[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A79KBE80SPV86GMGFVSC7T":3,"skill-same:01M7A79KBE80SPV86GMGFVSC7T":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7A79KBE80SPV86GMGFVSC7T","mongodb-expert",null,"MongoDB document modeling, schema design, aggregation pipelines, transactions, change streams, and driver usage for Go and Python. Use when building document databases with flexible schemas, analytics pipelines, CDC, or migrating to AWS DocumentDB. Trigger: MongoDB, aggregation, indexing, transactions. Do NOT trigger for: relational DB design, SQL queries, PostgreSQL\u002FMySQL aggregation queries, window functions, caching patterns.","ronsilver\u002Fagent-covenant","ronsilver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F46677526?v=4","01M7A719H1DVMZSKNAESAC82DA","Jorge Maturana","01M7A719J5GP33TM303CB8NN00",1,"MIT","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fmongodb-expert\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mongodb-expert\ndescription: \"MongoDB document modeling, schema design, aggregation pipelines, transactions, change streams, and driver usage for Go and Python. Use when building document databases with flexible schemas, analytics pipelines, CDC, or migrating to AWS DocumentDB. Trigger: MongoDB, aggregation, indexing, transactions. Do NOT trigger for: relational DB design, SQL queries, PostgreSQL\u002FMySQL aggregation queries, window functions, caching patterns.\"\nlicense: MIT\nmetadata:\n  author: Community\n  version: \"1.0\"\n  category: data\n  status: stable\n---\n# MongoDB Expert\n\n**MongoDB Atlas + DocumentDB: schemas, aggregations and CDC.**\n\n## Core Stack\n\n- Database: MongoDB Atlas (analytics database), AWS DocumentDB compatible\n- Drivers: Go `mongo-driver`, Python `motor` (async)\n- Patterns: Embed vs Reference, aggregation pipelines, change streams\n- Operations: Multi-doc transactions, indexes, Atlas Search\n\n## Schema Design\n\n| Pattern | Use When | Example |\n|---|---|---|\n| Embed | Data read together, rarely changes independently | Record + line items |\n| Reference | Entities accessed independently, many-to-many | User -> Events |\n| Bucket | Time-series, IoT, event streams | Metrics per hour\u002Fday |\n\n```go\ntype Record struct {\n    ID         primitive.ObjectID `bson:\"_id,omitempty\"`\n    UserID     string             `bson:\"user_id\"`\n    Amount     int64              `bson:\"amount\"`     \u002F\u002F units\n    Category   string             `bson:\"category\"`\n    Items      []RecordItem       `bson:\"items\"`       \u002F\u002F embedded\n    CreatedAt  time.Time          `bson:\"created_at\"`\n}\n```\n\n## Aggregation Pipeline\n\n```go\npipeline := mongo.Pipeline{\n    {{Key: \"$match\", Value: bson.D{{Key: \"user_id\", Value: \"usr_123\"}}}},\n    {{Key: \"$group\", Value: bson.D{\n        {Key: \"_id\", Value: \"$category\"},\n        {Key: \"total\", Value: bson.D{{Key: \"$sum\", Value: \"$amount\"}}},\n        {Key: \"count\", Value: bson.D{{Key: \"$sum\", Value: 1}}},\n    }}},\n    {{Key: \"$sort\", Value: bson.D{{Key: \"total\", Value: -1}}}},\n}\ncursor, err := collection.Aggregate(ctx, pipeline)\n```\n\n## Indexes\n\n```go\n\u002F\u002F Compound index for query patterns\nindexModel := mongo.IndexModel{\n    Keys: bson.D{\n        {Key: \"customer_id\", Value: 1},\n        {Key: \"created_at\", Value: -1},\n    },\n}\ncollection.Indexes().CreateOne(ctx, indexModel)\n```\n\n- Index on query fields in ESR order (Equality -> Sort -> Range)\n- Use `explain()` to verify index usage\n\n## Change Streams (CDC)\n\n```go\nstream, err := collection.Watch(ctx, mongo.Pipeline{})\nfor stream.Next(ctx) {\n    var changeEvent bson.M\n    stream.Decode(&changeEvent)\n    \u002F\u002F process insert\u002Fupdate\u002Fdelete event\n}\n```\n\n## Constraints\n\n- NEVER use unbounded arrays in documents (can exceed 16MB limit)\n- NEVER skip indexes on query fields (full collection scan)\n- NEVER use `$lookup` without indexes on foreign field\n- ALWAYS use `context.Context` with timeouts on all operations\n- ALWAYS use transactions for multi-doc atomic updates\n- ALWAYS monitor slow queries via Atlas profiler\n- NEVER store unencrypted PII\u002FCHD in MongoDB documents\n\n## Security\n\n- NEVER concatenate user input into `$where`, `$expr`, or `$regex` — NoSQL operator injection\n- ALWAYS enable authentication and TLS for every MongoDB\u002FDocumentDB connection\n- ALWAYS use parameterized driver APIs (filter documents) — never raw JSON strings\n- ALWAYS encrypt at rest (Atlas encryption or KMS) and rotate credentials\n\n## Overview\n\nMongoDB Atlas is team document database for semi-structured data, flexible schemas, and high-write workloads (analytics database). This skill covers document schema design (embed vs reference), aggregation pipelines for analytics, compound and multikey index strategies, multi-document ACID transactions via sessions, change streams for CDC, and AWS DocumentDB compatibility for migration scenarios.\n\n## Quick Reference\n\n| Pattern | Decision Rule | Max Size |\n|---|---|---|\n| Embed | Data read together, sub-doc \u003C 16MB total | 16MB\u002Fdoc hard limit |\n| Reference | Entity accessed independently, M:N relations | No limit (separate collection) |\n| Bucket | Time-series, event streams, 1 doc per hour\u002Fday | 16MB\u002Fdoc hard limit |\n| Index | ESR rule: Equality → Sort → Range fields | 64 indices\u002Fcollection max |\n| Change Streams | Sequenced per shard, exactly-once with idempotency | 16MB event batch |\n| Transactions | Multi-doc ACID, max 60s duration | 1K doc limit per txn |\n\n## Workflow\n\n1. **Design documents** — Identify entity relationships. Embed sub-documents that are always read together and rarely change independently. Reference entities that are queried separately or have many-to-many relationships.\n2. **Build indexes** — Apply ESR order: Equality filters first, Sort keys second, Range scans last. Use `explain(\"executionStats\")` to verify IXSCAN (not COLLSCAN). Add compound indexes for multi-field queries.\n3. **Write aggregation pipelines** — Chain stages: `$match` (early filter) → `$group`\u002F`$sort` → `$project` (shape output). Use `$lookup` sparingly — prefer embedded docs. Add indexes on `$lookup` foreign fields.\n4. **Implement change streams** — Open `collection.Watch()` for CDC. Process in order per document key. Use `resumeAfter` with checkpoint token for at-least-once delivery.\n5. **Use transactions** — For multi-document atomicity: start session → start transaction → execute operations → commit. Keep transactions under 1000 documents and 60 seconds.\n6. **Monitor performance** — Atlas profiler for slow queries (>100ms). Index usage stats. Connection pool utilization. Replica set lag.\n\n## Anti-patterns\n\nFAIL: Unbounded array growth in a single document (will exceed 16MB).\n```go\n\u002F\u002F BAD: Embedded array grows forever\ntype AuditLog struct {\n    Entries []AuditEntry `bson:\"entries\"` \u002F\u002F thousands over time → 16MB+\n}\n```\n```go\n\u002F\u002F GOOD: Separate collection for high-cardinality sub-items\ntype AuditLog struct {\n    LogID   string `bson:\"_id\"`\n}\n\u002F\u002F Audit entries in separate collection with log_id reference\n```\n\nFAIL: Using `$lookup` without indexes on the foreign field.\n```go\n\u002F\u002F BAD: $lookup with no index on user_id in events collection\npipeline := bson.A{\n    bson.D{{Key: \"$lookup\", Value: bson.D{\n        {Key: \"from\", Value: \"events\"},\n        {Key: \"foreignField\", Value: \"user_id\"},\n    }}}\n}\n```\n```go\n\u002F\u002F GOOD: Create index first, then $lookup\neventsCollection.Indexes().CreateOne(ctx, mongo.IndexModel{\n    Keys: bson.D{{Key: \"user_id\", Value: 1}},\n})\n```\n\nFAIL: No timeout on database operations (goroutine leak under load).