[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FZJ1VX03460J25516MB5G":3,"skill-same:01M71FZJ1VX03460J25516MB5G":89},{"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":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M71FZJ1VX03460J25516MB5G","supabase",null,"Database operations for Supabase: query\u002Fwrite\u002Fmigration\u002Flogs\u002Ftype generation. Triggers: query\u002Fstatistics\u002Fexport\u002Finsert\u002Fupdate\u002Fdelete\u002Ffix\u002Fbackfill\u002Fmigrate\u002Flogs\u002Falerts\u002Ftype generation. Does not trigger for: pure architecture discussion or code planning. Write operations require confirmation; UPDATE\u002FDELETE without WHERE is refused. MCP is optional — works with CLI\u002FConsole too.","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__Heyvhuang--supabase\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",[5,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"migrate","database operations","statistics","alerts","query","export","fix","write","read","confirmation","MCP","Bash","logs","database","code","update","delete","architecture","cli","2026-11-10 10:12:30",false,"---\nname: supabase\ndescription: \"Database operations for Supabase: query\u002Fwrite\u002Fmigration\u002Flogs\u002Ftype generation. Triggers: query\u002Fstatistics\u002Fexport\u002Finsert\u002Fupdate\u002Fdelete\u002Ffix\u002Fbackfill\u002Fmigrate\u002Flogs\u002Falerts\u002Ftype generation. Does not trigger for: pure architecture discussion or code planning. Write operations require confirmation; UPDATE\u002FDELETE without WHERE is refused. MCP is optional — works with CLI\u002FConsole too.\"\nallowed-tools:\n  - Read\n  - Bash\n  - WebFetch\n  - supabase-*\n---\n\n# Supabase Database Operations\n\nExecute database operations on Supabase: queries, writes, migrations, and diagnostics.\n\n> **MCP is optional.** This skill works with MCP (auto), Supabase CLI, psql, or Dashboard. See [BACKENDS.md](BACKENDS.md) for execution options.\n\n## Scope\n\n**Applies to:**\n- Database actions on Supabase: query\u002Fstatistics\u002Fexport, write (after confirmation), migration (DDL), type generation, query logs\u002Fadvisors\n\n**Does not apply to:**\n- Project-side integration (env\u002Fclient code\u002Fdata access layer)  \n  → Use `workflow-ship-faster` (Step 6) for project setup; this skill handles DB-side actions only\n\n**Called by:**\n- `workflow-ship-faster` uses this skill as DB operation foundation\n\n## Postgres Best Practices (Built-in)\n\nShip Faster vendors Supabase's Postgres best practices under `references\u002Fpostgres-best-practices\u002F`.\n\nConsult it when:\n- Writing\u002Freviewing\u002Foptimizing SQL queries\n- Designing indexes, schema changes, or RLS policies\n- Diagnosing performance, locking, or connection issues\n\nSource of truth:\n- Full guide: `references\u002Fpostgres-best-practices\u002FAGENTS.md`\n- Individual rules: `references\u002Fpostgres-best-practices\u002Frules\u002F*.md`\n\nWhen proposing changes, cite the relevant rule file path (for example: `references\u002Fpostgres-best-practices\u002Frules\u002Fquery-missing-indexes.md`) and keep changes minimal.\n\n## Security Rules (Must Follow)\n\n1. **Read first**: Always check schema before any operation\n2. **Default LIMIT 50**: All SELECT queries default to `LIMIT 50`, unless user explicitly requests more\n3. **Write operation confirmation**: INSERT\u002FUPDATE\u002FDELETE must before execution:\n   - Display the SQL to be executed\n   - State expected number of affected rows\n   - Await explicit user confirmation\n4. **No bare writes**: UPDATE\u002FDELETE without WHERE condition → refuse directly, do not execute\n5. **Batch threshold**: Affecting > 100 rows → force double confirmation + suggest `SELECT count(*)` first\n6. **DDL via migration**: Schema changes must use migrations, not direct DDL\n7. **Production environment**: Write disabled by default; only allow when user explicitly says \"execute on prod\" and double confirms\n8. **Sensitive fields**: email\u002Fphone\u002Ftoken\u002Fpassword are masked or not returned by default, unless user explicitly requests\n\n## Operation Flow\n\n```\n1. Parse requirements → restate objective\n2. Unsure about tables\u002Ffields → first query schema (information_schema or