[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71H8MR9BHB90THTFHADWVG2":3,"skill-same:01M71H8MR9BHB90THTFHADWVG2":92},{"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":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M71H8MR9BHB90THTFHADWVG2","apollo-mcp-server",null,"Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute), (4) troubleshooting MCP server connectivity or tool execution issues.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"mcp server","server","apollo mcp server","apollo","MCP","setting","graphql operations","guide","Tools","edit","write","read","ai agents","code","Bash","when","connect","issues","up","search","2026-11-10 10:12:30",false,"---\nname: apollo-mcp-server\ndescription: >\n  Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs.\n  Use this skill when: (1) setting up or configuring Apollo MCP Server,\n  (2) defining MCP tools from GraphQL operations, (3) using introspection\n  tools (introspect, search, validate, execute), (4) troubleshooting\n  MCP server connectivity or tool execution issues.\nlicense: MIT\ncompatibility: Works with Claude Code, Claude Desktop, Cursor.\nmetadata:\n  author: apollographql\n  version: \"1.1.0\"\nallowed-tools: Bash(rover:*) Bash(npx:*) Read Write Edit Glob Grep\n---\n\n# Apollo MCP Server Guide\n\nApollo MCP Server exposes GraphQL operations as MCP tools, enabling AI agents to interact with GraphQL APIs through the Model Context Protocol.\n\n## Quick Start\n\n### Step 1: Install\n\n```bash\n# Linux \u002F MacOS\ncurl -sSL https:\u002F\u002Fmcp.apollo.dev\u002Fdownload\u002Fnix\u002Flatest | sh\n\n# Windows\niwr 'https:\u002F\u002Fmcp.apollo.dev\u002Fdownload\u002Fwin\u002Flatest' | iex\n```\n\n### Step 2: Configure\n\nCreate `config.yaml` in your project root:\n\n```yaml\n# config.yaml\ntransport:\n  type: streamable_http\nschema:\n  source: local\n  path: .\u002Fschema.graphql\noperations:\n  source: local\n  paths:\n    - .\u002Foperations\u002F\nintrospection:\n  introspect:\n    enabled: true\n  search:\n    enabled: true\n  validate:\n    enabled: true\n  execute:\n    enabled: true\n```\n\nStart the server:\n```bash\napollo-mcp-server .\u002Fconfig.yaml\n```\n\nThe MCP endpoint is available at `http:\u002F\u002F127.0.0.1:8000\u002Fmcp` (streamable_http defaults: address `127.0.0.1`, port `8000`). The GraphQL endpoint defaults to `http:\u002F\u002Flocalhost:4000\u002F` — override with the `endpoint` key if your API runs elsewhere.\n\n### Step 3: Connect\n\nAdd to your MCP client configuration:\n\n**Streamable HTTP (recommended):**\n\nClaude Desktop (`claude_desktop_config.json`):\n```json\n{\n  \"mcpServers\": {\n    \"graphql-api\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-remote\", \"http:\u002F\u002F127.0.0.1:8000\u002Fmcp\"]\n    }\n  }\n}\n```\n\nClaude Code:\n```bash\nclaude mcp add graphql-api -- npx mcp-remote http:\u002F\u002F127.0.0.1:8000\u002Fmcp\n```\n\n**Stdio (client launches the server directly):**\n\nClaude Desktop (`claude_desktop_config.json`) or Claude Code (`.mcp.json`):\n```json\n{\n  \"mcpServers\": {\n    \"graphql-api\": {\n      \"command\": \".\u002Fapollo-mcp-server\",\n      \"args\": [\".\u002Fconfig.yaml\"]\n    }\n  }\n}\n```\n\n## Built-in Tools\n\nApollo MCP Server provides four introspection tools:\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `introspect` | Explore schema types in detail | Need type definitions, fields, relationships |\n| `search` | Find types in schema | Looking for specific types or fields |\n| `validate` | Check operation validity | Before executing operations |\n| `execute` | Run ad-hoc GraphQL operations | Testing or one-off queries |\n\n## Defining Custom Tools\n\nMCP tools are created from GraphQL operations. Three methods:\n\n### 1. Operation Files (Recommended)\n\n```yaml\noperations:\n  source: local\n  paths:\n    - .\u002Foperations\u002F\n```\n\n```graphql\n# operations\u002Fusers.graphql\nquery GetUser($id: ID!) {\n  user(id: $id) {\n    id\n    name\n    email\n  }\n}\n\nmutation CreateUser($input: CreateUserInput!) {\n  createUser(input: $input) {\n    id\n    name\n  }\n}\n```\n\nEach named operation becomes an MCP tool.\n\n### 2. Operation Collections\n\n```yaml\noperations:\n  source: collection\n  id: your-collection-id\n```\n\nUse GraphOS Studio to manage operations collaboratively.\n\n### 3. Persisted Queries\n\n```yaml\noperations:\n  source: manifest\n  path: .