\n```go\n\u002F\u002F BAD: Default context — no timeout\ncursor, _ := collection.Find(context.Background(), bson.D{})\n```\n```go\n\u002F\u002F GOOD: Explicit timeout\nctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)\ndefer cancel()\ncursor, _ := collection.Find(ctx, bson.D{})\n```\n\n## References\n\n| Resource | URL | Last verified |\n|---|---|---|\n| MongoDB — Schema Design Best Practices | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002Fcore\u002Fdata-modeling-introduction\u002F | 2026-05-25 |\n| MongoDB — Aggregation Pipeline Reference | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002Faggregation\u002F | 2026-05-25 |\n| MongoDB — Change Streams Production Best Practices | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002FchangeStreams\u002F | 2026-05-25 |\n\n- [references\u002Faggregation.md](references\u002Faggregation.md)\n- [references\u002Findexing.md](references\u002Findexing.md)\n\n## Verification Checklist\n\n- [ ] Document schema designed with correct embed vs reference decision for access patterns\n- [ ] Indexes created following ESR order (Equality → Sort → Range) with `explain()` verification\n- [ ] `context.Context` with timeout used on all database operations\n- [ ] Aggregation pipeline stages ordered with early `$match` filter\n- [ ] No unbounded arrays in documents (16MB doc size limit)\n- [ ] `$lookup` foreign fields indexed to prevent full collection scans\n- [ ] Change streams idempotent with `resumeAfter` token for at-least-once delivery\n- [ ] No user input in `$where`\u002F`$expr`\u002F`$regex`; auth + TLS enabled on all connections\n\n## Troubleshooting\n\n| Symptom | Likely cause | Fix |\n|---|---|---|\n| Query returns COLLSCAN instead of IXSCAN | Missing index on filter fields or wrong index order | Run `explain(\"executionStats\")`; create compound index matching query ESR order |\n| `Document too large` error (16MB+ limit) | Embedded array grew unbounded over time | Split high-cardinality data into separate collection with reference |\n| Change stream disconnects on replica set election | `resumeAfter` token lost after primary change | Use `startAfter` instead of `resumeAfter` for global resumption across elections |\n| Known issue: `$lookup` with `let` variables silently returns empty arrays | Variable reference syntax error in `let` block or pipeline stage mismatch | Verify `let` variable names match exactly in `$expr`; test the pipeline stage in isolation before composing |\n| Gotcha: `$text` search requires a `text` index | Missing `text` index causes full COLLSCAN even on small collections | Create `text` index on the search field: `db.collection.createIndex({field: \"text\"})`; verify with `explain()` |\n| [WARN] Known limitation: change stream `$lookup` results may be stale | Change events captured before `$lookup` target documents are fully committed | Use post-image or transactional consistency guarantees; avoid `$lookup` in change stream pipeline when cross-document consistency is required |\n","# MongoDB Expert\n\n**MongoDB Atlas + DocumentDB: schemas, aggregations and CDC.**\n\n## Core Stack\n\n- Database: MongoDB Atlas (analytics database), AWS DocumentDB compatible\n- Drivers: Go `mongo-driver`, Python `motor` (async)\n- Patterns: Embed vs Reference, aggregation pipelines, change streams\n- Operations: Multi-doc transactions, indexes, Atlas Search\n\n## Schema Design\n\n| Pattern | Use When | Example |\n|---|---|---|\n| Embed | Data read together, rarely changes independently | Record + line items |\n| Reference | Entities accessed independently, many-to-many | User -> Events |\n| Bucket | Time-series, IoT, event streams | Metrics per hour\u002Fday |\n\n```go\ntype Record struct {\n    ID         