `c-level-advisor\u002Fcmo-advisor`\n- Whole-company revenue strategy → `c-level-advisor\u002Fcro-advisor`\n- Technical-sale enablement → `business-growth\u002Fsales-engineer`\n\n## Workflow\n\n### Step 1 — Assess customer context\n\nFill `assets\u002Fpricing_brief_template.md` (≈ 20 min). Capture: industry, deal size avg, customer count, value drivers, adoption curve, consumption pattern (seat \u002F usage \u002F value \u002F hybrid), competitor models.\n\n### Step 2 — Pick the pricing model\n\nRun `scripts\u002Fpricing_model_picker.py --input brief.json --profile saas --output markdown`. Output ranks 5 models by fit-score 0-100 with trade-offs. Decision logic is deterministic: low usage variance + high seat-attach → subscription wins; power-law usage + variable customer value → usage-based wins.\n\n### Step 3 — Validate WTP with Van Westendorp PSM\n\nIf you have survey data (≥ 4 questions per respondent: too cheap \u002F bargain \u002F getting expensive \u002F too expensive), run `scripts\u002Fwtp_analyzer.py --input survey.json --output markdown`. Output: 4 intersection points (OPP, IDP, PMC, PME) and the Range of Acceptable Prices.\n\nPSM gives a **range**, not the price. See `references\u002Fvan_westendorp_methodology.md` for common misinterpretations.\n\n### Step 4 — Design packaging\n\nRun `scripts\u002Fpackaging_designer.py --input features.json --profile saas --output markdown`. Output: 3-tier Good\u002FBetter\u002FBest assignment with anti-pattern flags (decoy tier, feature dump, no upgrade trigger, Bronze loss leader, Enterprise no-anchor).\n\n### Step 5 — Decide\n\nTake model + range + packaging into the pricing committee. Skill does not commit the number — you do.\n\n## Scripts\n\n- `scripts\u002Fpricing_model_picker.py` — 5-model fit scorer (subscription \u002F usage \u002F value \u002F freemium \u002F hybrid)\n- `scripts\u002Fwtp_analyzer.py` — Van Westendorp PSM implementation\n- `scripts\u002Fpackaging_designer.py` — Good\u002FBetter\u002FBest tier designer with anti-pattern detection\n\nAll scripts: stdlib only. `--help` and `--sample` work on all three.\n\n## Quick example\n\n```bash\n# Emits a scored 5-model pricing-fit recommendation (subscription \u002F usage \u002F value \u002F freemium \u002F hybrid) for the built-in example\ncd commercial\u002Fskills\u002Fpricing-strategist && python3 scripts\u002Fpricing_model_picker.py --sample\n```\n\n## References\n\n- `references\u002Fsaas_pricing_canon.md` — Skok, Tunguz, Campbell, Ramanujam, BVP, Shevlin, Stanford GSB\n- `references\u002Fvan_westendorp_methodology.md` — original 1976 paper, NMS refinement, Conjoint.ly, Sawtooth, ESOMAR, Lipovetsky, Decision Analyst\n- `references\u002Fpackaging_anti_patterns.md` — ProfitWell, OpenView, BVP vertical SaaS, Ramanujam, Poyar, SaaS Capital\n\n## Assumptions\n\n- Pricing decisions are joint: Commercial owns the model + tier shape, Product owns the features-per-tier, Finance owns the discount envelope, Legal owns the contract.\n- Van Westendorp PSM is a **directional** tool. N ≥ 30 minimum, N ≥ 100 preferred. Below 30, the script emits a sample-size warning.\n- \"Value-based pricing\" requires a measurable customer value driver (revenue lift, cost saved, time recovered). If you can't measure it, don't pick value-based.\n- Industry profiles tune defaults — they don't override your data.\n- This is a decision-support skill, not a price oracle. Output is a model + range, never the number.\n\n## Anti-patterns\n\n- **Recommending a specific number.** This skill emits a model and a range. Final price is a human commercial decision involving deal-desk policy, competitive intel, and strategic intent that this skill cannot know.\n- **Using PSM with N \u003C 30.** Statistical noise dominates. The script warns; respect the warning.\n- **Treating PSM as \"the price.\"** PSM gives a Range of Acceptable Prices (RAP) and an Optimal Price Point (OPP). Test the range in market, don't anchor on a single intersection.\n- **Picking value-based pricing without a measurable value metric.** Without instrumentation to show customer ROI, value-based collapses into \"whatever they'll pay\" — which is just bad usage-based pricing.\n- **Designing tiers before picking a model.** Tier structure depends on the model. Run pricing_model_picker first.\n- **Packaging \"feature dumps\" into the Best tier.** If Best has 3x the features for 2x the price, customers buy Better and never upgrade. See `packaging_anti_patterns.md`.\n- **Hidden usage-based pricing inside subscription tiers.** \"Up to 100k API calls\u002Fmo, then $X per 1k\" disguised as a \"Pro tier\" is two pricing models in one. Customers notice. Pick one.\n- **Confusing this skill with deal-desk.