\u002Fpersisted-query-manifest.json\n```\n\nFor production environments with pre-approved operations.\n\n## Reference Files\n\nDetailed documentation for specific topics:\n\n- [Tools](references\u002Ftools.md) - Introspection tools and minify notation\n- [Configuration](references\u002Fconfiguration.md) - All configuration options\n- [Troubleshooting](references\u002Ftroubleshooting.md) - Common issues and solutions\n\n## Key Rules\n\n### Security\n\n- **Never expose sensitive operations** without authentication\n- Use `headers` configuration for API keys and tokens\n- Disable introspection tools in production (they are disabled by default)\n- Set `overrides.mutation_mode: explicit` to require confirmation for mutations\n\n### Authentication\n\n```yaml\n# Static header\nheaders:\n  Authorization: \"Bearer ${env.API_TOKEN}\"\n\n# Dynamic header forwarding\nforward_headers:\n  - x-forwarded-token\n\n# OAuth (streamable_http transport)\ntransport:\n  type: streamable_http\n  auth:\n    servers:\n      - https:\u002F\u002Fauth.example.com\u002F.well-known\u002Fopenid-configuration\n    audiences:\n      - https:\u002F\u002Fapi.example.com\n```\n\n### Token Optimization\n\nEnable minification to reduce token usage:\n\n```yaml\nintrospection:\n  introspect:\n    minify: true\n  search:\n    minify: true\n```\n\nMinified output uses compact notation:\n- **T** = type, **I** = input, **E** = enum\n- **s** = String, **i** = Int, **b** = Boolean, **f** = Float, **d** = ID\n- **!** = required, **[]** = list\n\n### Mutations\n\nControl mutation behavior via the `overrides` section:\n\n```yaml\noverrides:\n  mutation_mode: all       # Execute mutations directly\n  # mutation_mode: explicit  # Require explicit confirmation\n  # mutation_mode: none      # Block all mutations (default)\n```\n\n## Common Patterns\n\n### GraphOS Cloud Schema\n\n```yaml\n# schema.source defaults to uplink — can be omitted when graphos is configured\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: my-graph@production\n```\n\n### Local Development\n\n```yaml\ntransport:\n  type: streamable_http\nschema:\n  source: local\n  path: .\u002Fschema.graphql\nintrospection:\n  introspect:\n    enabled: true\n  search:\n    enabled: true\n  validate:\n    enabled: true\n  execute:\n    enabled: true\noverrides:\n  mutation_mode: all\n```\n\n### Production Setup\n\n```yaml\ntransport:\n  type: streamable_http\nendpoint: https:\u002F\u002Fapi.production.com\u002Fgraphql\noperations:\n  source: manifest\n  path: .\u002Fpersisted-query-manifest.json\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}\nheaders:\n  Authorization: \"Bearer ${env.API_TOKEN}\"\nhealth_check:\n  enabled: true\n```\n\n### Docker\n\n```yaml\ntransport:\n  type: streamable_http\n  address: 0.0.0.0\n  port: 8000\nendpoint: ${env.GRAPHQL_ENDPOINT}\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}\nhealth_check:\n  enabled: true\n```\n\n## Ground Rules\n\n- ALWAYS configure authentication before exposing to AI agents\n- ALWAYS use `mutation_mode: explicit` or `mutation_mode: none` in shared environments\n- NEVER expose introspection tools with write access to production data\n- PREFER operation files over ad-hoc execute for predictable behavior\n- PREFER streamable_http transport for remote and multi-client deployments\n- USE stdio only when the MCP client launches the server process directly\n- USE GraphOS Studio collections for team collaboration\n","# Apollo MCP Server Guide\n\nApollo MCP Server exposes GraphQL operations as MCP tools, enabling AI agents to interact with GraphQL APIs through the Model Context Protocol.\n\n## Quick Start\n\n### Step 1: Install\n\n```bash\n# Linux \u002F MacOS\ncurl -sSL https:\u002F\u002Fmcp.apollo.dev\u002Fdownload\u002Fnix\u002Flatest | sh\n\n# Windows\niwr 'https:\u002F\u002Fmcp.apollo.dev\u002Fdownload\u002Fwin\u002Flatest' | iex\n```\n\n### Step 2: Configure\n\nCreate `config.yaml` in your project root:\n\n```yaml\n# config.yaml\ntransport:\n  type: streamable_http\nschema:\n  source: local\n  path: .\u002Fschema.graphql\noperations:\n  source: local\n  paths:\n    - .\u002Foperations\u002F\nintrospection:\n  introspect:\n    enabled: true\n  search:\n    enabled: true\n  validate:\n    enabled: true\n  execute:\n    enabled: true\n```\n\nStart the server:\n```bash\napollo-mcp-server .