primitive.ObjectID `bson:\"_id,omitempty\"`\n    UserID     string             `bson:\"user_id\"`\n    Amount     int64              `bson:\"amount\"`     \u002F\u002F units\n    Category   string             `bson:\"category\"`\n    Items      []RecordItem       `bson:\"items\"`       \u002F\u002F embedded\n    CreatedAt  time.Time          `bson:\"created_at\"`\n}\n```\n\n## Aggregation Pipeline\n\n```go\npipeline := mongo.Pipeline{\n    {{Key: \"$match\", Value: bson.D{{Key: \"user_id\", Value: \"usr_123\"}}}},\n    {{Key: \"$group\", Value: bson.D{\n        {Key: \"_id\", Value: \"$category\"},\n        {Key: \"total\", Value: bson.D{{Key: \"$sum\", Value: \"$amount\"}}},\n        {Key: \"count\", Value: bson.D{{Key: \"$sum\", Value: 1}}},\n    }}},\n    {{Key: \"$sort\", Value: bson.D{{Key: \"total\", Value: -1}}}},\n}\ncursor, err := collection.Aggregate(ctx, pipeline)\n```\n\n## Indexes\n\n```go\n\u002F\u002F Compound index for query patterns\nindexModel := mongo.IndexModel{\n    Keys: bson.D{\n        {Key: \"customer_id\", Value: 1},\n        {Key: \"created_at\", Value: -1},\n    },\n}\ncollection.Indexes().CreateOne(ctx, indexModel)\n```\n\n- Index on query fields in ESR order (Equality -> Sort -> Range)\n- Use `explain()` to verify index usage\n\n## Change Streams (CDC)\n\n```go\nstream, err := collection.Watch(ctx, mongo.Pipeline{})\nfor stream.Next(ctx) {\n    var changeEvent bson.M\n    stream.Decode(&changeEvent)\n    \u002F\u002F process insert\u002Fupdate\u002Fdelete event\n}\n```\n\n## Constraints\n\n- NEVER use unbounded arrays in documents (can exceed 16MB limit)\n- NEVER skip indexes on query fields (full collection scan)\n- NEVER use `$lookup` without indexes on foreign field\n- ALWAYS use `context.Context` with timeouts on all operations\n- ALWAYS use transactions for multi-doc atomic updates\n- ALWAYS monitor slow queries via Atlas profiler\n- NEVER store unencrypted PII\u002FCHD in MongoDB documents\n\n## Security\n\n- NEVER concatenate user input into `$where`, `$expr`, or `$regex` — NoSQL operator injection\n- ALWAYS enable authentication and TLS for every MongoDB\u002FDocumentDB connection\n- ALWAYS use parameterized driver APIs (filter documents) — never raw JSON strings\n- ALWAYS encrypt at rest (Atlas encryption or KMS) and rotate credentials\n\n## Overview\n\nMongoDB Atlas is team document database for semi-structured data, flexible schemas, and high-write workloads (analytics database). This skill covers document schema design (embed vs reference), aggregation pipelines for analytics, compound and multikey index strategies, multi-document ACID transactions via sessions, change streams for CDC, and AWS DocumentDB compatibility for migration scenarios.\n\n## Quick Reference\n\n| Pattern | Decision Rule | Max Size |\n|---|---|---|\n| Embed | Data read together, sub-doc \u003C 16MB total | 16MB\u002Fdoc hard limit |\n| Reference | Entity accessed independently, M:N relations | No limit (separate collection) |\n| Bucket | Time-series, event streams, 1 doc per hour\u002Fday | 16MB\u002Fdoc hard limit |\n| Index | ESR rule: Equality → Sort → Range fields | 64 indices\u002Fcollection max |\n| Change Streams | Sequenced per shard, exactly-once with idempotency | 16MB event batch |\n| Transactions | Multi-doc ACID, max 60s duration | 1K doc limit per txn |\n\n## Workflow\n\n1. **Design documents** — Identify entity relationships. Embed sub-documents that are always read together and rarely change independently. Reference entities that are queried separately or have many-to-many relationships.\n2. **Build indexes** — Apply ESR order: Equality filters first, Sort keys second, Range scans last. Use `explain(\"executionStats\")` to verify IXSCAN (not COLLSCAN). Add compound indexes for multi-field queries.