list_tables)\n3. Plan SQL → present to user\n4. Read-only → execute directly\n5. Write operation → confirm before execution → verify affected rows → report result\n```\n\n## File-based Pipeline\n\nWhen integrating into multi-step workflows, persist artifacts to disk:\n\n```\nruns\u002F\u003Cworkflow>\u002Factive\u002F\u003Crun_id>\u002F\n├── proposal.md                # Requirements \u002F objective\n├── context.json               # Known tables\u002Ffields\u002FIDs\n├── tasks.md                   # Checklist + approval gate\n├── evidence\u002Fsql.md            # SQL to execute (write ops written here first)\n├── evidence\u002Fresult.md         # Conclusion + SQL + results\n└── logs\u002Fevents.jsonl          # Optional tool call summary (no sensitive data)\n```\n\n## Output Format\n\n- **Language**: English\n- **Structure**: Conclusion → Key numbers → Executed SQL → Result table (max 50 rows)\n- **Overflow handling**: Truncate + show total count + optional export\u002Fpagination\n\nExample:\n```\n✅ Query complete: 142 new users in the last 7 days\n\nExecuted SQL:\nSELECT DATE(created_at) as date, COUNT(*) as count \nFROM user_profiles \nWHERE created_at > NOW() - INTERVAL '7 days'\nGROUP BY DATE(created_at) ORDER BY date DESC;\n\n| date       | count |\n|------------|-------|\n| 2025-01-09 | 23    |\n| 2025-01-08 | 31    |\n| ...        | ...   |\n```\n\n## Error Handling\n\n| Situation | Action |\n|-----------|--------|\n| SQL syntax error | Return error summary + fix suggestions |\n| Insufficient permissions | Explain required permissions + alternatives |\n| No data returned | Explain possible reasons (conditions too strict? data doesn't exist?) |\n| RLS blocked | Suggest checking RLS policy or using service_role |\n\n## Example Workflows\n\n### Read: Simple Query\n```\nUser: Get registered user count for the last 7 days, by day\n\n1. Confirm table user_profiles, field created_at\n2. Execute aggregation SQL\n3. Return: conclusion + numbers + SQL + table\n```\n\n### Read: Complex Query\n```\nUser: Find projects that have runs but all failed\n\n1. Confirm projects, runs tables and status field\n2. Present JOIN + aggregation SQL\n3. Execute and return results (mask email)\n```\n\n### Write: Insert\n```\nUser: Create a new run for project xxx\n\n1. First check if project exists\n2. Present INSERT SQL + expected impact: 1 row\n3. Await confirmation → execute → return new record id\n```\n\n### Write: Update\n```\nUser: Change run abc's status to completed\n\n1. First SELECT to verify current state\n2. Present UPDATE SQL + WHERE id = 'abc'\n3. Confirm → execute → SELECT again to verify\n```\n\n### Dangerous: Delete\n```\nUser: Delete all runs where status = 'failed'\n\n1. First SELECT count(*) WHERE status = 'failed'\n2. Present count + DELETE SQL\n3. If > 100 rows, force double confirmation\n4. After confirmation execute → report deleted row count\n```\n\n### Dangerous: DELETE without WHERE\n```\nUser: Clear the runs table\n\n❌ Refuse to execute\n→ Prompt: DELETE without WHERE condition, this will delete all data\n→ Suggest: Use TRUNCATE (requires migration) or add explicit condition\n```\n\n## Schema Discovery\n\nGet latest schema at runtime:\n```sql\n-- List all tables\nSELECT table_name FROM information_schema.tables \nWHERE table_schema = 'public';\n\n-- View table structure\nSELECT column_name, data_type, is_nullable \nFROM information_schema.columns \nWHERE table_name = '\u003Ctable_name>';\n```\n\nFor project-specific schema (may be outdated), see [schema.md](schema.md).\n\n## Related Files\n\n- [BACKENDS.md](BACKENDS.md) — Execution options (MCP\u002FCLI\u002FConsole)\n- [SETUP.md](SETUP.md) — MCP configuration (optional)\n- [schema.md](schema.md) — Project-specific schema reference\n","# Supabase Database Operations\n\nExecute database operations on Supabase: queries, writes, migrations, and diagnostics.\n\n> **MCP is optional.** This skill works with MCP (auto), Supabase CLI, psql, or Dashboard. See [BACKENDS.md](BACKENDS.md) for execution options.