** Pricing strategy = the menu. Deal-desk = approving discounts off the menu. Different decision, different cadence, different owner.\n\n## Distinct from\n\n- **deal-desk** — per-deal discount approval, MEDDIC, deal scoring. Operates daily on existing pricing.\n- **c-level-advisor\u002Fcmo-advisor** — strategic positioning, brand, category. Pricing strategist consumes positioning as input, doesn't generate it.\n- **c-level-advisor\u002Fcro-advisor** — full-funnel revenue strategy, comp plans, territory design. Pricing strategist is one input to CRO.\n- **business-growth\u002Fsales-engineer** — technical sale, POC scoping. Sales engineering operates after pricing is set.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-commercial` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is your customer paying for outcomes, seats, or usage?\"**\n   Recommended: outcomes (value-based) if you can measure them; usage if marginal cost is variable; seats only if usage is roughly flat per user.\n   Canon: Ramanujam 2016 (*Monetizing Innovation*) — Mistake #1 of 9: seat-based pricing on a usage-variable product caps TAM at ~20% of WTP.\n\n2. **\"Do you have a measurable value metric, or are you guessing?\"**\n   Recommended: instrument the value metric BEFORE going to market with value-based pricing.\n   Canon: Patrick Campbell \u002F ProfitWell research — value-based without instrumentation collapses into bad usage-based pricing.\n\n3. **\"What's the variance in customer usage across your top decile vs. median?\"**\n   Recommended: variance > 10x → usage-based wins; variance \u003C 3x → subscription wins; in between → hybrid with usage overage.\n   Canon: Kyle Poyar (*Growth Unhinged*) — high-variance products lose 60%+ of revenue on flat-rate plans.\n\n4. **\"What's your competitor's pricing model, and why are you choosing the same or different?\"**\n   Recommended: surface the differentiation hypothesis explicitly. Identical pricing = identical value claim.\n   Canon: David Skok (*For Entrepreneurs*) — pricing is a positioning signal.\n\n5. **\"What sample size do you have for WTP analysis, and is it segmented?\"**\n   Recommended: N≥30 per segment for PSM, N≥100 for conjoint.\n   Canon: van Westendorp 1976 \u002F Sawtooth Software methodology — sub-30 PSM is statistical noise.\n\n6. **\"What's the ONE feature that forces a tier upgrade?\"**\n   Recommended: every Better and Best tier needs a single non-negotiable upgrade trigger.\n   Canon: Ramanujam (*Monetizing Innovation*) — Mistake #4: tiers with no clear differentiator make 70% of customers pick the cheapest.\n\nWalk depth-first. Lock 1-3 before opening 4-6. After all 6 are answered, invoke `pricing_model_picker.py` → `wtp_analyzer.py` → `packaging_designer.py` in sequence.\n","# pricing-strategist\n\n## Purpose\n\nHelp Commercial, Product Marketing, and CMO functions answer three questions at the pricing-design moment:\n\n1. **Which pricing model fits this product + customer + market?** (subscription seat-based, usage-based, value-based, freemium, hybrid)\n2. **What does the customer actually pay before it feels too expensive?** (Van Westendorp PSM on WTP survey responses)\n3. **How should we package this into tiers?** (Good \u002F Better \u002F Best — with anti-pattern detection)\n\nThe skill recommends **a model and a range**. The human picks the number, owns the trade-offs, and runs the GTM.\n\n## When to use\n\n- Launching a new SaaS \u002F API \u002F AI tool and choosing the first pricing model\n- Revisiting pricing after 18+ months of GTM data (model shift, not just price increase)\n- Designing or redesigning tier packaging (Good\u002FBetter\u002FBest, Bronze\u002FSilver\u002FGold)\n- You have Van Westendorp survey data and want the optimal price range\n- A board \u002F exec is asking \"what should we charge?\" and you need the structured answer\n- You suspect your packaging has anti-patterns (decoy tier, feature dump, no upgrade trigger)\n\n**Do not use for:**\n- Per-deal discount approval → `deal-desk`\n- Strategic CMO positioning, brand, category creation → `c-level-advisor\u002Fcmo-advisor`\n- Whole-company revenue strategy → `c-level-advisor\u002Fcro-advisor`\n- Technical-sale enablement → `business-growth\u002Fsales-engineer`\n\n## Workflow\n\n### Step 1 — Assess customer context\n\nFill `assets\u002Fpricing_brief_template.md` (≈ 20 min). Capture: industry, deal size avg, customer count, value drivers, adoption curve, consumption pattern (seat \u002F usage \u002F value \u002F hybrid), competitor models.