\n3. **Write aggregation pipelines** — Chain stages: `$match` (early filter) → `$group`\u002F`$sort` → `$project` (shape output). Use `$lookup` sparingly — prefer embedded docs. Add indexes on `$lookup` foreign fields.\n4. **Implement change streams** — Open `collection.Watch()` for CDC. Process in order per document key. Use `resumeAfter` with checkpoint token for at-least-once delivery.\n5. **Use transactions** — For multi-document atomicity: start session → start transaction → execute operations → commit. Keep transactions under 1000 documents and 60 seconds.\n6. **Monitor performance** — Atlas profiler for slow queries (>100ms). Index usage stats. Connection pool utilization. Replica set lag.\n\n## Anti-patterns\n\nFAIL: Unbounded array growth in a single document (will exceed 16MB).\n```go\n\u002F\u002F BAD: Embedded array grows forever\ntype AuditLog struct {\n    Entries []AuditEntry `bson:\"entries\"` \u002F\u002F thousands over time → 16MB+\n}\n```\n```go\n\u002F\u002F GOOD: Separate collection for high-cardinality sub-items\ntype AuditLog struct {\n    LogID   string `bson:\"_id\"`\n}\n\u002F\u002F Audit entries in separate collection with log_id reference\n```\n\nFAIL: Using `$lookup` without indexes on the foreign field.\n```go\n\u002F\u002F BAD: $lookup with no index on user_id in events collection\npipeline := bson.A{\n    bson.D{{Key: \"$lookup\", Value: bson.D{\n        {Key: \"from\", Value: \"events\"},\n        {Key: \"foreignField\", Value: \"user_id\"},\n    }}}\n}\n```\n```go\n\u002F\u002F GOOD: Create index first, then $lookup\neventsCollection.Indexes().CreateOne(ctx, mongo.IndexModel{\n    Keys: bson.D{{Key: \"user_id\", Value: 1}},\n})\n```\n\nFAIL: No timeout on database operations (goroutine leak under load).\n```go\n\u002F\u002F BAD: Default context — no timeout\ncursor, _ := collection.Find(context.Background(), bson.D{})\n```\n```go\n\u002F\u002F GOOD: Explicit timeout\nctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)\ndefer cancel()\ncursor, _ := collection.Find(ctx, bson.D{})\n```\n\n## References\n\n| Resource | URL | Last verified |\n|---|---|---|\n| MongoDB — Schema Design Best Practices | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002Fcore\u002Fdata-modeling-introduction\u002F | 2026-05-25 |\n| MongoDB — Aggregation Pipeline Reference | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002Faggregation\u002F | 2026-05-25 |\n| MongoDB — Change Streams Production Best Practices | https:\u002F\u002Fwww.mongodb.com\u002Fdocs\u002Fmanual\u002FchangeStreams\u002F | 2026-05-25 |\n\n- [references\u002Faggregation.md](references\u002Faggregation.md)\n- [references\u002Findexing.md](references\u002Findexing.md)\n\n## Verification Checklist\n\n- [ ] Document schema designed with correct embed vs reference decision for access patterns\n- [ ] Indexes created following ESR order (Equality → Sort → Range) with `explain()` verification\n- [ ] `context.Context` with timeout used on all database operations\n- [ ] Aggregation pipeline stages ordered with early `$match` filter\n- [ ] No unbounded arrays in documents (16MB doc size limit)\n- [ ] `$lookup` foreign fields indexed to prevent full collection scans\n- [ ] Change streams idempotent with `resumeAfter` token for at-least-once delivery\n- [ ] No user input in `$where`\u002F`$expr`\u002F`$regex`; auth + TLS enabled on all connections\n\n## Troubleshooting\n\n| Symptom | Likely cause | Fix |\n|---|---|---|\n| Query returns COLLSCAN instead of IXSCAN | Missing index on filter fields or wrong index order | Run `explain(\"executionStats\")`; create compound index matching query ESR order |\n| `Document too large` error (16MB+ limit) | Embedded array grew unbounded over time | Split high-cardinality data into separate collection with reference |\n| Change stream disconnects on replica set election | `resumeAfter` token lost after primary change | Use `startAfter` instead of `resumeAfter` for global resumption across elections |\n| Known issue: `$lookup` with `let` variables silently returns empty arrays | Variable reference syntax error in `let` block or pipeline stage mismatch | Verify `let` variable names match exactly in `$expr`; test the pipeline stage in isolation before composing |\n| Gotcha: `$text` search requires a `text` index | Missing `text` index causes full COLLSCAN even on small collections | Create `text` index on the search field: `db.collection.createIndex({field: \"text\"})`; verify with `explain()` |\n| [WARN] Known limitation: change stream `$lookup` results may be stale | Change events captured before `$lookup` target documents are fully committed | Use post-image or transactional consistency guarantees; avoid `$lookup` in change stream pipeline when cross-document consistency is required |\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":25,"status":26,"version":27,"category":28},"Community","stable","1.0","data","main","6692ee5cbe39d4533b824e1c55d7d4fc01c4dde7","content\u002Fskills\u002Fmongodb-expert",0,"https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant","https:\u002F\u002Fgithub.com\u002Fronsilver",":v","2026-08-27 05:49:26",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add ronsilver\u002Fagent-covenant --skill mongodb-expert",{"tool":43,"command":44},"bunx","bunx skills add ronsilver\u002Fagent-covenant --skill mongodb-expert",{"tool":46,"command":47},"pnpm","pnpm dlx skills add ronsilver\u002Fagent-covenant --skill mongodb-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fmongodb-expert\u002FSKILL.md",true,[51,57,61],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Fevals.json","REFERENCE","参考文档",2673,"https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fmongodb-expert\u002Fevals\u002Fevals.json",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Faggregation.md",697,"https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fmongodb-expert\u002Freferences\u002Faggregation.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Findexing.md",744,"https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fmongodb-expert\u002Freferences\u002Findexing.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7A7HYVYNZ60GNGWAV51ZQ52","web-browsing-agent-expert","Web browsing for AI agents: driving a headless browser (Playwright, Puppeteer) from agent tooling, navigation and page-state grounding, DOM extraction and structured data capture, form interaction, session and cookie management, anti-bot mitigation awareness, and safe browsing rules (no PII exfiltration, respect robots and terms). Use when building a browsing tool or MCP server for an agent, teaching an agent to navigate and read web pages, extracting structured content from dynamic sites, or handling login walls and pagination in agent workflows. Trigger: web browsing agent, headless browser, Playwright MCP, Puppeteer, browser automation for agents, DOM extraction, page navigation, session management. Do NOT trigger for: end-to-end UI testing of an application (use playwright-expert); writing standalone scraping scripts for data pipelines (use python-expert); fetching a single public URL (use the fetch tool).","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fweb-browsing-agent-expert\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7A7HRC6951BAJ9NHBZA2M7Y","vector-databases","Design and operate vector databases for cloud-native AI features. Use when selecting between pgvector, Pinecone, or Weaviate for AI context layer or integration-hub; designing embedding schemas and index parameters; implementing ANN search with metadata filtering; managing embedding model versions; optimizing query latency; or debugging low retrieval quality. Pairs with rag-architecture for pipeline design and postgres-database-expert for