[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EMSWNXFEKXVPH21565WAS7":3,"skill-same:01M6EMSWNXFEKXVPH21565WAS7":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M6EMSWNXFEKXVPH21565WAS7","reasoning-abductive",null,"Generate and evaluate explanatory hypotheses from incomplete observations. Use when diagnosing anomalies, explaining unexpected outcomes, or inferring causes from effects. Produces ranked hypotheses with evidence and confidence scores.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbellabe\u002Freasoning-abductive\u002FSKILL.md",[],[19,20,21,22,23,24],"reasoning","reasoning abductive","generate","use","outcomes","evidence","2026-11-10 10:12:30",false,"---\nname: reasoning-abductive\ndescription: Generate and evaluate explanatory hypotheses from incomplete observations. Use when diagnosing anomalies, explaining unexpected outcomes, or inferring causes from effects. Produces ranked hypotheses with evidence and confidence scores.\n---\n\n# Abductive Reasoning\n\nGenerate best explanations from observations. The logic of diagnosis and inference to cause.\n\n## Type Signature\n\n```\nAbductive : Observation → Hypotheses[] → Evidence → BestExplanation\n\nWhere:\n  Observation     : RawData × Surprise → AnomalyDescription\n  Hypotheses      : AnomalyDescription → [PossibleCause]\n  Evidence        : [PossibleCause] × AvailableData → [ScoredHypothesis]\n  BestExplanation : [ScoredHypothesis] → (Cause × Confidence × NextSteps)\n```\n\n## When to Use\n\n**Use abductive when:**\n- Anomaly or surprise present (metric deviation, unexpected behavior)\n- Need to explain an observation (why did X happen?)\n- Incomplete data, must infer cause\n- Diagnostic context (errors, issues, failures)\n- Multiple possible explanations exist\n\n**Don't use when:**\n- Cause is already known (use causal execution instead)\n- Need to compare decision alternatives\n- Resolving stakeholder disagreements\n\n## Four-Stage Process\n\n### Stage 1: Observation\n\n**Purpose:** Transform raw data into structured anomaly description.\n\n**Input:**\n```yaml\nobservation:\n  raw_data: \"Conversion dropped from 12% to 7% in Q4\"\n  context:\n    timeframe: \"Q4 2025\"\n    baseline: \"12% historical average\"\n    current: \"7% observed\"\n  surprise_level: 0.8  # How unexpected is this?\n```\n\n**Process:**\n1. Quantify the deviation (% change, sigma from mean)\n2. Identify temporal boundaries (when did it start?)\n3. Scope the phenomenon (which segments affected?)\n4. Rate surprise level (expected vs unexpected)\n\n**Output:**\n```yaml\nanomaly:\n  description: \"42% drop in conversion rate (12% → 7%)\"\n  deviation: \"-5 percentage points, -42% relative\"\n  temporal: \"Started week 3 of Q4, persists through Q4\"\n  scope: \"All segments equally affected\"\n  surprise: 0.8\n  baseline_source: \"12-month rolling average\"\n```\n\n### Stage 2: Hypotheses Generation\n\n**Purpose:** Generate diverse possible explanations without judgment.\n\n**Rules:**\n- Generate ≥5 hypotheses (more is better initially)\n- Include obvious AND non-obvious causes\n- Consider internal AND external factors\n- Don't filter yet - cast wide net\n\n**Hypothesis Categories:**\n\n| Category | Examples |\n|----------|----------|\n| **Technical** | Site issues, bugs, performance |\n| **Product** | Features, pricing, positioning |\n| **Market** | Competition, trends, seasonality |\n| **Operational** | Team changes, process issues |\n| **External** | Economy, regulations, events |\n\n**Output:**\n```yaml\nhypotheses:\n  - id: H1\n    cause: \"Website performance degradation\"\n    category: technical\n    mechanism: \"Slow load times → abandonment\"\n    \n  - id: H2\n    cause: \"Competitor launched aggressive pricing\"\n    category: market\n    mechanism: \"Price undercut → customer diversion\"\n    \n  - id: H3\n    cause: \"Seasonal Q4 shopping behavior change\"\n    category: market\n    mechanism: \"Holiday spending patterns differ\"\n    \n  - id: H4\n    cause: \"Product-market fit weakening\"\n    category: product\n    mechanism: \"Customer needs evolving away\"\n    \n  - id: H5\n    cause: \"Sales qualification criteria changed\"\n    category: operational\n    mechanism: \"Different lead quality entering funnel\"\n    \n  # ... continue until exhaustive\n```\n\n### Stage 3: Evidence Evaluation\n\n**Purpose:** Score each hypothesis against available evidence.