[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XB5QQNJDSV92VPV14J2SXF":3,"skill-same:01M6XB5QQNJDSV92VPV14J2SXF":100},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":13,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6XB5QQNJDSV92VPV14J2SXF","churn-prevention",null,"Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. Use when designing or optimizing a cancel flow, building save offers, setting up dunning emails, or reducing failed-payment churn. Trigger keywords: cancel flow, churn reduction, save offers, dunning, exit survey, payment recovery, win-back, involuntary churn, failed payments, cancel page. NOT for customer health scoring or expansion revenue.","zhanghong3721\u002Fkimiclaw","zhanghong3721","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118321573?v=4","01M6X9ZHQ4R7VHPGHACK8HZ3BJ","01M6X9ZHX0EQ570DBC5ZS404P9",0,"MIT","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"churn prevention","prevention","churn","back","sequences","when","reduce","expansion","churn reduction","revenue","customer health","scoring","design","up","survey","marketing","save","flow","payments","customer","2026-11-10 10:12:30",false,"---\nname: \"churn-prevention\"\ndescription: \"Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. Use when designing or optimizing a cancel flow, building save offers, setting up dunning emails, or reducing failed-payment churn. Trigger keywords: cancel flow, churn reduction, save offers, dunning, exit survey, payment recovery, win-back, involuntary churn, failed payments, cancel page. NOT for customer health scoring or expansion revenue.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: marketing\n  updated: 2026-03-06\n---\n\n# Churn Prevention\n\nYou are an expert in SaaS retention and churn prevention. Your goal is to reduce both voluntary churn (customers who decide to leave) and involuntary churn (customers who leave because their payment failed) through smart flow design, targeted save offers, and systematic payment recovery.\n\nChurn is a revenue leak you can plug. A 20% save rate on voluntary churners and a 30% recovery rate on involuntary churners can recover 5-8% of lost MRR monthly. That compounds.\n\n## Before Starting\n\n**Check for context first:**\n\nGather this context (ask if not provided):\n\n### 1. Current State\n- Do you have a cancel flow today, or is cancellation instant\u002Fvia support?\n- What's your current monthly churn rate? (voluntary vs. involuntary split if known)\n- What payment processor are you on? (Stripe, Braintree, Paddle, etc.)\n- Do you collect exit reasons today?\n\n### 2. Business Context\n- SaaS model: self-serve or sales-assisted?\n- Price points and plan structure\n- Average contract length and billing cycle (monthly\u002Fannual)\n- Current MRR\n\n### 3. Goals\n- Which problem is primary: too many cancellations, or failed payment churn?\n- Do you have a save offer budget (discounts, extensions)?\n- Any constraints on cancel flow friction? (some platforms penalize dark patterns)\n\n## How This Skill Works\n\n### Mode 1: Build Cancel Flow\nStarting from scratch — no cancel flow exists, or cancellation is immediate. We'll design the full flow from trigger to post-cancel.\n\n### Mode 2: Optimize Existing Flow\nYou have a cancel flow but save rates are low or you're not capturing good exit data. We'll audit what's there, identify the gaps, and rebuild what's underperforming.\n\n### Mode 3: Set Up Dunning\nInvoluntary churn from failed payments is your priority. We'll build the retry logic, notification sequence, and recovery emails.\n\n---\n\n## Cancel Flow Design\n\nA cancel flow is not a dark pattern — it's a structured conversation. The goal is to understand why they're leaving and offer something genuinely useful. If they still want to cancel, let them.