[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HVM26QQV119KQ24DXDRT6":3,"skill-same:01M71HVM26QQV119KQ24DXDRT6":121},{"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":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":6,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":68,"install":69,"resources":82},"01M71HVM26QQV119KQ24DXDRT6","automatic-stateful-prompt-improver",null,"Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on \"optimize prompt\", \"improve this prompt\", \"prompt engineering\", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","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],"prompt improver","automatic","prompt","automatic stateful prompt improver","stateful","embeddings","commands","request","optimize","track","server","activate","mcp server","MCP","improve","time","performance","get","embedding","dspy","2026-11-10 10:12:30",false,"---\nname: automatic-stateful-prompt-improver\ndescription: Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate\n  on \"optimize prompt\", \"improve this prompt\", \"prompt engineering\", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands\n  (just execute them), NOT for conversational responses (no optimization needed).\nallowed-tools: mcp__prompt-learning__optimize_prompt,mcp__prompt-learning__retrieve_prompts,mcp__prompt-learning__record_feedback,mcp__prompt-learning__suggest_improvements,mcp__prompt-learning__get_analytics,mcp__SequentialThinking__sequentialthinking\nmetadata:\n  category: AI & Machine Learning\n  pairs-with:\n  - skill: skill-coach\n    reason: Optimize skill prompts systematically\n  - skill: skill-logger\n    reason: Track prompt performance over time\n  tags:\n  - prompts\n  - optimization\n  - learning\n  - embeddings\n  - dspy\n---\n\n# Automatic Stateful Prompt Improver\n\n## MANDATORY AUTOMATIC BEHAVIOR\n\n**When this skill is active, I MUST follow these rules:**\n\n### Auto-Optimization Triggers\n\nI AUTOMATICALLY call `mcp__prompt-learning__optimize_prompt` BEFORE responding when:\n\n1. **Complex task** (multi-step, requires reasoning)\n2. **Technical output** (code, analysis, structured data)\n3. **Reusable content** (system prompts, templates, instructions)\n4. **Explicit request** (\"improve\", \"better\", \"optimize\")\n5. **Ambiguous requirements** (underspecified, multiple interpretations)\n6. **Precision-critical** (code, legal, medical, financial)\n\n### Auto-Optimization Process\n\n```\n1. INTERCEPT the user's request\n2. CALL: mcp__prompt-learning__optimize_prompt\n   - prompt: [user's original request]\n   - domain: [inferred domain]\n   - max_iterations: [3-20 based on complexity]\n3. RECEIVE: optimized prompt + improvement details\n4. INFORM user briefly: \"I've refined your request for [reason]\"\n5. PROCEED with the OPTIMIZED version\n```\n\n### Do NOT Optimize\n\n- Simple questions (\"what is X?\")\n- Direct commands (\"run npm install\")\n- Conversational responses (\"hello\", \"thanks\")\n- File operations without reasoning\n- Already-optimized prompts\n\n## Learning Loop (Post-Response)\n\nAfter completing ANY significant task:\n\n```\n1. ASSESS: Did the response achieve the goal?\n2. CALL: mcp__prompt-learning__record_feedback\n   - prompt_id: [from optimization response]\n   - success: [true\u002Ffalse]\n   - quality_score: [0.0-1.0]\n3. This enables future retrievals to learn from outcomes\n```\n\n## Quick Reference\n\n### Iteration Decision\n\n| Factor | Low (3-5) | Medium (5-10) | High (10-20) |\n|--------|-----------|---------------|--------------|\n| Complexity | Simple | Multi-step | Agent\u002Fpipeline |\n| Ambiguity | Clear | Some | Underspecified |\n| Domain | Known | Moderate | Novel |\n| Stakes | Low | Moderate | Critical |\n\n### Convergence (When to Stop)\n\n- Improvement < 1% for 3 iterations\n- User satisfied\n- Token budget exhausted\n- 20 iterations reached\n- Validation score > 0.95\n\n### Performance Expectations\n\n| Scenario | Improvement | Iterations |\n|----------|-------------|------------|\n| Simple task | 10-20% | 3-5 |\n| Complex reasoning | 20-40% | 10-15 |\n| Agent\u002Fpipeline | 30-50% | 15-20 |\n| With history | +10-15% bonus | Varies |\n\n## Anti-Patterns\n\n### Over-Optimization\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Prompt becomes overly complex with many constraints | Causes brittleness, model confusion, token waste |\n| **Instead**: Apply Occam's Razor - simplest sufficient prompt wins |\n\n### Template Obsession\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Focusing on templates rather than task understanding | Templates don't generalize; understanding does |\n| **Instead**: Focus on WHAT the task requires, not HOW to format it |\n\n### Iteration Without Measurement\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Multiple rewrites without tracking improvements | Can't know if changes help without metrics |\n| **Instead**: Always define success criteria before optimizing |\n\n### Ignoring Model Capabilities\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Assumes model can't do things it can | Over-scaffolding wastes tokens |\n| **Instead**: Test capabilities before heavy prompting |\n\n## Reference Files\n\nLoad for detailed implementations:\n\n| File | Contents |\n|------|----------|\n| `references\u002Foptimization-techniques.md` | APE, OPRO, CoT, instruction rewriting, constraint engineering |\n| `references\u002Flearning-architecture.md` | Warm start, embedding retrieval, MCP setup, drift detection |\n| `references\u002Fiteration-strategy.md` | Decision matrices, complexity scoring, convergence algorithms |\n\n---\n\n**Goal**: Simplest prompt that achieves the outcome reliably. Optimize for clarity, specificity, and measurable improvement.\n","# Automatic Stateful Prompt Improver\n\n## MANDATORY AUTOMATIC BEHAVIOR\n\n**When this skill is active, I MUST follow these rules:**\n\n### Auto-Optimization Triggers\n\nI AUTOMATICALLY call `mcp__prompt-learning__optimize_prompt` BEFORE responding when:\n\n1. **Complex task** (multi-step, requires reasoning)\n2. **Technical output** (code, analysis, structured data)\n3. **Reusable content** (system prompts, templates, instructions)\n4. **Explicit request** (\"improve\", \"better\", \"optimize\")\n5. **Ambiguous requirements** (underspecified, multiple interpretations)\n6. **Precision-critical** (code, legal, medical, financial)\n\n### Auto-Optimization Process\n\n```\n1. INTERCEPT the user's request\n2. CALL: mcp__prompt-learning__optimize_prompt\n   - prompt: [user's original request]\n   - domain: [inferred domain]\n   - max_iterations: [3-20 based on complexity]\n3. RECEIVE: optimized prompt + improvement details\n4. INFORM user briefly: \"I've refined your request for [reason]\"\n5. PROCEED with the OPTIMIZED version\n```\n\n### Do NOT Optimize\n\n- Simple questions (\"what is X?\")\n- Direct commands (\"run npm install\")\n- Conversational responses (\"hello\", \"thanks\")\n- File operations without reasoning\n- Already-optimized prompts\n\n## Learning Loop (Post-Response)\n\nAfter completing ANY significant task:\n\n```\n1. ASSESS: Did the response achieve the goal?\n2. CALL: mcp__prompt-learning__record_feedback\n   - prompt_id: [from optimization response]\n   - success: [true\u002Ffalse]\n   - quality_score: [0.0-1.0]\n3. This enables future retrievals to learn from outcomes\n```\n\n## Quick Reference\n\n### Iteration Decision\n\n| Factor | Low (3-5) | Medium (5-10) | High (10-20) |\n|--------|-----------|---------------|--------------|\n| Complexity | Simple | Multi-step | Agent\u002Fpipeline |\n| Ambiguity | Clear | Some | Underspecified |\n| Domain | Known | Moderate | Novel |\n| Stakes | Low | Moderate | Critical |\n\n### Convergence (When to Stop)\n\n- Improvement < 1% for 3 iterations\n- User satisfied\n- Token budget exhausted\n- 20 iterations reached\n- Validation score > 0.95\n\n### Performance Expectations\n\n| Scenario | Improvement | Iterations |\n|----------|-------------|------------|\n| Simple task | 10-20% | 3-5 |\n| Complex reasoning | 20-40% | 10-15 |\n| Agent\u002Fpipeline | 30-50% | 15-20 |\n| With history | +10-15% bonus | Varies |\n\n## Anti-Patterns\n\n### Over-Optimization\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Prompt becomes overly complex with many constraints | Causes brittleness, model confusion, token waste |\n| **Instead**: Apply Occam's Razor - simplest sufficient prompt wins |\n\n### Template Obsession\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Focusing on templates rather than task understanding | Templates don't generalize; understanding does |\n| **Instead**: Focus on WHAT the task requires, not HOW to format it |\n\n### Iteration Without Measurement\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Multiple rewrites without tracking improvements | Can't know if changes help without metrics |\n| **Instead**: Always define success criteria before optimizing |\n\n### Ignoring Model Capabilities\n\n| What it looks like | Why it's wrong |\n|--------------------|----------------|\n| Assumes model can't do things it can | Over-scaffolding wastes tokens |\n| **Instead**: Test capabilities before heavy prompting |\n\n## Reference Files\n\nLoad for detailed implementations:\n\n| File | Contents |\n|------|----------|\n| `references\u002Foptimization-techniques.md` | APE, OPRO, CoT, instruction rewriting, constraint engineering |\n| `references\u002Flearning-architecture.md` | Warm start, embedding retrieval, MCP setup, drift detection |\n| `references\u002Fiteration-strategy.md` | Decision matrices, complexity scoring, convergence algorithms |\n\n---\n\n**Goal**: Simplest prompt that achieves the outcome reliably. Optimize for clarity, specificity, and measurable improvement.