\u002Fconfig.yaml\n```\n\nThe MCP endpoint is available at `http:\u002F\u002F127.0.0.1:8000\u002Fmcp` (streamable_http defaults: address `127.0.0.1`, port `8000`). The GraphQL endpoint defaults to `http:\u002F\u002Flocalhost:4000\u002F` — override with the `endpoint` key if your API runs elsewhere.\n\n### Step 3: Connect\n\nAdd to your MCP client configuration:\n\n**Streamable HTTP (recommended):**\n\nClaude Desktop (`claude_desktop_config.json`):\n```json\n{\n  \"mcpServers\": {\n    \"graphql-api\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-remote\", \"http:\u002F\u002F127.0.0.1:8000\u002Fmcp\"]\n    }\n  }\n}\n```\n\nClaude Code:\n```bash\nclaude mcp add graphql-api -- npx mcp-remote http:\u002F\u002F127.0.0.1:8000\u002Fmcp\n```\n\n**Stdio (client launches the server directly):**\n\nClaude Desktop (`claude_desktop_config.json`) or Claude Code (`.mcp.json`):\n```json\n{\n  \"mcpServers\": {\n    \"graphql-api\": {\n      \"command\": \".\u002Fapollo-mcp-server\",\n      \"args\": [\".\u002Fconfig.yaml\"]\n    }\n  }\n}\n```\n\n## Built-in Tools\n\nApollo MCP Server provides four introspection tools:\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `introspect` | Explore schema types in detail | Need type definitions, fields, relationships |\n| `search` | Find types in schema | Looking for specific types or fields |\n| `validate` | Check operation validity | Before executing operations |\n| `execute` | Run ad-hoc GraphQL operations | Testing or one-off queries |\n\n## Defining Custom Tools\n\nMCP tools are created from GraphQL operations. Three methods:\n\n### 1. Operation Files (Recommended)\n\n```yaml\noperations:\n  source: local\n  paths:\n    - .\u002Foperations\u002F\n```\n\n```graphql\n# operations\u002Fusers.graphql\nquery GetUser($id: ID!) {\n  user(id: $id) {\n    id\n    name\n    email\n  }\n}\n\nmutation CreateUser($input: CreateUserInput!) {\n  createUser(input: $input) {\n    id\n    name\n  }\n}\n```\n\nEach named operation becomes an MCP tool.\n\n### 2. Operation Collections\n\n```yaml\noperations:\n  source: collection\n  id: your-collection-id\n```\n\nUse GraphOS Studio to manage operations collaboratively.\n\n### 3. Persisted Queries\n\n```yaml\noperations:\n  source: manifest\n  path: .\u002Fpersisted-query-manifest.json\n```\n\nFor production environments with pre-approved operations.\n\n## Reference Files\n\nDetailed documentation for specific topics:\n\n- [Tools](references\u002Ftools.md) - Introspection tools and minify notation\n- [Configuration](references\u002Fconfiguration.md) - All configuration options\n- [Troubleshooting](references\u002Ftroubleshooting.md) - Common issues and solutions\n\n## Key Rules\n\n### Security\n\n- **Never expose sensitive operations** without authentication\n- Use `headers` configuration for API keys and tokens\n- Disable introspection tools in production (they are disabled by default)\n- Set `overrides.mutation_mode: explicit` to require confirmation for mutations\n\n### Authentication\n\n```yaml\n# Static header\nheaders:\n  Authorization: \"Bearer ${env.API_TOKEN}\"\n\n# Dynamic header forwarding\nforward_headers:\n  - x-forwarded-token\n\n# OAuth (streamable_http transport)\ntransport:\n  type: streamable_http\n  auth:\n    servers:\n      - https:\u002F\u002Fauth.example.com\u002F.well-known\u002Fopenid-configuration\n    audiences:\n      - https:\u002F\u002Fapi.example.com\n```\n\n### Token Optimization\n\nEnable minification to reduce token usage:\n\n```yaml\nintrospection:\n  introspect:\n    minify: true\n  search:\n    minify: true\n```\n\nMinified output uses compact notation:\n- **T** = type, **I** = input, **E** = enum\n- **s** = String, **i** = Int, **b** = Boolean, **f** = Float, **d** = ID\n- **!** = required, **[]** = list\n\n### Mutations\n\nControl mutation behavior via the `overrides` section:\n\n```yaml\noverrides:\n  mutation_mode: all       # Execute mutations directly\n  # mutation_mode: explicit  # Require explicit confirmation\n  # mutation_mode: none      # Block all mutations (default)\n```\n\n## Common Patterns\n\n### GraphOS Cloud Schema\n\n```yaml\n# schema.source defaults to uplink — can be omitted when graphos is configured\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: my-graph@production\n```\n\n### Local Development\n\n```yaml\ntransport:\n  type: streamable_http\nschema:\n  source: local\n  path: .