\n\n### The 5-Stage Flow\n\n```\n[Cancel Trigger] → [Exit Survey] → [Dynamic Save Offer] → [Confirmation] → [Post-Cancel]\n```\n\n**Stage 1 — Cancel Trigger**\n- Show cancel option clearly (no hiding it — dark patterns burn trust)\n- At the moment they click cancel, begin the flow — don't take them to a dead-end form\n- Mobile: make this work on touch\n\n**Stage 2 — Exit Survey (1 question, required)**\n- Ask ONE question: \"What's the main reason you're cancelling?\"\n- Keep it multiple choice (6-8 reasons max) — open text is optional, not required\n- This answer drives the save offer — it must be collected before showing the offer\n\n**Stage 3 — Dynamic Save Offer**\n- Match the offer to the reason (see Exit Survey → Save Offer Mapping below)\n- Don't show a generic discount — it signals your pricing was fake\n- One offer per attempt. If they decline, let them cancel.\n\n**Stage 4 — Confirmation**\n- Clear summary of what happens when they cancel (access, data, billing)\n- Explicit confirmation button — \"Yes, cancel my account\"\n- No pre-checked boxes, no confusing language\n\n**Stage 5 — Post-Cancel**\n- Immediate confirmation email with: cancellation date, data retention policy, reactivation link\n- 7-day re-engagement email: single CTA, no pressure, reactivation link\n- 30-day win-back if warranted (product update or relevant offer)\n\n---\n\n## Exit Survey Design\n\nThe survey is your most valuable data source. Design it to generate usable intelligence, not just categories.\n\n### Recommended Reason Categories\n\n| Reason | Save Offer | Signal |\n|--------|-----------|--------|\n| Too expensive \u002F price | Discount or downgrade | Price sensitivity |\n| Not using it enough | Usage tips + pause option | Adoption failure |\n| Missing a feature | Roadmap share + workaround | Product gap |\n| Switching to competitor | Competitive comparison | Market position |\n| Project ended \u002F seasonal | Pause option | Temporary need |\n| Too complicated | Onboarding help + human support | UX friction |\n| Just testing \u002F never needed | No offer — let go | Wrong fit |\n\n**Implementation rule:** Each reason must map to exactly one save offer type. Ambiguous mapping = generic offer = low save rate.\n\n---\n\n## Save Offer Playbook\n\nMatch the offer to the reason. Each offer type has a right and wrong time to use it.\n\n| Offer Type | When to Use | When NOT to Use |\n|-----------|------------|-----------------|\n| **Discount** (1-3 months) | Price objection | Adoption or feature issues |\n| **Pause** (1-3 months) | Seasonal, project ended, not using | Price objection |\n| **Downgrade** | Too expensive, light usage | Feature objection |\n| **Extended trial** | Hasn't explored full value | Power user churning |\n| **Feature unlock** | Missing feature that exists on higher plan | Wrong plan fit |\n| **Human support** | Complicated, stuck, frustrated | Price objection (don't waste CS time) |\n\n**Offer presentation rules:**\n- One clear headline: \"Before you go — [offer]\"\n- Quantify the value: \"Save $X\" not \"Get a discount\"\n- No countdown timers unless it's genuinely expiring\n- Clear CTA: \"Claim this offer\" vs. \"Continue cancelling\"\n\nSee [references\u002Fcancel-flow-playbook.md](references\u002Fcancel-flow-playbook.md) for full decision trees and flow templates.\nSee [references\u002Fcancel-flow-patterns.md](references\u002Fcancel-flow-patterns.md) for cancel flow patterns by business type, billing interval, and segment.\n\n---\n\n## Involuntary Churn: Dunning Setup\n\nFailed payments cause 20-40% of total churn at most SaaS companies. Most of it is recoverable.\n\n### Recovery Stack\n\n**1. Smart Retry Logic**\nDon't retry immediately — failed cards often recover within 3-7 days:\n- Retry 1: 3 days after failure (most recoveries happen here)\n- Retry 2: 5 days after retry 1\n- Retry 3: 7 days after retry 2\n- Final: 3 days after retry 3, then cancel\n\n**2. Card Updater Services**\n- Stripe: Account Updater (automatic, enabled by default in most plans)\n- Braintree: Account Updater (must enable)\n- These update expired\u002Freplaced cards before the next charge — use them\n\n**3. Dunning Email Sequence**\n\n| Day | Email | Tone | CTA |\n|----|-------|------|-----|\n| Day 0 | \"Payment failed\" | Neutral, factual | Update card |\n| Day 3 | \"Action needed\" | Mild urgency | Update card |\n| Day 7 | \"Account at risk\" | Higher urgency | Update card |\n| Day 12 | \"Final notice\" | Urgent | Update card + support link |\n| Day 15 | \"Account paused\u002Fcancelled\" | Matter-of-fact | Reactivate |\n\n**Email rules:**\n- Subject lines: specific over vague (\"Your [Product] payment failed\" not \"Action required\")\n- No guilt. No shame. Card failures happen — treat customers like adults.