[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DM7QJYDP9Y3Y00CM419CGY":3,"skill-same:01M7DM7QJYDP9Y3Y00CM419CGY":46},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7DM7QJYDP9Y3Y00CM419CGY","intent-taxonomy-builder",null,"Methodology for systematically designing a chatbot's intent classification taxonomy. Use this skill for 'intent taxonomy design', 'intent system', 'NLU intent list', 'entity dictionary', 'slot design', and other chatbot intent classification taxonomy design tasks. Note: actual NLU model training and cloud NLU service deployment are outside the scope of this skill.","danielnguyenfinhub\u002Ffinhub-harness","danielnguyenfinhub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264356854?v=4","01M7DM55XETDR9HF92FWC28SBN","Daniel Nguyen","01M7DM55YGJYBWW488JZSQYEJ4",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Fpacks\u002Ffinhub-ops-pack\u002Fskills\u002Fintent-taxonomy-builder\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: intent-taxonomy-builder\ndescription: \"Methodology for systematically designing a chatbot's intent classification taxonomy. Use this skill for 'intent taxonomy design', 'intent system', 'NLU intent list', 'entity dictionary', 'slot design', and other chatbot intent classification taxonomy design tasks. Note: actual NLU model training and cloud NLU service deployment are outside the scope of this skill.\"\n---\n\n# Intent Taxonomy Builder — Intent Classification Taxonomy Design Methodology\n\nA skill that enhances intent classification design for the nlu-developer and conversation-designer.\n\n## Target Agents\n\n- **nlu-developer** — Used when designing intent\u002Fentity\u002Fslot systems\n- **conversation-designer** — Used when mapping conversation scenarios to intents\n\n## Intent Classification Taxonomy Design Framework\n\n### Step 1: Domain Intent Collection\n\n```\nCollect user utterances > Group > Derive intent candidates\n\nCollection sources:\n- Existing FAQ documents\n- Customer service inquiry logs\n- Competitor chatbot analysis\n- User interviews\u002Fsurveys\n- Domain expert brainstorming\n```\n\n### Step 2: Intent Hierarchy\n\n```\nLevel 0 (Domain)\n├── Level 1 (Category)\n│   ├── Level 2 (Specific intent)\n│   └── Level 2\n└── Level 1\n    └── Level 2\n\nExample (E-commerce):\ncommerce\n├── order\n│   ├── order.place — \"I want to place an order\"\n│   ├── order.status — \"Check my order status\"\n│   ├── order.cancel — \"Cancel my order\"\n│   └── order.modify — \"I want to change my order\"\n├── product\n│   ├── product.search — \"Do you have this kind of product?\"\n│   ├── product.detail — \"Details about this product\"\n│   └── product.compare — \"Compare these two products\"\n├── payment\n│   ├── payment.method — \"What payment methods are available?\"\n│   ├── payment.refund — \"Refund request\"\n│   └── payment.receipt — \"Issue a receipt\"\n└── general\n    ├── general.greeting — \"Hello\"\n    ├── general.goodbye — \"Thank you\"\n    └── general.fallback — (unrecognized)\n```\n\n### Step 3: Intent Quality Checklist\n\n| Criterion | Description | Pass Condition |\n|-----------|------------|----------------|\n| Mutual exclusivity | No overlap between intents | 1 utterance = 1 intent |\n| Completeness | Covers all user scenarios | fallback \u003C 10% |\n| Balance | Even training data per intent | Minimum 20 utterances\u002Fintent |\n| Clarity | Purpose clear from name alone | `verb.noun` format |\n| Appropriate count | Manageable range | 20-50 (small-scale), 50-150 (large-scale) |\n\n## Entity Design Methodology\n\n### Entity Types\n\n| Type | Description | Examples |\n|------|------------|---------|\n| System entity | Platform built-in | @sys.date, @sys.number, @sys.email |\n| Dictionary entity | Domain fixed list | Menu items, sizes, colors |\n| Pattern entity | Regex-based | Order number (`ORD-\\d{8}`), phone number |\n| Composite entity | Entity combinations | Address (city+district+street), date range |\n\n### Entity-Slot Mapping\n\n```\nIntent: order.place\nRequired slots:\n  - product_name (@product) — \"Americano\"\n  - quantity (@sys.number) — \"two\"\nOptional slots:\n  - size (@size) — \"tall size\"\n  - option (@option) — \"less ice\"\n  - takeout (@boolean) — \"to go\"\n\nWhen slot is unfilled > Prompt:\n  - product_name missing: \"What would you like to order?\"\n  - quantity missing: \"How many would you like?