\n\n**For each hypothesis, evaluate:**\n\n| Criterion | Question | Score |\n|-----------|----------|-------|\n| **Explanatory power** | Does it fully explain the anomaly? | 0-1 |\n| **Simplicity** | Fewest assumptions required? | 0-1 |\n| **Coherence** | Consistent with other known facts? | 0-1 |\n| **Testability** | Can we verify\u002Ffalsify it? | 0-1 |\n| **Prior probability** | How likely independent of this data? | 0-1 |\n\n**Evidence Collection:**\n```yaml\nevidence:\n  H1_technical:\n    supporting:\n      - \"Page load time increased 2s in Q4\" (confidence: 0.9)\n      - \"Mobile bounce rate up 15%\" (confidence: 0.85)\n    contradicting:\n      - \"Desktop conversion stable\" (confidence: 0.8)\n    net_score: 0.65\n    \n  H2_competitor:\n    supporting:\n      - \"Competitor launched Oct 15\" (confidence: 1.0)\n      - \"Google Trends shows competitor interest up\" (confidence: 0.7)\n    contradicting:\n      - \"Our traffic unchanged\" (confidence: 0.9)\n    net_score: 0.55\n    \n  # ... evaluate all hypotheses\n```\n\n**Scoring Formula:**\n```\nScore(H) = (Explanatory × 0.3) + (Simplicity × 0.2) + \n           (Coherence × 0.25) + (Testability × 0.1) + \n           (Prior × 0.15)\n```\n\n### Stage 4: Best Explanation\n\n**Purpose:** Select most probable cause with confidence and next steps.\n\n**Ranking:**\n```yaml\nranked_hypotheses:\n  - rank: 1\n    hypothesis: H1\n    cause: \"Website performance degradation\"\n    score: 0.78\n    confidence: 0.75\n    \n  - rank: 2\n    hypothesis: H3\n    cause: \"Seasonal behavior change\"\n    score: 0.62\n    confidence: 0.60\n    \n  - rank: 3\n    hypothesis: H2\n    cause: \"Competitor pricing\"\n    score: 0.55\n    confidence: 0.50\n```\n\n**Best Explanation Output:**\n```yaml\nconclusion:\n  primary_cause: \"Website performance degradation\"\n  confidence: 0.75\n  mechanism: \"2s increase in load time caused 42% more abandonment, \n              consistent with industry benchmarks (1s = ~7% conversion loss)\"\n  \n  contributing_factors:\n    - \"Seasonal patterns may account for 10-15% of drop\"\n    \n  ruled_out:\n    - \"Competitor pricing (traffic unchanged, not price-sensitive segment)\"\n    \n  remaining_uncertainty:\n    - \"Whether mobile-specific or site-wide\"\n    - \"Whether fix will fully restore conversion\"\n    \n  next_steps:\n    - \"Verify: Run A\u002FB test with performance fix (high priority)\"\n    - \"Measure: Mobile vs desktop split post-fix\"\n    - \"Monitor: Competitor activity (low priority)\"\n    \n  suggested_next_mode: causal  # Ready to act on diagnosis\n```\n\n## Quality Gates\n\n| Gate | Requirement | Failure Action |\n|------|-------------|----------------|\n| Hypothesis count | ≥5 hypotheses | Generate more before proceeding |\n| Category diversity | ≥3 categories | Expand hypothesis search |\n| Evidence present | ≥1 data point per top-3 | Gather more evidence |\n| Confidence threshold | ≥0.6 for best | Flag as inconclusive |\n| Testability | Best hypothesis testable | Propose test design |\n\n## Common Failure Modes\n\n| Failure | Symptom | Fix |\n|---------|---------|-----|\n| **Anchoring** | First hypothesis gets all attention | Force diversity in Stage 2 |\n| **Confirmation bias** | Only seek supporting evidence | Require contradicting evidence |\n| **Complexity creep** | Elaborate explanations preferred | Weight simplicity appropriately |\n| **Premature closure** | Stop at first plausible cause | Complete all 4 stages |\n\n## Output Contract\n\n```yaml\nabductive_output:\n  conclusion:\n    primary_cause: string\n    confidence: float  # 0.0-1.0\n    mechanism: string  # How cause produces effect\n    \n  hypotheses:\n    ranked: [ScoredHypothesis]  # All evaluated\n    ruled_out: [string]         # Definitively excluded\n    \n  evidence:\n    supporting: [EvidenceItem]\n    contradicting: [EvidenceItem]\n    gaps: [string]  # What evidence is missing?