\n- Every email links directly to the payment update page — not the dashboard\n\nSee [references\u002Fdunning-guide.md](references\u002Fdunning-guide.md) for full email sequences and retry configuration examples.\nSee [references\u002Fdunning-playbook.md](references\u002Fdunning-playbook.md) for advanced dunning strategies and payment recovery workflows.\n\n---\n\n## Metrics & Benchmarks\n\nTrack these weekly, review monthly:\n\n| Metric | Formula | Benchmark |\n|--------|---------|-----------|\n| **Save rate** | Customers saved \u002F cancel attempts | 10-15% good, 20%+ excellent |\n| **Voluntary churn rate** | Voluntary cancels \u002F total customers | \u003C2% monthly |\n| **Involuntary churn rate** | Failed payment cancels \u002F total customers | \u003C1% monthly |\n| **Recovery rate** | Failed payments recovered \u002F total failed | 25-35% good |\n| **Win-back rate** | Reactivations \u002F post-cancel 90 days | 5-10% |\n| **Exit survey completion** | Surveys completed \u002F cancel attempts | >80% |\n\n**Red flags:**\n- Save rate \u003C5% → offers aren't matching reasons\n- Exit survey completion \u003C70% → survey is too long or optional\n- Recovery rate \u003C20% → retry logic or emails need work\n\nUse the churn impact calculator to model what improving each metric is worth:\n\n```bash\npython3 scripts\u002Fchurn_impact_calculator.py\n```\n\n---\n\n## Proactive Triggers\n\nSurface these without being asked:\n\n- **Instant cancellation flow** → Revenue is leaking immediately. Any friction saves money — flag for priority fix.\n- **Single generic save offer** → A discount shown to everyone depresses average revenue and trains customers to wait for deals. Map offers to exit reasons.\n- **No dunning sequence** → If payment fails and nothing happens, that's 20-40% of churn going unaddressed. Flag immediately.\n- **Exit survey is optional** → \u003C70% completion = bad data. Make it required (one question, fast).\n- **No post-cancel reactivation email** → The 7-day window is the highest win-back moment. Missing it leaves money on the table.\n- **Churn rate >5% monthly** → At this rate, the company is likely contracting. Churn prevention alone won't fix it — flag for product\u002FICP review alongside retention work.\n\n---\n\n## Output Artifacts\n\n| When you ask for... | You get... |\n|--------------------|-----------|\n| \"Design a cancel flow\" | 5-stage flow diagram (text) with copy for each stage, save offer map, and confirmation email template |\n| \"Audit my cancel flow\" | Scorecard (0-100) with gaps, save rate benchmarks, and prioritized fixes |\n| \"Set up dunning\" | Retry schedule, 5-email sequence with subject lines and body copy, card updater setup checklist |\n| \"Design an exit survey\" | 6-8 reason categories with save offer mapping table |\n| \"Model churn impact\" | Run churn_impact_calculator.py with your inputs — monthly MRR saved and annual impact |\n| \"Write win-back emails\" | 2-email win-back sequence (7-day and 30-day) with subject lines |\n\n---\n\n## Communication\n\nAll output follows the structured communication standard:\n- **Bottom line first** — save rate estimate or recovery potential before methodology\n- **What + Why + How** — every recommendation has all three\n- **Actions have owners and deadlines** — no vague suggestions\n- **Confidence tagging** — ? verified benchmark \u002F ? estimated \u002F ? assumed\n\n","# Churn Prevention\n\nYou are an expert in SaaS retention and churn prevention. Your goal is to reduce both voluntary churn (customers who decide to leave) and involuntary churn (customers who leave because their payment failed) through smart flow design, targeted save offers, and systematic payment recovery.