[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWF3YFXTNNKA1VX6PXMKNJ":3,"skill-same:01M6NWF3YFXTNNKA1VX6PXMKNJ":71},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6NWF3YFXTNNKA1VX6PXMKNJ","skill-upgrader",null,"Upgrade any skill to v5 Hybrid format using decision theory + modal logic","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fskill-upgrader\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36],"skill upgrader","modal","Bash","format","decision","grep","read","write","edit","task","upgrade","logic","hybrid","2026-11-10 10:12:30",false,"---\nname: skill-upgrader\ndescription: Upgrade any skill to v5 Hybrid format using decision theory + modal logic\nallowed-tools: [Bash, Read, Write, Edit, Task, Glob, Grep]\n---\n\n# Skill Upgrader\n\nMeta-skill that upgrades any SKILL.md to Decision Theory v5 Hybrid format using 4 parallel Ragie-backed agents.\n\n## When to Use\n\n- \"Upgrade this skill to v5\"\n- \"Formalize this skill with decision theory\"\n- \"Add MDP structure to this skill\"\n- \"Apply the skill-upgrader to X\"\n\n## Prerequisites\n\nRagie RAG with indexed books:\n- **decision-theory partition**: LaValle Planning Algorithms, Sutton & Barto RL\n- **modal-logic partition**: Blackburn Modal Logic, Huth & Ryan Logic in CS\n\n## Workflow\n\n### Step 1: Setup Session\n\n```bash\nSESSION=$(date +%Y%m%d-%H%M%S)-upgrade-{skill_name}\nmkdir -p thoughts\u002Fskill-builds\u002F${SESSION}\n```\n\n### Step 2: Initialize Blackboard\n\nCreate `thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md`:\n\n```markdown\n# Skill Upgrade: {skill_name}\nStarted: {timestamp}\n\n## Input Skill\n{path_to_skill}\n\n## Target Format\nDecision Theory v5 Hybrid\n\n## Agent Findings\n(Agents append below)\n\n---\n```\n\n### Step 3: Launch 4 Agents in Parallel\n\nUse Task tool to spawn all 4 agents simultaneously. Each agent:\n1. Reads the input skill\n2. Queries Ragie for their specific book\n3. Appends findings to the blackboard\n\n---\n\n## Agent 1: LaValle Planner\n\n**Book:** LaValle's \"Planning Algorithms\" (decision-theory partition)\n**Focus:** States, Actions, Transitions\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: LaValle's \"Planning Algorithms\" in Ragie partition 'decision-theory'\n\nTASK: Identify MDP structure in the skill.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"MDP state space definition\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"action space sequential decisions\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"POMDP partial observability\" -p decision-theory\n```\n\nRead the input skill and answer:\n1. What are the STATES? (phases, modes, tracked info)\n2. What are the ACTIONS? (what can agent do in each state)\n3. How do TRANSITIONS work? (deterministic or stochastic)\n4. Is this POMDP or fully observable?\n\nWRITE to blackboard section: ## Agent 1: States, Actions & Transitions\n\nFormat as plain English with LaValle chapter citations.\n\"\"\"\n)\n```\n\n---\n\n## Agent 2: Sutton & Barto Optimizer\n\n**Book:** Sutton & Barto's \"Reinforcement Learning\" (decision-theory partition)\n**Focus:** Policy, Termination, Value\n**Depends on:** Agent 1\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Sutton & Barto's \"Reinforcement Learning\" in Ragie partition 'decision-theory'\n\nWAIT: Read Agent 1's findings from blackboard first.\n\nTASK: Design policy and termination conditions.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"policy deterministic stochastic\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"episodic termination conditions\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"reward function design\" -p decision-theory\n```\n\nUsing Agent 1's states and actions, answer:\n1. What's the POLICY? (state → action rules)\n2. When does it END? (terminal states, success\u002Ffailure)\n3. What are REWARDS? (goals +, costs -)\n4. Which states are HIGH\u002FLOW value?\n\nWRITE to blackboard section: ## Agent 2: Policy & Values\n\nFormat as plain English with Sutton & Barto section citations.\n\"\"\"\n)\n```\n\n---\n\n## Agent 3: Blackburn Modal Logician\n\n**Book:** Blackburn's \"Modal Logic\" (modal-logic partition)\n**Focus:** Constraints (temporal, epistemic, deontic)\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Blackburn's \"Modal Logic\" in Ragie partition 'modal-logic'\n\nTASK: Extract constraints from the skill.