\n    \n  uncertainty:\n    remaining_questions: [string]\n    confidence_bounds: [float, float]  # Low, high\n    \n  next:\n    immediate_actions: [string]\n    tests_to_run: [string]\n    suggested_mode: optional\u003CReasoningMode>\n    \n  trace:\n    stages_completed: [1, 2, 3, 4]\n    duration_ms: int\n    hypotheses_generated: int\n    evidence_points: int\n```\n\n## Example Execution\n\n**Context:** \"Enterprise conversion dropped 40% last quarter\"\n\n**Stage 1 - Observation:**\n```\nAnomaly: 40% drop (15% → 9%) in enterprise conversion\nTemporal: Started week 5 of Q3, accelerated Q4\nScope: Enterprise only, SMB stable\nSurprise: 0.85\n```\n\n**Stage 2 - Hypotheses:**\n```\nH1: Enterprise buyer behavior changed (economic uncertainty)\nH2: Sales team restructuring disrupted relationships\nH3: Competitor launched enterprise-specific offering\nH4: Our enterprise pricing became uncompetitive\nH5: Product gaps for enterprise use cases\nH6: Longer sales cycles (not drop, just delay)\nH7: Key account manager departures\n```\n\n**Stage 3 - Evidence:**\n```\nH1: Supporting (CFO involvement up 40%), Contradicting (overall enterprise IT spend flat)\nH2: Supporting (3 senior reps left Q3), Contradicting (coverage maintained)\nH6: Supporting (average cycle +45 days), Strong supporting\nH7: Supporting (2 key AMs left), Moderate supporting\n```\n\n**Stage 4 - Conclusion:**\n```\nPrimary: Sales cycle elongation (not true drop) + AM departures (relationship gaps)\nConfidence: 0.72\nMechanism: Economic uncertainty extended CFO approval cycles by 45 days;\n           AM departures created relationship gaps in 6 key accounts\n\nNext: Wait 45 days to see if \"delayed\" deals close (causal monitoring)\n      Immediately backfill AM roles (causal action)\n```\n","# Abductive Reasoning\n\nGenerate best explanations from observations. The logic of diagnosis and inference to cause.\n\n## Type Signature\n\n```\nAbductive : Observation → Hypotheses[] → Evidence → BestExplanation\n\nWhere:\n  Observation     : RawData × Surprise → AnomalyDescription\n  Hypotheses      : AnomalyDescription → [PossibleCause]\n  Evidence        : [PossibleCause] × AvailableData → [ScoredHypothesis]\n  BestExplanation : [ScoredHypothesis] → (Cause × Confidence × NextSteps)\n```\n\n## When to Use\n\n**Use abductive when:**\n- Anomaly or surprise present (metric deviation, unexpected behavior)\n- Need to explain an observation (why did X happen?)\n- Incomplete data, must infer cause\n- Diagnostic context (errors, issues, failures)\n- Multiple possible explanations exist\n\n**Don't use when:**\n- Cause is already known (use causal execution instead)\n- Need to compare decision alternatives\n- Resolving stakeholder disagreements\n\n## Four-Stage Process\n\n### Stage 1: Observation\n\n**Purpose:** Transform raw data into structured anomaly description.\n\n**Input:**\n```yaml\nobservation:\n  raw_data: \"Conversion dropped from 12% to 7% in Q4\"\n  context:\n    timeframe: \"Q4 2025\"\n    baseline: \"12% historical average\"\n    current: \"7% observed\"\n  surprise_level: 0.8  # How unexpected is this?\n```\n\n**Process:**\n1. Quantify the deviation (% change, sigma from mean)\n2. Identify temporal boundaries (when did it start?)\n3. Scope the phenomenon (which segments affected?)\n4. Rate surprise level (expected vs unexpected)\n\n**Output:**\n```yaml\nanomaly:\n  description: \"42% drop in conversion rate (12% → 7%)\"\n  deviation: \"-5 percentage points, -42% relative\"\n  temporal: \"Started week 3 of Q4, persists through Q4\"\n  scope: \"All segments equally affected\"\n  surprise: 0.8\n  baseline_source: \"12-month rolling average\"\n```\n\n### Stage 2: Hypotheses Generation\n\n**Purpose:** Generate diverse possible explanations without judgment.