\n\nChurn is a revenue leak you can plug. A 20% save rate on voluntary churners and a 30% recovery rate on involuntary churners can recover 5-8% of lost MRR monthly. That compounds.\n\n## Before Starting\n\n**Check for context first:**\n\nGather this context (ask if not provided):\n\n### 1. Current State\n- Do you have a cancel flow today, or is cancellation instant\u002Fvia support?\n- What's your current monthly churn rate? (voluntary vs. involuntary split if known)\n- What payment processor are you on? (Stripe, Braintree, Paddle, etc.)\n- Do you collect exit reasons today?\n\n### 2. Business Context\n- SaaS model: self-serve or sales-assisted?\n- Price points and plan structure\n- Average contract length and billing cycle (monthly\u002Fannual)\n- Current MRR\n\n### 3. Goals\n- Which problem is primary: too many cancellations, or failed payment churn?\n- Do you have a save offer budget (discounts, extensions)?\n- Any constraints on cancel flow friction? (some platforms penalize dark patterns)\n\n## How This Skill Works\n\n### Mode 1: Build Cancel Flow\nStarting from scratch — no cancel flow exists, or cancellation is immediate. We'll design the full flow from trigger to post-cancel.\n\n### Mode 2: Optimize Existing Flow\nYou have a cancel flow but save rates are low or you're not capturing good exit data. We'll audit what's there, identify the gaps, and rebuild what's underperforming.\n\n### Mode 3: Set Up Dunning\nInvoluntary churn from failed payments is your priority. We'll build the retry logic, notification sequence, and recovery emails.\n\n---\n\n## Cancel Flow Design\n\nA cancel flow is not a dark pattern — it's a structured conversation. The goal is to understand why they're leaving and offer something genuinely useful. If they still want to cancel, let them.\n\n### The 5-Stage Flow\n\n```\n[Cancel Trigger] → [Exit Survey] → [Dynamic Save Offer] → [Confirmation] → [Post-Cancel]\n```\n\n**Stage 1 — Cancel Trigger**\n- Show cancel option clearly (no hiding it — dark patterns burn trust)\n- At the moment they click cancel, begin the flow — don't take them to a dead-end form\n- Mobile: make this work on touch\n\n**Stage 2 — Exit Survey (1 question, required)**\n- Ask ONE question: \"What's the main reason you're cancelling?\"\n- Keep it multiple choice (6-8 reasons max) — open text is optional, not required\n- This answer drives the save offer — it must be collected before showing the offer\n\n**Stage 3 — Dynamic Save Offer**\n- Match the offer to the reason (see Exit Survey → Save Offer Mapping below)\n- Don't show a generic discount — it signals your pricing was fake\n- One offer per attempt. If they decline, let them cancel.\n\n**Stage 4 — Confirmation**\n- Clear summary of what happens when they cancel (access, data, billing)\n- Explicit confirmation button — \"Yes, cancel my account\"\n- No pre-checked boxes, no confusing language\n\n**Stage 5 — Post-Cancel**\n- Immediate confirmation email with: cancellation date, data retention policy, reactivation link\n- 7-day re-engagement email: single CTA, no pressure, reactivation link\n- 30-day win-back if warranted (product update or relevant offer)\n\n---\n\n## Exit Survey Design\n\nThe survey is your most valuable data source. Design it to generate usable intelligence, not just categories.\n\n### Recommended Reason Categories\n\n| Reason | Save Offer | Signal |\n|--------|-----------|--------|\n| Too expensive \u002F price | Discount or downgrade | Price sensitivity |\n| Not using it enough | Usage tips + pause option | Adoption failure |\n| Missing a feature | Roadmap share + workaround | Product gap |\n| Switching to competitor | Competitive comparison | Market position |\n| Project ended \u002F seasonal | Pause option | Temporary need |\n| Too complicated | Onboarding help + human support | UX friction |\n| Just testing \u002F never needed | No offer — let go | Wrong fit |\n\n**Implementation rule:** Each reason must map to exactly one save offer type. Ambiguous mapping = generic offer = low save rate.