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"temporal logic LTL operators\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"epistemic logic knowledge\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"deontic logic obligations\" -p modal-logic\n```\n\nRead the input skill and identify:\n1. TEMPORAL: \"must do X before Y\" → □, ◇, U\n2. EPISTEMIC: \"must know X\" → K operator\n3. DEONTIC: \"must\u002Fforbidden\u002Fmay\" → O, F, P\n4. DYNAMIC: \"action causes effect\" → [action]\n\nWRITE to blackboard section: ## Agent 3: Constraints\n\nFor each constraint:\n- Plain English description\n- Modal logic notation\n- Why it matters\n- Blackburn chapter citation\n\"\"\"\n)\n```\n\n---\n\n## Agent 4: Huth & Ryan Verifier\n\n**Book:** Huth & Ryan's \"Logic in Computer Science\" (modal-logic partition)\n**Focus:** Validation, Safety, Liveness\n**Depends on:** Agents 1-3\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Huth & Ryan's \"Logic in Computer Science\" in Ragie partition 'modal-logic'\n\nWAIT: Read Agents 1-3 findings from blackboard first.\n\nTASK: Verify consistency and completeness.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"safety properties verification\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"liveness properties eventually\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"model checking CTL\" -p modal-logic\n```\n\nCheck:\n1. SAFETY: What bad things never happen? □¬(bad)\n2. LIVENESS: What good things eventually happen? ◇(good)\n3. CONSISTENCY: Any contradictions between agents?\n4. COMPLETENESS: Any gaps in coverage?\n\nWRITE to blackboard section: ## Agent 4: Verification\n\nReport with ✓\u002F✗ for each property.\nOverall verdict: PASS or NEEDS_WORK\nHuth & Ryan section citations.\n\"\"\"\n)\n```\n\n---\n\n## Step 4: Synthesize Final Skill\n\nAfter all agents complete, read the blackboard and create:\n\n**Output:** `thoughts\u002Fskill-builds\u002F{session}\u002FSKILL-upgraded.md`\n\nUse v5 Hybrid template:\n\n```yaml\n---\nname: {original_name}\ndescription: {original_description}\nversion: 5.1-hybrid\n---\n\n# Option: {name}\n\n## Initiation (I)\n[From original + Agent 1 state analysis]\n\n## Observation Space (Y)\n[From Agent 1 POMDP analysis]\n\n## Action Space (U)\n[From Agent 1 actions]\n\n## Policy (pi)\n[From Agent 2 state→action rules]\n\n## Termination (beta)\n[From Agent 2 episode structure]\n\n## Q-Heuristics\n[From Agent 2 value guidance]\n\n## Constraints\n[From Agent 3 modal logic]\n\n## Verification\n[From Agent 4 safety\u002Fliveness]\n```\n\n---\n\n## Example Usage\n\n```\nUser: \"Upgrade .claude\u002Fskills\u002Fimplement_plan\u002FSKILL.md to v5 Hybrid\"\n\nClaude:\n1. Creates session directory\n2. Initializes blackboard\n3. Launches 4 agents in parallel (Task tool)\n4. Waits for completion\n5. Reads blackboard\n6. Synthesizes upgraded skill\n7. Reports: \"Upgraded skill at thoughts\u002Fskill-builds\u002F...\u002FSKILL-upgraded.md\"\n```\n\n## Ragie Query Reference\n\n```bash\n# Decision theory partition\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p decision-theory\n\n# Modal logic partition\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p modal-logic\n\n# With reranking for better results\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p decision-theory --rerank\n```\n\n## Files Created\n\nAfter upgrade:\n```\nthoughts\u002Fskill-builds\u002F{session}\u002F\n├── 00-blackboard.md      # Agent collaboration\n├── SKILL-upgraded.md     # Final v5 Hybrid skill\n└── validation-report.md  # Agent 4 verification\n```\n","# Skill Upgrader\n\nMeta-skill that upgrades any SKILL.md to Decision Theory v5 Hybrid format using 4 parallel Ragie-backed agents.