\n\n## Scope\n\n**Applies to:**\n- Database actions on Supabase: query\u002Fstatistics\u002Fexport, write (after confirmation), migration (DDL), type generation, query logs\u002Fadvisors\n\n**Does not apply to:**\n- Project-side integration (env\u002Fclient code\u002Fdata access layer)  \n  → Use `workflow-ship-faster` (Step 6) for project setup; this skill handles DB-side actions only\n\n**Called by:**\n- `workflow-ship-faster` uses this skill as DB operation foundation\n\n## Postgres Best Practices (Built-in)\n\nShip Faster vendors Supabase's Postgres best practices under `references\u002Fpostgres-best-practices\u002F`.\n\nConsult it when:\n- Writing\u002Freviewing\u002Foptimizing SQL queries\n- Designing indexes, schema changes, or RLS policies\n- Diagnosing performance, locking, or connection issues\n\nSource of truth:\n- Full guide: `references\u002Fpostgres-best-practices\u002FAGENTS.md`\n- Individual rules: `references\u002Fpostgres-best-practices\u002Frules\u002F*.md`\n\nWhen proposing changes, cite the relevant rule file path (for example: `references\u002Fpostgres-best-practices\u002Frules\u002Fquery-missing-indexes.md`) and keep changes minimal.\n\n## Security Rules (Must Follow)\n\n1. **Read first**: Always check schema before any operation\n2. **Default LIMIT 50**: All SELECT queries default to `LIMIT 50`, unless user explicitly requests more\n3. **Write operation confirmation**: INSERT\u002FUPDATE\u002FDELETE must before execution:\n   - Display the SQL to be executed\n   - State expected number of affected rows\n   - Await explicit user confirmation\n4. **No bare writes**: UPDATE\u002FDELETE without WHERE condition → refuse directly, do not execute\n5. **Batch threshold**: Affecting > 100 rows → force double confirmation + suggest `SELECT count(*)` first\n6. **DDL via migration**: Schema changes must use migrations, not direct DDL\n7. **Production environment**: Write disabled by default; only allow when user explicitly says \"execute on prod\" and double confirms\n8. **Sensitive fields**: email\u002Fphone\u002Ftoken\u002Fpassword are masked or not returned by default, unless user explicitly requests\n\n## Operation Flow\n\n```\n1. Parse requirements → restate objective\n2. Unsure about tables\u002Ffields → first query schema (information_schema or list_tables)\n3. Plan SQL → present to user\n4. Read-only → execute directly\n5. Write operation → confirm before execution → verify affected rows → report result\n```\n\n## File-based Pipeline\n\nWhen integrating into multi-step workflows, persist artifacts to disk:\n\n```\nruns\u002F\u003Cworkflow>\u002Factive\u002F\u003Crun_id>\u002F\n├── proposal.md                # Requirements \u002F objective\n├── context.json               # Known tables\u002Ffields\u002FIDs\n├── tasks.md                   # Checklist + approval gate\n├── evidence\u002Fsql.md            # SQL to execute (write ops written here first)\n├── evidence\u002Fresult.md         # Conclusion + SQL + results\n└── logs\u002Fevents.jsonl          # Optional tool call summary (no sensitive data)\n```\n\n## Output Format\n\n- **Language**: English\n- **Structure**: Conclusion → Key numbers → Executed SQL → Result table (max 50 rows)\n- **Overflow handling**: Truncate + show total count + optional export\u002Fpagination\n\nExample:\n```\n✅ Query complete: 142 new users in the last 7 days\n\nExecuted SQL:\nSELECT DATE(created_at) as date, COUNT(*) as count \nFROM user_profiles \nWHERE created_at > NOW() - INTERVAL '7 days'\nGROUP BY DATE(created_at) ORDER BY date DESC;\n\n| date       | count |\n|------------|-------|\n| 2025-01-09 | 23    |\n| 2025-01-08 | 31    |\n| ...        | ...   |\n```\n\n## Error Handling\n\n| Situation | Action |\n|-----------|--------|\n| SQL syntax error | Return error summary + fix suggestions |\n| Insufficient permissions | Explain required permissions + alternatives |\n| No data returned | Explain possible reasons (conditions too strict? data doesn't exist?) |\n| RLS blocked | Suggest checking RLS policy or using service_role |\n\n## Example Workflows\n\n### Read: Simple Query\n```\nUser: Get registered user count for the last 7 days, by day\n\n1. Confirm table user_profiles, field created_at\n2. Execute aggregation SQL\n3. Return: conclusion + numbers + SQL + table\n```\n\n### Read: Complex Query\n```\nUser: Find projects that have runs but all failed\n\n1. Confirm projects, runs tables and status field\n2. Present JOIN + aggregation SQL\n3. Execute and return results (mask email)\n```\n\n### Write: Insert\n```\nUser: Create a new run