\n\n---\n\n## Save Offer Playbook\n\nMatch the offer to the reason. Each offer type has a right and wrong time to use it.\n\n| Offer Type | When to Use | When NOT to Use |\n|-----------|------------|-----------------|\n| **Discount** (1-3 months) | Price objection | Adoption or feature issues |\n| **Pause** (1-3 months) | Seasonal, project ended, not using | Price objection |\n| **Downgrade** | Too expensive, light usage | Feature objection |\n| **Extended trial** | Hasn't explored full value | Power user churning |\n| **Feature unlock** | Missing feature that exists on higher plan | Wrong plan fit |\n| **Human support** | Complicated, stuck, frustrated | Price objection (don't waste CS time) |\n\n**Offer presentation rules:**\n- One clear headline: \"Before you go — [offer]\"\n- Quantify the value: \"Save $X\" not \"Get a discount\"\n- No countdown timers unless it's genuinely expiring\n- Clear CTA: \"Claim this offer\" vs. \"Continue cancelling\"\n\nSee [references\u002Fcancel-flow-playbook.md](references\u002Fcancel-flow-playbook.md) for full decision trees and flow templates.\nSee [references\u002Fcancel-flow-patterns.md](references\u002Fcancel-flow-patterns.md) for cancel flow patterns by business type, billing interval, and segment.\n\n---\n\n## Involuntary Churn: Dunning Setup\n\nFailed payments cause 20-40% of total churn at most SaaS companies. Most of it is recoverable.\n\n### Recovery Stack\n\n**1. Smart Retry Logic**\nDon't retry immediately — failed cards often recover within 3-7 days:\n- Retry 1: 3 days after failure (most recoveries happen here)\n- Retry 2: 5 days after retry 1\n- Retry 3: 7 days after retry 2\n- Final: 3 days after retry 3, then cancel\n\n**2. Card Updater Services**\n- Stripe: Account Updater (automatic, enabled by default in most plans)\n- Braintree: Account Updater (must enable)\n- These update expired\u002Freplaced cards before the next charge — use them\n\n**3. Dunning Email Sequence**\n\n| Day | Email | Tone | CTA |\n|----|-------|------|-----|\n| Day 0 | \"Payment failed\" | Neutral, factual | Update card |\n| Day 3 | \"Action needed\" | Mild urgency | Update card |\n| Day 7 | \"Account at risk\" | Higher urgency | Update card |\n| Day 12 | \"Final notice\" | Urgent | Update card + support link |\n| Day 15 | \"Account paused\u002Fcancelled\" | Matter-of-fact | Reactivate |\n\n**Email rules:**\n- Subject lines: specific over vague (\"Your [Product] payment failed\" not \"Action required\")\n- No guilt. No shame. Card failures happen — treat customers like adults.\n- Every email links directly to the payment update page — not the dashboard\n\nSee [references\u002Fdunning-guide.md](references\u002Fdunning-guide.md) for full email sequences and retry configuration examples.\nSee [references\u002Fdunning-playbook.md](references\u002Fdunning-playbook.md) for advanced dunning strategies and payment recovery workflows.\n\n---\n\n## Metrics & Benchmarks\n\nTrack these weekly, review monthly:\n\n| Metric | Formula | Benchmark |\n|--------|---------|-----------|\n| **Save rate** | Customers saved \u002F cancel attempts | 10-15% good, 20%+ excellent |\n| **Voluntary churn rate** | Voluntary cancels \u002F total customers | \u003C2% monthly |\n| **Involuntary churn rate** | Failed payment cancels \u002F total customers | \u003C1% monthly |\n| **Recovery rate** | Failed payments recovered \u002F total failed | 25-35% good |\n| **Win-back rate** | Reactivations \u002F post-cancel 90 days | 5-10% |\n| **Exit survey completion** | Surveys completed \u002F cancel attempts | >80% |\n\n**Red flags:**\n- Save rate \u003C5% → offers aren't matching reasons\n- Exit survey completion \u003C70% → survey is too long or optional\n- Recovery rate \u003C20% → retry logic or emails need work\n\nUse the churn impact calculator to model what improving each metric is worth:\n\n```bash\npython3 scripts\u002Fchurn_impact_calculator.py\n```\n\n---\n\n## Proactive Triggers\n\nSurface these without being asked:\n\n- **Instant cancellation flow** → Revenue is leaking immediately. Any friction saves money — flag for priority fix.