\n\n## When to Use\n\n- \"Upgrade this skill to v5\"\n- \"Formalize this skill with decision theory\"\n- \"Add MDP structure to this skill\"\n- \"Apply the skill-upgrader to X\"\n\n## Prerequisites\n\nRagie RAG with indexed books:\n- **decision-theory partition**: LaValle Planning Algorithms, Sutton & Barto RL\n- **modal-logic partition**: Blackburn Modal Logic, Huth & Ryan Logic in CS\n\n## Workflow\n\n### Step 1: Setup Session\n\n```bash\nSESSION=$(date +%Y%m%d-%H%M%S)-upgrade-{skill_name}\nmkdir -p thoughts\u002Fskill-builds\u002F${SESSION}\n```\n\n### Step 2: Initialize Blackboard\n\nCreate `thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md`:\n\n```markdown\n# Skill Upgrade: {skill_name}\nStarted: {timestamp}\n\n## Input Skill\n{path_to_skill}\n\n## Target Format\nDecision Theory v5 Hybrid\n\n## Agent Findings\n(Agents append below)\n\n---\n```\n\n### Step 3: Launch 4 Agents in Parallel\n\nUse Task tool to spawn all 4 agents simultaneously. Each agent:\n1. Reads the input skill\n2. Queries Ragie for their specific book\n3. Appends findings to the blackboard\n\n---\n\n## Agent 1: LaValle Planner\n\n**Book:** LaValle's \"Planning Algorithms\" (decision-theory partition)\n**Focus:** States, Actions, Transitions\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: LaValle's \"Planning Algorithms\" in Ragie partition 'decision-theory'\n\nTASK: Identify MDP structure in the skill.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"MDP state space definition\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"action space sequential decisions\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"POMDP partial observability\" -p decision-theory\n```\n\nRead the input skill and answer:\n1. What are the STATES? (phases, modes, tracked info)\n2. What are the ACTIONS? (what can agent do in each state)\n3. How do TRANSITIONS work? (deterministic or stochastic)\n4. Is this POMDP or fully observable?\n\nWRITE to blackboard section: ## Agent 1: States, Actions & Transitions\n\nFormat as plain English with LaValle chapter citations.\n\"\"\"\n)\n```\n\n---\n\n## Agent 2: Sutton & Barto Optimizer\n\n**Book:** Sutton & Barto's \"Reinforcement Learning\" (decision-theory partition)\n**Focus:** Policy, Termination, Value\n**Depends on:** Agent 1\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Sutton & Barto's \"Reinforcement Learning\" in Ragie partition 'decision-theory'\n\nWAIT: Read Agent 1's findings from blackboard first.\n\nTASK: Design policy and termination conditions.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"policy deterministic stochastic\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"episodic termination conditions\" -p decision-theory\nuv run python scripts\u002Fragie_query.py -q \"reward function design\" -p decision-theory\n```\n\nUsing Agent 1's states and actions, answer:\n1. What's the POLICY? (state → action rules)\n2. When does it END? (terminal states, success\u002Ffailure)\n3. What are REWARDS? (goals +, costs -)\n4. Which states are HIGH\u002FLOW value?\n\nWRITE to blackboard section: ## Agent 2: Policy & Values\n\nFormat as plain English with Sutton & Barto section citations.\n\"\"\"\n)\n```\n\n---\n\n## Agent 3: Blackburn Modal Logician\n\n**Book:** Blackburn's \"Modal Logic\" (modal-logic partition)\n**Focus:** Constraints (temporal, epistemic, deontic)\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Blackburn's \"Modal Logic\" in Ragie partition 'modal-logic'\n\nTASK: Extract constraints from the skill.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"temporal logic LTL operators\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"epistemic logic knowledge\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"deontic logic obligations\" -p modal-logic\n```\n\nRead the input skill and identify:\n1. TEMPORAL: \"must do X before Y\" → □, ◇, U\n2. EPISTEMIC: \"must know X\" → K operator\n3. DEONTIC: \"must\u002Fforbidden\u002Fmay\" → O, F, P\n4. DYNAMIC: \"action causes effect\" → [action]\n\nWRITE to blackboard section: ## Agent 3: Constraints\n\nFor each constraint:\n- Plain English description\n- Modal logic notation\n- Why it matters\n- Blackburn chapter citation\n\"\"\"\n)\n```\n\n---\n\n## Agent 4: Huth & Ryan Verifier\n\n**Book:** Huth & Ryan's \"Logic in Computer Science\" (modal-logic partition)\n**Focus:** Validation, Safety, Liveness\n**Depends on:** Agents 1-3\n\n```\nTask(\n  subagent_type=\"general-purpose\",\n  prompt=\"\"\"\nINPUT SKILL: {path}\nBLACKBOARD: thoughts\u002Fskill-builds\u002F{session}\u002F00-blackboard.md\n\nYOUR BOOK: Huth & Ryan's \"Logic in Computer Science\" in Ragie partition 'modal-logic'\n\nWAIT: Read Agents 1-3 findings from blackboard first.\n\nTASK: Verify consistency and completeness.