[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J4AXCCKD4Z1FFC9SR2QDZ6":3,"skill-same:01M6J4AXCCKD4Z1FFC9SR2QDZ6":97},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6J4AXCCKD4Z1FFC9SR2QDZ6","mk-decision-framework",null,"Operational decision frameworks: triage, escalation, case management, billing ops. Use for 'how to handle X cases', 'build triage', 'escalation protocol'.","ngocsangyem\u002FMeowKit","ngocsangyem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33769536?v=4","01M6J3FSMJAG9PVQEGRT7AQ9J2","Sang Nguyen","01M6J3FSRTJG0MNP6NV71639RM",16,"MIT","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"framework","decision","mk decision framework","triage","protocol","escalation","how","management","ops","use","build","frameworks","how to","case","billing","for","2026-11-10 10:12:30",false,"---\nname: \"mk-decision-framework\"\ndescription: \"Operational decision frameworks: triage, escalation, case management, billing ops. Use for 'how to handle X cases', 'build triage', 'escalation protocol'.\"\n---\n\n# Decision Framework Builder\n\nStructures expert judgment into repeatable, auditable decision systems for recurring high-stakes choices.\n\n## When to Use\n\nActivate when:\n- User asks \"how should we handle X cases?\" or \"build triage system\"\n- Designing escalation protocols or case management workflows\n- Billing ops, support, returns, incident response, compliance decisions\n- Any domain with classified decision types and routing rules\n\n## Phase Anchor\n\n**Phase: 1 (Plan)** — Produces a decision framework document.\n**Handoff:** Developer agent implements the decision logic in code.\n\n## Failure Handling\n\n- **Domain unclear:** Ask user for 3 example cases. Derive taxonomy from examples.\n- **No domain expert available:** Flag output as `needs-expert-input`. Mark uncertain classifications explicitly.\n\n## Process (7 Steps)\n\n### Step 1: Identify Decision Type\nClarify the recurring decision being structured. What is decided? Who decides? How often?\n\n### Step 2: Build Classification Taxonomy\nLoad `references\u002Fdecision-tree-template.md`. Map every case type into mutually exclusive categories. Aim for 3-7 top-level buckets — too few collapses distinct cases, too many creates lookup overhead.\n\n### Step 3: Define Sequential Decision Rules\nOrder rules by: **Safety > Compliance > Economics > Speed**. Never let speed override safety. Document the reasoning for each rule's position in the sequence.\n\n### Step 4: Create Weighted Scoring\nLoad `references\u002Fweighted-scoring-guide.md`. Define 3-5 factors with weights summing to 100%. Calibrate against 3 historical cases.\n\n### Step 5: Define Escalation Protocol\nLoad `references\u002Fescalation-protocol-template.md`. Map 4 escalation levels: Expert → Manager → Director → VP. Each level must have authority scope, timeline, and escalation trigger.\n\n### Step 6: Add Communication Templates\nLoad `references\u002Fcommunication-patterns.md`. Select tone per relationship state: Routine \u002F Significant \u002F Crisis. Customize placeholders.\n\n### Step 7: Document Edge Cases\nLoad `references\u002Fedge-case-discovery.md`. Collect edge cases from team (\"what surprised you?\"). Document each as: situation → why obvious approach fails → correct approach.\n\n## References\n\n| File | Purpose |\n|------|---------|\n| `references\u002Fdecision-tree-template.md` | Domain-agnostic taxonomy + rules template |\n| `references\u002Fescalation-protocol-template.md` | 4-level escalation with authority\u002Ftimeline\u002Ftriggers |\n| `references\u002Fweighted-scoring-guide.md` | Multi-factor scoring + calibration method |\n| `references\u002Fcommunication-patterns.md` | 3 tones with example templates |\n| `references\u002Fedge-case-discovery.md` | Edge case collection and documentation process |\n| `references\u002Fexamples\u002Fexample-returns-triage.md` | Worked example: returns processing |\n| `references\u002Fexamples\u002Fexample-billing-ops.md` | Worked example: billing operations |\n| `references\u002Fexamples\u002Fexample-incident-response.md` | Worked example: security incidents |\n\n## Output Format\n\nProduce a decision framework document with:\n1. **Domain Summary** — what is being decided, frequency, stakes\n2. **Classification Taxonomy** — case types and definitions\n3. **Decision Rules** — ordered Safety → Compliance → Economics → Speed\n4. **Scoring Matrix** — weighted factors with calibration notes\n5. **Escalation Protocol** — 4-level table\n6. **Communication Templates** — one per tone\n7. **Edge Case Playbook** — 2-3 sentence entries per known exception\n\n## Gotchas\n\n- Do not merge case types that have different decision rules — keep taxonomy granular\n- Scoring weights must sum to 100%; calibrate on real cases, not hypothetical ones\n- Escalation timelines must be specific (hours, not \"soon\")\n- Edge cases are not exceptions to document and ignore — they are the most important cases to get right","# Decision Framework Builder\n\nStructures expert judgment into repeatable, auditable decision systems for recurring high-stakes choices.