\n- **Single generic save offer** → A discount shown to everyone depresses average revenue and trains customers to wait for deals. Map offers to exit reasons.\n- **No dunning sequence** → If payment fails and nothing happens, that's 20-40% of churn going unaddressed. Flag immediately.\n- **Exit survey is optional** → \u003C70% completion = bad data. Make it required (one question, fast).\n- **No post-cancel reactivation email** → The 7-day window is the highest win-back moment. Missing it leaves money on the table.\n- **Churn rate >5% monthly** → At this rate, the company is likely contracting. Churn prevention alone won't fix it — flag for product\u002FICP review alongside retention work.\n\n---\n\n## Output Artifacts\n\n| When you ask for... | You get... |\n|--------------------|-----------|\n| \"Design a cancel flow\" | 5-stage flow diagram (text) with copy for each stage, save offer map, and confirmation email template |\n| \"Audit my cancel flow\" | Scorecard (0-100) with gaps, save rate benchmarks, and prioritized fixes |\n| \"Set up dunning\" | Retry schedule, 5-email sequence with subject lines and body copy, card updater setup checklist |\n| \"Design an exit survey\" | 6-8 reason categories with save offer mapping table |\n| \"Model churn impact\" | Run churn_impact_calculator.py with your inputs — monthly MRR saved and annual impact |\n| \"Write win-back emails\" | 2-email win-back sequence (7-day and 30-day) with subject lines |\n\n---\n\n## Communication\n\nAll output follows the structured communication standard:\n- **Bottom line first** — save rate estimate or recovery potential before methodology\n- **What + Why + How** — every recommendation has all three\n- **Actions have owners and deadlines** — no vague suggestions\n- **Confidence tagging** — ? verified benchmark \u002F ? estimated \u002F ? assumed\n\n",{"name":5,"license":14,"metadata":48,"description":7},{"author":49,"updated":50,"version":51,"category":38},"Alireza Rezvani",1772755200000,"1.0.0","main","a56eb2c0cba8a30e497cee4f4a4c79aa1f76aff0","skills\u002Fchurn-prevention","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw","https:\u002F\u002Fgithub.com\u002Fzhanghong3721","2026-10-10 09:01:14",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add zhanghong3721\u002Fkimiclaw --skill churn-prevention",{"tool":64,"command":65},"bunx","bunx skills add zhanghong3721\u002Fkimiclaw --skill churn-prevention",{"tool":67,"command":68},"pnpm","pnpm dlx skills add zhanghong3721\u002Fkimiclaw --skill churn-prevention","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002FSKILL.md",true,[72,77,83,87,91,95],{"path":73,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"LICENSE","许可证",1072,"https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002FLICENSE",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fcancel-flow-patterns.md","REFERENCE","参考文档",10708,"https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002Freferences\u002Fcancel-flow-patterns.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fcancel-flow-playbook.md",8573,"https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002Freferences\u002Fcancel-flow-playbook.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fdunning-guide.md",8652,"https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002Freferences\u002Fdunning-guide.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fdunning-playbook.md",12688,"https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002Freferences\u002Fdunning-playbook.