\n\n**Rules:**\n- Generate ≥5 hypotheses (more is better initially)\n- Include obvious AND non-obvious causes\n- Consider internal AND external factors\n- Don't filter yet - cast wide net\n\n**Hypothesis Categories:**\n\n| Category | Examples |\n|----------|----------|\n| **Technical** | Site issues, bugs, performance |\n| **Product** | Features, pricing, positioning |\n| **Market** | Competition, trends, seasonality |\n| **Operational** | Team changes, process issues |\n| **External** | Economy, regulations, events |\n\n**Output:**\n```yaml\nhypotheses:\n  - id: H1\n    cause: \"Website performance degradation\"\n    category: technical\n    mechanism: \"Slow load times → abandonment\"\n    \n  - id: H2\n    cause: \"Competitor launched aggressive pricing\"\n    category: market\n    mechanism: \"Price undercut → customer diversion\"\n    \n  - id: H3\n    cause: \"Seasonal Q4 shopping behavior change\"\n    category: market\n    mechanism: \"Holiday spending patterns differ\"\n    \n  - id: H4\n    cause: \"Product-market fit weakening\"\n    category: product\n    mechanism: \"Customer needs evolving away\"\n    \n  - id: H5\n    cause: \"Sales qualification criteria changed\"\n    category: operational\n    mechanism: \"Different lead quality entering funnel\"\n    \n  # ... continue until exhaustive\n```\n\n### Stage 3: Evidence Evaluation\n\n**Purpose:** Score each hypothesis against available evidence.\n\n**For each hypothesis, evaluate:**\n\n| Criterion | Question | Score |\n|-----------|----------|-------|\n| **Explanatory power** | Does it fully explain the anomaly? | 0-1 |\n| **Simplicity** | Fewest assumptions required? | 0-1 |\n| **Coherence** | Consistent with other known facts? | 0-1 |\n| **Testability** | Can we verify\u002Ffalsify it? | 0-1 |\n| **Prior probability** | How likely independent of this data? | 0-1 |\n\n**Evidence Collection:**\n```yaml\nevidence:\n  H1_technical:\n    supporting:\n      - \"Page load time increased 2s in Q4\" (confidence: 0.9)\n      - \"Mobile bounce rate up 15%\" (confidence: 0.85)\n    contradicting:\n      - \"Desktop conversion stable\" (confidence: 0.8)\n    net_score: 0.65\n    \n  H2_competitor:\n    supporting:\n      - \"Competitor launched Oct 15\" (confidence: 1.0)\n      - \"Google Trends shows competitor interest up\" (confidence: 0.7)\n    contradicting:\n      - \"Our traffic unchanged\" (confidence: 0.9)\n    net_score: 0.55\n    \n  # ... evaluate all hypotheses\n```\n\n**Scoring Formula:**\n```\nScore(H) = (Explanatory × 0.3) + (Simplicity × 0.2) + \n           (Coherence × 0.25) + (Testability × 0.1) + \n           (Prior × 0.15)\n```\n\n### Stage 4: Best Explanation\n\n**Purpose:** Select most probable cause with confidence and next steps.\n\n**Ranking:**\n```yaml\nranked_hypotheses:\n  - rank: 1\n    hypothesis: H1\n    cause: \"Website performance degradation\"\n    score: 0.78\n    confidence: 0.75\n    \n  - rank: 2\n    hypothesis: H3\n    cause: \"Seasonal behavior change\"\n    score: 0.62\n    confidence: 0.60\n    \n  - rank: 3\n    hypothesis: H2\n    cause: \"Competitor pricing\"\n    score: 0.55\n    confidence: 0.50\n```\n\n**Best Explanation Output:**\n```yaml\nconclusion:\n  primary_cause: \"Website performance degradation\"\n  confidence: 0.75\n  mechanism: \"2s increase in load time caused 42% more abandonment, \n              consistent with industry benchmarks (1s = ~7% conversion loss)\"\n  \n  contributing_factors:\n    - \"Seasonal patterns may account for 10-15% of drop\"\n    \n  ruled_out:\n    - \"Competitor pricing (traffic unchanged, not price-sensitive segment)\"\n    \n  remaining_uncertainty:\n    - \"Whether mobile-specific or site-wide\"\n    - \"Whether fix will fully restore conversion\"\n    \n  next_steps:\n    - \"Verify: Run A\u002FB test with performance fix (high priority)\"\n    - \"Measure: Mobile vs desktop split post-fix\"\n    - \"Monitor: Competitor activity (low priority)\"\n    \n  suggested_next_mode: causal  # Ready to act on diagnosis\n```\n\n## Quality Gates\n\n| Gate | Requirement | Failure Action |\n|------|-------------|----------------|\n| Hypothesis count | ≥5 hypotheses | Generate more before proceeding |\n| Category diversity | ≥3 categories | Expand hypothesis search |\n| Evidence present | ≥1 data point per top-3 | Gather more evidence |\n| Confidence threshold | ≥0.6 for best | Flag as inconclusive |\n| Testability | Best hypothesis testable | Propose test design |\n\n## Common Failure Modes\n\n| Failure | Symptom | Fix |\n|---------|---------|-----|\n| **Anchoring** | First hypothesis gets all attention | Force diversity in Stage 2 |\n| **Confirmation bias** | Only seek supporting evidence | Require contradicting evidence |\n| **Complexity creep** | Elaborate explanations preferred | Weight simplicity appropriately |\n| **Premature closure** | Stop at first plausible cause | Complete all 4 stages |\n\n## Output Contract\n\n```yaml\nabductive_output:\n  conclusion:\n    primary_cause: string\n    confidence: float  # 0.0-1.0\n    mechanism: string  # How cause produces effect\n    \n  hypotheses:\n    ranked: [ScoredHypothesis]  # All evaluated\n    ruled_out: [string]         # Definitively excluded\n    \n  evidence:\n    supporting: [EvidenceItem]\n    contradicting: [EvidenceItem]\n    gaps: [string]  # What evidence is missing?