\"\n```\n\n## Training Data Generation Guide\n\n### Utterance Variation Patterns\n\n```\nOriginal: \"I want to cancel my order\"\n\nVariation strategies:\n1. Ending variation: \"Please cancel\", \"Cancel this\", \"I'd like to cancel please\"\n2. Expression substitution: \"Revoke order\", \"Undo order\", \"I don't want my order anymore\"\n3. Context addition: \"Cancel the order I just placed\", \"Cancel what I ordered earlier\"\n4. Typos\u002Fabbreviations: \"cancle order\", \"cancel plz\", \"cxl\"\n5. Indirect expression: \"I don't want to receive my order\", \"I changed my mind\"\n6. With entity: \"Cancel ORD-12345678\"\n```\n\n### Utterance Count Guide\n\n| Intent Complexity | Minimum Utterances | Recommended Utterances |\n|------------------|-------------------|----------------------|\n| Simple (greeting\u002Fgoodbye) | 10 | 20 |\n| Medium (lookup\u002Fconfirmation) | 20 | 50 |\n| Complex (order\u002Fmodification) | 30 | 80 |\n| Easily confused (similar intents) | 50 | 100+ |\n\n## Intent Confusion Matrix Analysis\n\n```\nHigh-confusion pair examples:\n- order.cancel \u003C> payment.refund (cancel vs refund)\n- product.search \u003C> product.detail (search vs detail)\n- order.modify \u003C> order.cancel (modify vs cancel)\n\nResolution strategies:\n1. Add distinguishing utterances (strengthen unique keywords for each intent)\n2. Merge intents (when distinction is unnecessary)\n3. Context-dependent separation (based on dialog state)\n4. Clarifying question (\"Do you want to cancel or get a refund?\")\n```\n\n## Deliverable Template\n\n```yaml\nintent_taxonomy:\n  - intent: order.place\n    description: \"Place a new order\"\n    examples:\n      - \"I'd like to order two Americanos\"\n      - \"I want to order this\"\n    required_slots:\n      - name: product_name\n        entity: \"@product\"\n        prompt: \"What would you like to order?\"\n    optional_slots:\n      - name: quantity\n        entity: \"@sys.number\"\n        default: 1\n    responses:\n      success: \"Your order for {quantity} {product_name}(s) has been placed.\"\n      slot_missing: \"Please tell me what you'd like to order.\"\n```\n","# Intent Taxonomy Builder — Intent Classification Taxonomy Design Methodology\n\nA skill that enhances intent classification design for the nlu-developer and conversation-designer.\n\n## Target Agents\n\n- **nlu-developer** — Used when designing intent\u002Fentity\u002Fslot systems\n- **conversation-designer** — Used when mapping conversation scenarios to intents\n\n## Intent Classification Taxonomy Design Framework\n\n### Step 1: Domain Intent Collection\n\n```\nCollect user utterances > Group > Derive intent candidates\n\nCollection sources:\n- Existing FAQ documents\n- Customer service inquiry logs\n- Competitor chatbot analysis\n- User interviews\u002Fsurveys\n- Domain expert brainstorming\n```\n\n### Step 2: Intent Hierarchy\n\n```\nLevel 0 (Domain)\n├── Level 1 (Category)\n│   ├── Level 2 (Specific intent)\n│   └── Level 2\n└── Level 1\n    └── Level 2\n\nExample (E-commerce):\ncommerce\n├── order\n│   ├── order.place — \"I want to place an order\"\n│   ├── order.status — \"Check my order status\"\n│   ├── order.cancel — \"Cancel my order\"\n│   └── order.modify — \"I want to change my order\"\n├── product\n│   ├── product.search — \"Do you have this kind of product?\"\n│   ├── product.detail — \"Details about this product\"\n│   └── product.compare — \"Compare these two products\"\n├── payment\n│   ├── payment.method — \"What payment methods are available?\"\n│   ├── payment.refund — \"Refund request\"\n│   └── payment.receipt — \"Issue a receipt\"\n└── general\n    ├── general.greeting — \"Hello\"\n    ├── general.goodbye — \"Thank you\"\n    └── general.fallback — (unrecognized)\n```\n\n### Step 3: Intent Quality Checklist\n\n| Criterion | Description | Pass Condition |\n|-----------|------------|----------------|\n| Mutual exclusivity | No overlap between intents | 1 utterance = 1 intent |\n| Completeness | Covers all user scenarios | fallback \u003C 10% |\n| Balance | Even training data per intent | Minimum 20 utterances\u002Fintent |\n| Clarity | Purpose clear from name alone | `verb.noun` format |\n| Appropriate count | Manageable range | 20-50 (small-scale), 50-150 (large-scale) |\n\n## Entity Design Methodology\n\n### Entity Types\n\n| Type | Description | Examples |\n|------|------------|---------|\n| System entity | Platform built-in | @sys.date, @sys.number, @sys.email |\n| Dictionary entity | Domain fixed list | Menu items, sizes, colors |\n| Pattern entity | Regex-based | Order number (`ORD-\\d{8}`), phone number |\n| Composite entity | Entity combinations | Address (city+district+street), date range |\n\n### Entity-Slot Mapping\n\n```\nIntent: order.place\nRequired slots:\n  - product_name (@product) — \"Americano\"\n  - quantity (@sys.number) — \"two\"\nOptional slots:\n  - size (@size) — \"tall size\"\n  - option (@option) — \"less ice\"\n  - takeout (@boolean) — \"to go\"\n\nWhen slot is unfilled > Prompt:\n  - product_name missing: \"What would you like to order?