\u002Fschema.graphql\nintrospection:\n  introspect:\n    enabled: true\n  search:\n    enabled: true\n  validate:\n    enabled: true\n  execute:\n    enabled: true\noverrides:\n  mutation_mode: all\n```\n\n### Production Setup\n\n```yaml\ntransport:\n  type: streamable_http\nendpoint: https:\u002F\u002Fapi.production.com\u002Fgraphql\noperations:\n  source: manifest\n  path: .\u002Fpersisted-query-manifest.json\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}\nheaders:\n  Authorization: \"Bearer ${env.API_TOKEN}\"\nhealth_check:\n  enabled: true\n```\n\n### Docker\n\n```yaml\ntransport:\n  type: streamable_http\n  address: 0.0.0.0\n  port: 8000\nendpoint: ${env.GRAPHQL_ENDPOINT}\ngraphos:\n  apollo_key: ${env.APOLLO_KEY}\n  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}\nhealth_check:\n  enabled: true\n```\n\n## Ground Rules\n\n- ALWAYS configure authentication before exposing to AI agents\n- ALWAYS use `mutation_mode: explicit` or `mutation_mode: none` in shared environments\n- NEVER expose introspection tools with write access to production data\n- PREFER operation files over ad-hoc execute for predictable behavior\n- PREFER streamable_http transport for remote and multi-client deployments\n- USE stdio only when the MCP client launches the server process directly\n- USE GraphOS Studio collections for team collaboration\n",{"name":5,"license":14,"metadata":51,"description":54,"allowed-tools":55,"compatibility":56},{"author":52,"version":53},"apollographql","1.1.0","Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute), (4) troubleshooting MCP server connectivity or tool execution issues.\n","Bash(rover:*) Bash(npx:*) Read Write Edit Glob Grep","Works with Claude Code, Claude Desktop, Cursor.","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add JSGforever\u002Fskillguard --skill apollo-mcp-server",{"tool":70,"command":71},"bunx","bunx skills add JSGforever\u002Fskillguard --skill apollo-mcp-server",{"tool":73,"command":74},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill apollo-mcp-server","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server\u002FSKILL.md",true,[78,84,88],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fconfiguration.md","REFERENCE","参考文档",8351,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server\u002Freferences\u002Fconfiguration.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Ftools.md",6093,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server\u002Freferences\u002Ftools.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ftroubleshooting.md",5591,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__apollographql--apollo-mcp-server\u002Freferences\u002Ftroubleshooting.md",[93,121,136,162,183,202],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"publishedAt":46},"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.","GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[100],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[102,103,104,105,106,107,108,109,110,111,112,113,41,114,115,116,117,118,119,120],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":132,"publishedAt":46},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[133,134,135],"data","data exfiltrator","files",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":46},"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",[],[143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,40,158,159,160,161],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","activate","optimizer","react","streaming",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":46},"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",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[152,172,159,160,173,174,175,176,177,178,143,179,180,156,40,39,158,161,181,182],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","router","strategies",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":46},"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",[189],{"categoryNo":169,"categoryName":170,"taxonomyType":20,"taxonomyTypeDesc":21},[191,161,192,193,194,195,152,143,196,197,198,40,158,159,199,160,200,201,27,37],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":215,"publishedAt":46},"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",[208,211,214],{"categoryNo":209,"categoryName":210,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":212,"categoryName":213,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[216,217,218,219,220,221,222,150,177,223,224,225,158,182,226,37,227,36,35,228],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","git"]