for project xxx\n\n1. First check if project exists\n2. Present INSERT SQL + expected impact: 1 row\n3. Await confirmation → execute → return new record id\n```\n\n### Write: Update\n```\nUser: Change run abc's status to completed\n\n1. First SELECT to verify current state\n2. Present UPDATE SQL + WHERE id = 'abc'\n3. Confirm → execute → SELECT again to verify\n```\n\n### Dangerous: Delete\n```\nUser: Delete all runs where status = 'failed'\n\n1. First SELECT count(*) WHERE status = 'failed'\n2. Present count + DELETE SQL\n3. If > 100 rows, force double confirmation\n4. After confirmation execute → report deleted row count\n```\n\n### Dangerous: DELETE without WHERE\n```\nUser: Clear the runs table\n\n❌ Refuse to execute\n→ Prompt: DELETE without WHERE condition, this will delete all data\n→ Suggest: Use TRUNCATE (requires migration) or add explicit condition\n```\n\n## Schema Discovery\n\nGet latest schema at runtime:\n```sql\n-- List all tables\nSELECT table_name FROM information_schema.tables \nWHERE table_schema = 'public';\n\n-- View table structure\nSELECT column_name, data_type, is_nullable \nFROM information_schema.columns \nWHERE table_name = '\u003Ctable_name>';\n```\n\nFor project-specific schema (may be outdated), see [schema.md](schema.md).\n\n## Related Files\n\n- [BACKENDS.md](BACKENDS.md) — Execution options (MCP\u002FCLI\u002FConsole)\n- [SETUP.md](SETUP.md) — MCP configuration (optional)\n- [schema.md](schema.md) — Project-specific schema reference\n",{"name":5,"description":7,"allowed-tools":50},[51,37,52,53],"Read","WebFetch","supabase-*","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Heyvhuang--supabase",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add JSGforever\u002Fskillguard --skill supabase",{"tool":67,"command":68},"bunx","bunx skills add JSGforever\u002Fskillguard --skill supabase",{"tool":70,"command":71},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill supabase","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Heyvhuang--supabase\u002FSKILL.md",true,[75,81,85],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"BACKENDS.md","REFERENCE","参考文档",3498,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Heyvhuang--supabase\u002FBACKENDS.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"schema.md",5012,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Heyvhuang--supabase\u002Fschema.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"SETUP.md",2397,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Heyvhuang--supabase\u002FSETUP.md",[90,118,134,160,181,201],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":97,"publishedAt":45},"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",[96],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":122,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":130,"publishedAt":45},"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",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[131,132,133],"data","data exfiltrator","files",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":45},"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",[],[141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,37,156,157,158,159],"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":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":45},"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",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[150,170,157,158,171,172,173,174,175,176,141,177,178,154,37,40,156,159,179,180],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","router","strategies",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":45},"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",[187],{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},[189,159,190,191,192,193,150,141,194,195,196,37,156,157,197,158,198,199,200,34],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":214,"publishedAt":45},"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",[207,210,213],{"categoryNo":208,"categoryName":209,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":211,"categoryName":212,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[215,216,217,218,219,220,221,148,175,222,223,224,156,180,225,34,226,33,227,228],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","edit","git"]