\n\n## When to Use\n\nActivate when:\n- User asks \"how should we handle X cases?\" or \"build triage system\"\n- Designing escalation protocols or case management workflows\n- Billing ops, support, returns, incident response, compliance decisions\n- Any domain with classified decision types and routing rules\n\n## Phase Anchor\n\n**Phase: 1 (Plan)** — Produces a decision framework document.\n**Handoff:** Developer agent implements the decision logic in code.\n\n## Failure Handling\n\n- **Domain unclear:** Ask user for 3 example cases. Derive taxonomy from examples.\n- **No domain expert available:** Flag output as `needs-expert-input`. Mark uncertain classifications explicitly.\n\n## Process (7 Steps)\n\n### Step 1: Identify Decision Type\nClarify the recurring decision being structured. What is decided? Who decides? How often?\n\n### Step 2: Build Classification Taxonomy\nLoad `references\u002Fdecision-tree-template.md`. Map every case type into mutually exclusive categories. Aim for 3-7 top-level buckets — too few collapses distinct cases, too many creates lookup overhead.\n\n### Step 3: Define Sequential Decision Rules\nOrder rules by: **Safety > Compliance > Economics > Speed**. Never let speed override safety. Document the reasoning for each rule's position in the sequence.\n\n### Step 4: Create Weighted Scoring\nLoad `references\u002Fweighted-scoring-guide.md`. Define 3-5 factors with weights summing to 100%. Calibrate against 3 historical cases.\n\n### Step 5: Define Escalation Protocol\nLoad `references\u002Fescalation-protocol-template.md`. Map 4 escalation levels: Expert → Manager → Director → VP. Each level must have authority scope, timeline, and escalation trigger.\n\n### Step 6: Add Communication Templates\nLoad `references\u002Fcommunication-patterns.md`. Select tone per relationship state: Routine \u002F Significant \u002F Crisis. Customize placeholders.\n\n### Step 7: Document Edge Cases\nLoad `references\u002Fedge-case-discovery.md`. Collect edge cases from team (\"what surprised you?\"). Document each as: situation → why obvious approach fails → correct approach.\n\n## References\n\n| File | Purpose |\n|------|---------|\n| `references\u002Fdecision-tree-template.md` | Domain-agnostic taxonomy + rules template |\n| `references\u002Fescalation-protocol-template.md` | 4-level escalation with authority\u002Ftimeline\u002Ftriggers |\n| `references\u002Fweighted-scoring-guide.md` | Multi-factor scoring + calibration method |\n| `references\u002Fcommunication-patterns.md` | 3 tones with example templates |\n| `references\u002Fedge-case-discovery.md` | Edge case collection and documentation process |\n| `references\u002Fexamples\u002Fexample-returns-triage.md` | Worked example: returns processing |\n| `references\u002Fexamples\u002Fexample-billing-ops.md` | Worked example: billing operations |\n| `references\u002Fexamples\u002Fexample-incident-response.md` | Worked example: security incidents |\n\n## Output Format\n\nProduce a decision framework document with:\n1. **Domain Summary** — what is being decided, frequency, stakes\n2. **Classification Taxonomy** — case types and definitions\n3. **Decision Rules** — ordered Safety → Compliance → Economics → Speed\n4. **Scoring Matrix** — weighted factors with calibration notes\n5. **Escalation Protocol** — 4-level table\n6. **Communication Templates** — one per tone\n7. **Edge Case Playbook** — 2-3 sentence entries per known exception\n\n## Gotchas\n\n- Do not merge case types that have different decision rules — keep taxonomy granular\n- Scoring weights must sum to 100%; calibrate on real cases, not hypothetical ones\n- Escalation timelines must be specific (hours, not \"soon\")\n- Edge cases are not exceptions to document and ignore — they are the most important cases to get right",{"name":5,"description":7},"main","0b5569142101a45a6dc48d1b01bfae8801383fb7","packages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-12 20:22:02",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-decision-framework",{"tool":55,"command":56},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-decision-framework",{"tool":58,"command":59},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-decision-framework","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002FSKILL.md",true,[63,69,73,77,81,85,89,93],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fcommunication-patterns.md","REFERENCE","参考文档",3909,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fcommunication-patterns.md",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fdecision-tree-template.md",2499,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fdecision-tree-template.