\n    \n  uncertainty:\n    remaining_questions: [string]\n    confidence_bounds: [float, float]  # Low, high\n    \n  next:\n    immediate_actions: [string]\n    tests_to_run: [string]\n    suggested_mode: optional\u003CReasoningMode>\n    \n  trace:\n    stages_completed: [1, 2, 3, 4]\n    duration_ms: int\n    hypotheses_generated: int\n    evidence_points: int\n```\n\n## Example Execution\n\n**Context:** \"Enterprise conversion dropped 40% last quarter\"\n\n**Stage 1 - Observation:**\n```\nAnomaly: 40% drop (15% → 9%) in enterprise conversion\nTemporal: Started week 5 of Q3, accelerated Q4\nScope: Enterprise only, SMB stable\nSurprise: 0.85\n```\n\n**Stage 2 - Hypotheses:**\n```\nH1: Enterprise buyer behavior changed (economic uncertainty)\nH2: Sales team restructuring disrupted relationships\nH3: Competitor launched enterprise-specific offering\nH4: Our enterprise pricing became uncompetitive\nH5: Product gaps for enterprise use cases\nH6: Longer sales cycles (not drop, just delay)\nH7: Key account manager departures\n```\n\n**Stage 3 - Evidence:**\n```\nH1: Supporting (CFO involvement up 40%), Contradicting (overall enterprise IT spend flat)\nH2: Supporting (3 senior reps left Q3), Contradicting (coverage maintained)\nH6: Supporting (average cycle +45 days), Strong supporting\nH7: Supporting (2 key AMs left), Moderate supporting\n```\n\n**Stage 4 - Conclusion:**\n```\nPrimary: Sales cycle elongation (not true drop) + AM departures (relationship gaps)\nConfidence: 0.72\nMechanism: Economic uncertainty extended CFO approval cycles by 45 days;\n           AM departures created relationship gaps in 6 key accounts\n\nNext: Wait 45 days to see if \"delayed\" deals close (causal monitoring)\n      Immediately backfill AM roles (causal action)\n```\n",{"name":5,"description":7},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fbellabe\u002Freasoning-abductive",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill reasoning-abductive",{"tool":45,"command":46},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill reasoning-abductive",{"tool":48,"command":49},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill reasoning-abductive","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbellabe\u002Freasoning-abductive\u002FSKILL.md",true,[53],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"skill-report.json","REFERENCE","参考文档",11583,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbellabe\u002Freasoning-abductive\u002Fskill-report.json",[60,74,84,93,99,106],{"skillNo":61,"name":62,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":70,"publishedAt":25},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[65],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[71,72,73],"model","model hierarchy","model hierarchy skill",{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":25},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[79],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[81,82,83],"MCP","zoom","zoom mcp",{"skillNo":85,"name":86,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":25},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[90,91,92,82],"sdk","zoom apps sdk","apps",{"skillNo":94,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":25},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[95],{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":25},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[104],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[101],{"skillNo":107,"name":108,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":25},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[108]]