\"\n  - quantity missing: \"How many would you like?\"\n```\n\n## Training Data Generation Guide\n\n### Utterance Variation Patterns\n\n```\nOriginal: \"I want to cancel my order\"\n\nVariation strategies:\n1. Ending variation: \"Please cancel\", \"Cancel this\", \"I'd like to cancel please\"\n2. Expression substitution: \"Revoke order\", \"Undo order\", \"I don't want my order anymore\"\n3. Context addition: \"Cancel the order I just placed\", \"Cancel what I ordered earlier\"\n4. Typos\u002Fabbreviations: \"cancle order\", \"cancel plz\", \"cxl\"\n5. Indirect expression: \"I don't want to receive my order\", \"I changed my mind\"\n6. With entity: \"Cancel ORD-12345678\"\n```\n\n### Utterance Count Guide\n\n| Intent Complexity | Minimum Utterances | Recommended Utterances |\n|------------------|-------------------|----------------------|\n| Simple (greeting\u002Fgoodbye) | 10 | 20 |\n| Medium (lookup\u002Fconfirmation) | 20 | 50 |\n| Complex (order\u002Fmodification) | 30 | 80 |\n| Easily confused (similar intents) | 50 | 100+ |\n\n## Intent Confusion Matrix Analysis\n\n```\nHigh-confusion pair examples:\n- order.cancel \u003C> payment.refund (cancel vs refund)\n- product.search \u003C> product.detail (search vs detail)\n- order.modify \u003C> order.cancel (modify vs cancel)\n\nResolution strategies:\n1. Add distinguishing utterances (strengthen unique keywords for each intent)\n2. Merge intents (when distinction is unnecessary)\n3. Context-dependent separation (based on dialog state)\n4. Clarifying question (\"Do you want to cancel or get a refund?\")\n```\n\n## Deliverable Template\n\n```yaml\nintent_taxonomy:\n  - intent: order.place\n    description: \"Place a new order\"\n    examples:\n      - \"I'd like to order two Americanos\"\n      - \"I want to order this\"\n    required_slots:\n      - name: product_name\n        entity: \"@product\"\n        prompt: \"What would you like to order?\"\n    optional_slots:\n      - name: quantity\n        entity: \"@sys.number\"\n        default: 1\n    responses:\n      success: \"Your order for {quantity} {product_name}(s) has been placed.\"\n      slot_missing: \"Please tell me what you'd like to order.\"\n```\n",{"name":5,"description":7},"main","dda161ff9daf0d9bccbdba26e34bbee0438a18b0","packs\u002Ffinhub-ops-pack\u002Fskills\u002Fintent-taxonomy-builder",0,"https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub","www.finhub.net.au","2026-11-12 17:07:32",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add danielnguyenfinhub\u002Ffinhub-harness --skill intent-taxonomy-builder",{"tool":38,"command":39},"bunx","bunx skills add danielnguyenfinhub\u002Ffinhub-harness --skill intent-taxonomy-builder",{"tool":41,"command":42},"pnpm","pnpm dlx skills add danielnguyenfinhub\u002Ffinhub-harness --skill intent-taxonomy-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Fpacks\u002Ffinhub-ops-pack\u002Fskills\u002Fintent-taxonomy-builder\u002FSKILL.md",true,[],[47,54,61,67,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7DMBP1MQ9X39BGJ9VF62M9P","linky","Fixture whose links and bundled-file mentions all resolve. Use to prove no false errors.","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_links_ok\u002Fskills\u002Flinky\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7DMBK70KXF6A3V1VDRHYGVT","dup-one","Second owner of the name. Use for the duplicate fixture.","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_links_bad\u002Fskills\u002Fdup-two\u002FSKILL.md",[],[],{"skillNo":62,"name":56,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DMBFWK8HD4AWNK89KGE89P","First owner of the name. Use for the duplicate fixture.","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_links_bad\u002Fskills\u002Fdup-one\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"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":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DMBETX7172TFNBAA3BVREQ","nested","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_links_bad\u002Fskills\u002Fbroken\u002Fnested\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"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":79,"publishedAt":19},"01M7DMBDCH5G61QVAB1QFMQA55","broken","Fixture with one defect per rule. Use to prove each rule fires.","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_links_bad\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DMBAQHY0Z2PTYGCPM8H7MT","notes-style","House style for client notes. Use when writing or editing a client note.","https:\u002F\u002Fgithub.com\u002Fdanielnguyenfinhub\u002Ffinhub-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fharness_good\u002Fskills\u002Fnotes-style\u002FSKILL.md",[],[]]