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fedge-case-discovery.md",2582,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fedge-case-discovery.md",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fescalation-protocol-template.md",3097,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fescalation-protocol-template.md",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fexamples\u002Fexample-billing-ops.md",4047,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fexamples\u002Fexample-billing-ops.md",{"path":86,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fexamples\u002Fexample-incident-response.md",4903,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fexamples\u002Fexample-incident-response.md",{"path":90,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fexamples\u002Fexample-returns-triage.md",2957,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fexamples\u002Fexample-returns-triage.md",{"path":94,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fweighted-scoring-guide.md",3557,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-decision-framework\u002Freferences\u002Fweighted-scoring-guide.md",[98,116,134,140,152,176],{"skillNo":99,"name":100,"nameZh":6,"description":101,"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":104,"publishedAt":35},"01M6J4NFDY0KY3XXJ6E5WBASAF","mk-sequential-thinking","Structured step-by-step reasoning before acting, to avoid guessing. For complex debugging, multi-step analysis, hypothesis checks. NOT for being stuck on approach (mk:problem-solving).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-sequential-thinking\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,34,114,115],"mk sequential thinking","sequential thinking","thinking","structured","problem","problem-solving","analysis","hypothesis","reasoning","debugging","multi",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":127,"publishedAt":35},"01M6J5D3G7C0V3BZ97Y61WB172","mk:fixture-valid","A valid fixture used to verify the skill structure validator.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Fvalid\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[128,129,130,131,132,133],"mk:fixture valid","fixture","valid","verify","structure","validator",{"skillNo":135,"name":136,"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":137,"categories":138,"keywords":139,"publishedAt":35},"01M6J5CZRVSN8T4BZM0Y42CXJY","invalid","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-creator\u002Finvalid\u002FSKILL.md",[],[136],{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":35},"01M6J5CVN0N8KP9JFAWCV2PC2T","mk:sample-skill","Sample skill for fixture purposes — small enough to land below noise floor.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Ftests\u002Ffixtures\u002Fcontext-audit\u002F.claude\u002Fskills\u002Fsample-skill\u002FSKILL.md",[146],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},[148,149,150,151,129,34],"mk:sample skill","sample","sample skill","land",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":35},"01M6J5CP99X9S0B7XCSBX6H5P2","mk-worktree","Manages git worktrees for parallel agent isolation: creates parallel\u002F{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[158],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},[160,161,162,163,28,164,165,166,167,168,169,170,34,171,172,173,174,175],"mk worktree","worktree","user","git worktrees","worktrees","branches","conflict","feature","isolation","name","with","parallel","timestamp","git","detection","git worktree",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":35},"01M6J5CJT8ZGXH9YYJ7GV3R2B4","mk-workflow-orchestrator","Auto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fpackages\u002Fmewkit\u002Fsrc\u002Fmigrate\u002Fmodules\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[182],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},[184,185,186,187,188,189,190,191,192,193,194,167,195,196,34,197,198,199,200,201,202,203],"mk workflow orchestrator","workflow orchestrator","orchestrator","workflow","green-field","tasks","fix","auto","simple","intent","green","autobuild","mode","fixes","mk:autobuild","mk:cook","mk:fix","fasttrack","complex-feature","phase"]