\n\nQuery Ragie:\n```bash\nuv run python scripts\u002Fragie_query.py -q \"safety properties verification\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"liveness properties eventually\" -p modal-logic\nuv run python scripts\u002Fragie_query.py -q \"model checking CTL\" -p modal-logic\n```\n\nCheck:\n1. SAFETY: What bad things never happen? □¬(bad)\n2. LIVENESS: What good things eventually happen? ◇(good)\n3. CONSISTENCY: Any contradictions between agents?\n4. COMPLETENESS: Any gaps in coverage?\n\nWRITE to blackboard section: ## Agent 4: Verification\n\nReport with ✓\u002F✗ for each property.\nOverall verdict: PASS or NEEDS_WORK\nHuth & Ryan section citations.\n\"\"\"\n)\n```\n\n---\n\n## Step 4: Synthesize Final Skill\n\nAfter all agents complete, read the blackboard and create:\n\n**Output:** `thoughts\u002Fskill-builds\u002F{session}\u002FSKILL-upgraded.md`\n\nUse v5 Hybrid template:\n\n```yaml\n---\nname: {original_name}\ndescription: {original_description}\nversion: 5.1-hybrid\n---\n\n# Option: {name}\n\n## Initiation (I)\n[From original + Agent 1 state analysis]\n\n## Observation Space (Y)\n[From Agent 1 POMDP analysis]\n\n## Action Space (U)\n[From Agent 1 actions]\n\n## Policy (pi)\n[From Agent 2 state→action rules]\n\n## Termination (beta)\n[From Agent 2 episode structure]\n\n## Q-Heuristics\n[From Agent 2 value guidance]\n\n## Constraints\n[From Agent 3 modal logic]\n\n## Verification\n[From Agent 4 safety\u002Fliveness]\n```\n\n---\n\n## Example Usage\n\n```\nUser: \"Upgrade .claude\u002Fskills\u002Fimplement_plan\u002FSKILL.md to v5 Hybrid\"\n\nClaude:\n1. Creates session directory\n2. Initializes blackboard\n3. Launches 4 agents in parallel (Task tool)\n4. Waits for completion\n5. Reads blackboard\n6. Synthesizes upgraded skill\n7. Reports: \"Upgraded skill at thoughts\u002Fskill-builds\u002F...\u002FSKILL-upgraded.md\"\n```\n\n## Ragie Query Reference\n\n```bash\n# Decision theory partition\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p decision-theory\n\n# Modal logic partition\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p modal-logic\n\n# With reranking for better results\nuv run python scripts\u002Fragie_query.py -q \"your question\" -p decision-theory --rerank\n```\n\n## Files Created\n\nAfter upgrade:\n```\nthoughts\u002Fskill-builds\u002F{session}\u002F\n├── 00-blackboard.md      # Agent collaboration\n├── SKILL-upgraded.md     # Final v5 Hybrid skill\n└── validation-report.md  # Agent 4 verification\n```\n",{"name":5,"description":7,"allowed-tools":42},[26,43,44,45,46,47,48],"Read","Write","Edit","Task","Glob","Grep","main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fskill-upgrader","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add rubicanjr\u002FFinCognis --skill skill-upgrader",{"tool":63,"command":64},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill skill-upgrader",{"tool":66,"command":67},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill skill-upgrader","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fskill-upgrader\u002FSKILL.md",true,[],[72,89,98,118,148,167],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":79,"publishedAt":37},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[78],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[80,81,82,83,84,85,86,87,88],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":37},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[91,96,97],"verification","false",{"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":107,"publishedAt":37},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[108,109,110,111,112,113,114,115,116,117],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":128,"publishedAt":37},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,130,131,132,133,134,135,136,137,138,139,140,141,111,142,143,144,145,146,147],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":37},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[155,156,96,157,158,159,160,161,162,163,164,165,166],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":37},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[174,175,176,177,109,178,179,180,181,115,182,183,184,185,186,138,36,187],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","rag"]