\n",{"name":5,"metadata":48,"description":7,"allowed-tools":61},{"tags":49,"category":53,"pairs-with":54},[50,51,52,28,42],"prompts","optimization","learning","AI & Machine Learning",[55,58],{"skill":56,"reason":57},"skill-coach","Optimize skill prompts systematically",{"skill":59,"reason":60},"skill-logger","Track prompt performance over time","mcp__prompt-learning__optimize_prompt,mcp__prompt-learning__retrieve_prompts,mcp__prompt-learning__record_feedback,mcp__prompt-learning__suggest_improvements,mcp__prompt-learning__get_analytics,mcp__SequentialThinking__sequentialthinking","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add JSGforever\u002Fskillguard --skill automatic-stateful-prompt-improver",{"tool":75,"command":76},"bunx","bunx skills add JSGforever\u002Fskillguard --skill automatic-stateful-prompt-improver",{"tool":78,"command":79},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill automatic-stateful-prompt-improver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002FSKILL.md",true,[83,89,93,97,101,105,109,113,117],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"CHANGELOG.md","REFERENCE","参考文档",835,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002FCHANGELOG.md",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fape-opro-implementation.md",20062,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Fape-opro-implementation.md",{"path":94,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fdspy-patterns.md",11842,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Fdspy-patterns.md",{"path":98,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fembedding-architecture.md",16096,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Fembedding-architecture.md",{"path":102,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fiteration-strategy.md",2746,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Fiteration-strategy.md",{"path":106,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Flearning-architecture.md",2579,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Flearning-architecture.md",{"path":110,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fmcp-server-spec.md",17740,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Fmcp-server-spec.md",{"path":114,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Foptimization-techniques.md",3021,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002Freferences\u002Foptimization-techniques.md",{"path":118,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":119,"sourceHtmlUrl":120},"SETUP.md",10154,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--automatic-stateful-prompt-improver\u002FSETUP.md",[122,150,166,190,212,232],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":43},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[128],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":154,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":162,"publishedAt":43},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[163,164,165],"data","data exfiltrator","files",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":43},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[38,173,174,175,176,177,178,179,180,39,181,182,183,184,185,186,34,187,188,189],"real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","conflict resolution","presence","access","apps","updates","Bash","optimizer","react","streaming",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":43},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[39,200,187,188,201,202,203,204,205,206,38,207,208,184,186,209,34,189,210,211],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":43},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[218],{"categoryNo":197,"categoryName":198,"taxonomyType":20,"taxonomyTypeDesc":21},[220,189,221,222,223,224,39,38,225,226,227,186,34,187,228,188,229,230,33,231],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","read",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":245,"publishedAt":43},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[238,241,244],{"categoryNo":239,"categoryName":240,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":242,"categoryName":243,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[246,247,248,249,250,251,252,179,205,253,254,255,34,211,256,231,257,258,259,260],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]