pgvector specifics. Trigger: vector database, pgvector, Pinecone, Weaviate, embedding, ANN search, HNSW, cosine similarity. Do NOT trigger for: relational SQL optimization, standard PostgreSQL schema design, Redis caching.","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fvector-databases\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7A7HGHGWE7NZ5A08HQZJXDN","typescript-expert","Full-stack TypeScript stack for modern projects: frontend SSR\u002FCSR with Next.js 14 App Router and React, backend APIs with Node.js (Express\u002FFastify), state management with Zustand\u002FRedux Toolkit, unit and integration testing with Vitest\u002FJest + React Testing Library + MSW, and static analysis with ESLint\u002FPrettier\u002Ftsc. Use when building React components or hooks, implementing Next.js App Router or Server Components, writing Node.js REST API handlers, implementing middleware (auth, rate-limit, logging), managing client state (Zustand\u002FRTK), writing frontend\u002Fbackend tests, or running TypeScript linting\u002Ftype checks. Trigger: TypeScript, Next.js, React, Zustand, Node.js, Express, Fastify, MSW, Vitest. Do NOT trigger for: Python backend development, Go microservices, iOS\u002Fmobile development.","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Ftypescript-expert\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7A7H83JK9SENNYAPTTB6B4A","tool-usage","Guide correct tool selection, design, and orchestration for AI agents. Use when choosing between dedicated vs Bash tools, designing MCP tool interfaces, naming tool parameters, handling tool response limits, orchestrating parallel vs sequential calls, evaluating tool accuracy, applying ACI design principles, selecting workflow patterns, or reading\u002Ffiltering\u002Ftransforming\u002Fgenerating structured data (JSON, YAML, CSV, TOML, XML). Trigger: tool selection, MCP tool design, orchestration, ACI, parallel execution, composite tool, structured data, jq, yq, dasel, mlr, csvkit. Do NOT trigger for: writing application business logic, domain-specific development (route to domain skill), database migrations.","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Ftool-usage\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7A7GZ9A2VA9T7BJ07VV3PD5","token-efficiency","Enforce token-efficient output, compression, caching, and model routing. Use when calibrating response verbosity, applying compression strategies to logs or RAG chunks, routing tasks to the right model tier, setting thinking budgets, enforcing word limits, compressing context before reinitiation, applying KV-cache ordering, masking tool output observations, or applying clarification-first protocol before irreversible actions. Trigger: token efficiency, compression, model routing, thinking budget, KV-cache, clarification protocol. Do NOT trigger for: non-agent tooling, CI\u002FCD pipeline scripting, infrastructure provisioning.","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Ftoken-efficiency\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7A7GQFTY8GWVN4Z66Q4J52V","time-series-db","Time-series database patterns for cloud-native metrics and analytics: TimescaleDB, InfluxDB, and Amazon Timestream selection; continuous aggregates, retention policies, downsampling, and integration with Prometheus\u002FGrafana. Use when storing business metrics over time, building custom business dashboards, designing high-frequency event storage, or querying time-bucketed aggregations. Trigger: time-series, TimescaleDB, InfluxDB, Prometheus, Grafana, hypertable, continuous aggregate, retention policy. Do NOT trigger for: relational PostgreSQL schema design, NoSQL document stores, Kafka event streaming.","https:\u002F\u002Fgithub.com\u002Fronsilver\u002Fagent-covenant\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Ftime-series-db\u002FSKILL.md",[],[]]