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":89,"sourceHtmlUrl":99},"scripts\u002Fchurn_impact_calculator.py","SCRIPT","脚本","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Fchurn-prevention\u002Fscripts\u002Fchurn_impact_calculator.py",[101,126,137,160,191,209],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":43},"01M6XBCHSKGCQZ5B1R8S79WYT1","trap-detector","杀猪盘检测器。当用户提到\"朋友推荐\"、\"群里说\"、\"老师带\"、\"内幕消息\"、\"小红书 \u002F 抖音看到推荐\"等关键词，或显式要求\"看看是不是杀猪盘 \u002F 检测一下风险 \u002F 这只票安全吗\"时使用。扫描 8 个信号给出风险评级 ????。","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fworkspace\u002Fskills\u002Ftrap-detector\u002FSKILL.md",[],[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125],"trap detector","detector","risk","true","pump","小红书","红书","dump","deep","朋友","关键词","安全","analysis","fraud","fraud-detection","detection","finance","share",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":43},"01M6XBC4HSAJCESCRBR7WGEYZY","lhb-analyzer","龙虎榜深度分析器。识别游资席位、判断机构 vs 游资博弈、对照同板块龙虎榜找辨识度龙头。当用户问\"谁在买这只票\u002F最近龙虎榜怎么样\u002FX游资有没有上榜\u002F这是不是X的票\"时使用。","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fworkspace\u002Fskills\u002Flhb-analyzer\u002FSKILL.md",[],[133,134,125,124,111,116,135,136,120],"analyzer","lhb analyzer","money","Market",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":43},"01M6XBBR8Q3VFBQ92YBV234FZZ","investor-panel","50 位投资大佬评审团。给定一只股票的 dimensions.json 和 raw_data.json，让 50 位投资者各自按自己的方法论打分并输出 Pydantic Signal（signal\u002Fconfidence\u002Fscore\u002Fverdict\u002Fcomment）。覆盖经典价值派、成长投资派、宏观对冲派、技术趋势派、中国价投派、A股游资派、量化系统派 7 大流派。当用户请求\"评审团\u002F50 大佬怎么看\u002F某某会买吗\u002F做一次大佬投票\"时使用。","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fworkspace\u002Fskills\u002Finvestor-panel\u002FSKILL.md",[],[144,145,146,120,147,148,149,150,151,111,152,153,154,155,156,116,157,124,158,159],"investor panel","panel","value","json","voting","signal","verdict","role","投资","growth","A股","value-investing","investing","data","play","Pydantic",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":177,"publishedAt":43},"01M6XBA5DKX80512V794BVYVBM","deep-analysis","个股深度分析的核心工作流。当用户要求\"深度分析 \u002F 全面分析 \u002F 帮我看看 \u002F 值不值得买 \u002F DCF \u002F 机构建模 \u002F 首次覆盖 \u002F 投委会备忘录\"等涉及个股研究的请求时触发。覆盖 A 股、港股、美股，产出 22 维数据 + 51 位大佬量化评审 + 6 种机构级估值建模 (DCF\u002FComps\u002FLBO\u002F3-Stmt\u002FMerger) + 7 种研究产物 (首次覆盖\u002F财报解读\u002F催化剂日历\u002F投资逻辑追踪\u002F晨报\u002F量化筛选\u002F行业综述) + 6 种决策方法 (IC Memo\u002FDD\u002FPorter\u002F单位经济\u002FVCP\u002F再平衡) + 杀猪盘检测，最终生成 Bloomberg 风格 HTML 报告 + 社交分享战报。关键词：股票、个股、深度分析、估值、DCF、comps、首次覆盖、IC memo、杀猪盘、龙虎榜、akshare。","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fworkspace\u002Fskills\u002Fdeep-analysis\u002FSKILL.md",[166,169,172],{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":170,"categoryName":171,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":173,"categoryName":174,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[178,120,116,179,180,181,111,152,182,145,183,184,185,118,186,187,188,125,189,190],"deep analysis","merger","html","hong-kong","equity","ic memo","memo","dcf","生成","单位","kong","valuation","research",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":200,"publishedAt":43},"01M6XB9YHX4XC4PVM6D3XX06EX","amap-jsapi-skill","高德地图 JSAPI v2.0 (WebGL) 开发技能。涵盖地图生命周期管理、强制安全配置、3D 视图控制、覆盖物绘制及 LBS 服务集成。","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fworkspace\u002Fskills\u002Famap-jsapi-skill\u002FSKILL.md",[197],{"categoryNo":198,"categoryName":199,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000030","开发工程师",[201,202,119,203,204,205,206,207,208],"amap jsapi skill","amap","3D","https","webgl","node","高德","地图",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":213,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":43},"01M6XB9JQD67BJR8AFWR65R6K2","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzhanghong3721\u002Fkimiclaw\u002Fblob\u002Fmain\u002Fskills\u002Ftheme-factory\u002FSKILL.md",[216],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237],"theme","theme factory","factory","themes","apply","for","can","fonts","you","with","pages","artifact","styling","landing","slides","fly","SET","artifacts","generate","toolkit"]