\n\n### Step 2 — Pick the pricing model\n\nRun `scripts\u002Fpricing_model_picker.py --input brief.json --profile saas --output markdown`. Output ranks 5 models by fit-score 0-100 with trade-offs. Decision logic is deterministic: low usage variance + high seat-attach → subscription wins; power-law usage + variable customer value → usage-based wins.\n\n### Step 3 — Validate WTP with Van Westendorp PSM\n\nIf you have survey data (≥ 4 questions per respondent: too cheap \u002F bargain \u002F getting expensive \u002F too expensive), run `scripts\u002Fwtp_analyzer.py --input survey.json --output markdown`. Output: 4 intersection points (OPP, IDP, PMC, PME) and the Range of Acceptable Prices.\n\nPSM gives a **range**, not the price. See `references\u002Fvan_westendorp_methodology.md` for common misinterpretations.\n\n### Step 4 — Design packaging\n\nRun `scripts\u002Fpackaging_designer.py --input features.json --profile saas --output markdown`. Output: 3-tier Good\u002FBetter\u002FBest assignment with anti-pattern flags (decoy tier, feature dump, no upgrade trigger, Bronze loss leader, Enterprise no-anchor).\n\n### Step 5 — Decide\n\nTake model + range + packaging into the pricing committee. Skill does not commit the number — you do.\n\n## Scripts\n\n- `scripts\u002Fpricing_model_picker.py` — 5-model fit scorer (subscription \u002F usage \u002F value \u002F freemium \u002F hybrid)\n- `scripts\u002Fwtp_analyzer.py` — Van Westendorp PSM implementation\n- `scripts\u002Fpackaging_designer.py` — Good\u002FBetter\u002FBest tier designer with anti-pattern detection\n\nAll scripts: stdlib only. `--help` and `--sample` work on all three.\n\n## Quick example\n\n```bash\n# Emits a scored 5-model pricing-fit recommendation (subscription \u002F usage \u002F value \u002F freemium \u002F hybrid) for the built-in example\ncd commercial\u002Fskills\u002Fpricing-strategist && python3 scripts\u002Fpricing_model_picker.py --sample\n```\n\n## References\n\n- `references\u002Fsaas_pricing_canon.md` — Skok, Tunguz, Campbell, Ramanujam, BVP, Shevlin, Stanford GSB\n- `references\u002Fvan_westendorp_methodology.md` — original 1976 paper, NMS refinement, Conjoint.ly, Sawtooth, ESOMAR, Lipovetsky, Decision Analyst\n- `references\u002Fpackaging_anti_patterns.md` — ProfitWell, OpenView, BVP vertical SaaS, Ramanujam, Poyar, SaaS Capital\n\n## Assumptions\n\n- Pricing decisions are joint: Commercial owns the model + tier shape, Product owns the features-per-tier, Finance owns the discount envelope, Legal owns the contract.\n- Van Westendorp PSM is a **directional** tool. N ≥ 30 minimum, N ≥ 100 preferred. Below 30, the script emits a sample-size warning.\n- \"Value-based pricing\" requires a measurable customer value driver (revenue lift, cost saved, time recovered). If you can't measure it, don't pick value-based.\n- Industry profiles tune defaults — they don't override your data.\n- This is a decision-support skill, not a price oracle. Output is a model + range, never the number.\n\n## Anti-patterns\n\n- **Recommending a specific number.** This skill emits a model and a range. Final price is a human commercial decision involving deal-desk policy, competitive intel, and strategic intent that this skill cannot know.\n- **Using PSM with N \u003C 30.** Statistical noise dominates. The script warns; respect the warning.\n- **Treating PSM as \"the price.\"** PSM gives a Range of Acceptable Prices (RAP) and an Optimal Price Point (OPP). Test the range in market, don't anchor on a single intersection.\n- **Picking value-based pricing without a measurable value metric.** Without instrumentation to show customer ROI, value-based collapses into \"whatever they'll pay\" — which is just bad usage-based pricing.\n- **Designing tiers before picking a model.** Tier structure depends on the model. Run pricing_model_picker first.\n- **Packaging \"feature dumps\" into the Best tier.** If Best has 3x the features for 2x the price, customers buy Better and never upgrade. See `packaging_anti_patterns.md`.\n- **Hidden usage-based pricing inside subscription tiers.** \"Up to 100k API calls\u002Fmo, then $X per 1k\" disguised as a \"Pro tier\" is two pricing models in one. Customers notice. Pick one.\n- **Confusing this skill with deal-desk.** Pricing strategy = the menu. Deal-desk = approving discounts off the menu. Different decision, different cadence, different owner.\n\n## Distinct from\n\n- **deal-desk** — per-deal discount approval, MEDDIC, deal scoring. Operates daily on existing pricing.\n- **c-level-advisor\u002Fcmo-advisor** — strategic positioning, brand, category. Pricing strategist consumes positioning as input, doesn't generate it.\n- **c-level-advisor\u002Fcro-advisor** — full-funnel revenue strategy, comp plans, territory design. Pricing strategist is one input to CRO.\n- **business-growth\u002Fsales-engineer** — technical sale, POC scoping. Sales engineering operates after pricing is set.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-commercial` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is your customer paying for outcomes, seats, or usage?\"**\n   Recommended: outcomes (value-based) if you can measure them; usage if marginal cost is variable; seats only if usage is roughly flat per user.\n   Canon: Ramanujam 2016 (*Monetizing Innovation*) — Mistake #1 of 9: seat-based pricing on a usage-variable product caps TAM at ~20% of WTP.\n\n2. **\"Do you have a measurable value metric, or are you guessing?\"**\n   Recommended: instrument the value metric BEFORE going to market with value-based pricing.\n   Canon: Patrick Campbell \u002F ProfitWell research — value-based without instrumentation collapses into bad usage-based pricing.\n\n3. **\"What's the variance in customer usage across your top decile vs. median?\"**\n   Recommended: variance > 10x → usage-based wins; variance \u003C 3x → subscription wins; in between → hybrid with usage overage.\n   Canon: Kyle Poyar (*Growth Unhinged*) — high-variance products lose 60%+ of revenue on flat-rate plans.\n\n4. **\"What's your competitor's pricing model, and why are you choosing the same or different?\"**\n   Recommended: surface the differentiation hypothesis explicitly. Identical pricing = identical value claim.\n   Canon: David Skok (*For Entrepreneurs*) — pricing is a positioning signal.\n\n5. **\"What sample size do you have for WTP analysis, and is it segmented?\"**\n   Recommended: N≥30 per segment for PSM, N≥100 for conjoint.\n   Canon: van Westendorp 1976 \u002F Sawtooth Software methodology — sub-30 PSM is statistical noise.\n\n6. **\"What's the ONE feature that forces a tier upgrade?\"**\n   Recommended: every Better and Best tier needs a single non-negotiable upgrade trigger.\n   Canon: Ramanujam (*Monetizing Innovation*) — Mistake #4: tiers with no clear differentiator make 70% of customers pick the cheapest.\n\nWalk depth-first. Lock 1-3 before opening 4-6. After all 6 are answered, invoke `pricing_model_picker.py` → `wtp_analyzer.py` → `packaging_designer.py` in sequence.\n",{"name":5,"tags":53,"author":55,"license":14,"version":56,"description":7,"compatible_tools":57},[54,28,44,43,42,41,40],"commercial","claude-code-skills","2.8.0",[58,59,60,61,62,63],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-pricing-strategist-skill-00f6e383","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill pricing-strategist",{"tool":76,"command":77},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill pricing-strategist",{"tool":79,"command":80},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill pricing-strategist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-pricing-strategist-skill-00f6e383\u002FSKILL.md",true,[],[85,110,138,169,197,230],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":48},"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",[],[87,92,93,94,95,47,96,97,98,99,100,101,102,103,104,105,106,107,108,109],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":114,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":48},"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",[],[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"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":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":150,"publishedAt":48},"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",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":148,"categoryName":149,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[151,152,153,154,155,156,157,158,159,160,161,162,163,103,164,165,166,167,108,168],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":48},"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",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[179,180,181,182,183,184,185,186,187,103,188,189,190,191,192,193,194,195,196,108],"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":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":212,"publishedAt":48},"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",[203,206,209],{"categoryNo":204,"categoryName":205,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":207,"categoryName":208,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":210,"categoryName":211,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000038","人力资源",[213,214,215,216,217,218,219,220,119,221,103,222,223,224,225,226,227,228,108,229],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":236,"publishedAt":48},"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",[],[237,238,239,240,241,216,242,103,226,243,244,245,246,247,248,249,250,251,108,252],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]