[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718TH5NF35VXQCKC4EATW5W":3,"skill-same:01M718TH5NF35VXQCKC4EATW5W":118},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M718TH5NF35VXQCKC4EATW5W","oma-db",null,"Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model, vector index design, RAG retrieval architecture, migration, query tuning, glossary, capacity estimation, backup strategy, database anti-pattern remediation work, and ISO 27001, ISO 27002, or ISO 22301-aware database recommendations.","vasceannie\u002Fslopgate","vasceannie","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20271133?v=4","01M718RGA8VV2EF22XJEMXVQ0Q","Travis Vasceannie","01M718RGB0GWSXBBZBN67Q6NHQ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"oma db","db","recommendations","concurrency","vector database","work","indexing","transactions","review","architecture","query","database","glossary","estimation","design","vector","iso","model","database specialist","backup strategy","2026-11-10 10:12:30",false,"---\nname: oma-db\ndescription: Database specialist for SQL, NoSQL, and vector database modeling,\n  schema design, normalization, indexing, transactions, integrity, concurrency\n  control, backup, capacity planning, data standards, anti-pattern review, and\n  compliance-aware database design. Use for database, schema, ERD, table design,\n  document model, vector index design, RAG retrieval architecture, migration,\n  query tuning, glossary, capacity estimation, backup strategy, database\n  anti-pattern remediation work, and ISO 27001, ISO 27002, or ISO 22301-aware\n  database recommendations.\n---\n\n# DB Agent - Data Modeling & Database Architecture Specialist\n\n## Scheduling\n\n### Goal\nDesign, review, optimize, and document SQL, NoSQL, vector, and retrieval-oriented data systems with explicit schema layers, integrity rules, transaction behavior, capacity assumptions, and audit-aware tradeoffs.\n\n### Intent signature\n- User asks about database, schema, ERD, table design, document model, vector index, RAG retrieval, migration, query tuning, glossary, backup, capacity, or database anti-patterns.\n- User needs database recommendations aligned with security, continuity, integrity, or compliance concerns.\n\n### When to use\n- Relational database modeling, ERD, and schema design\n- NoSQL document, key-value, wide-column, or graph data modeling\n- Vector database and retrieval architecture design for semantic search and RAG\n- SQL\u002FNoSQL technology selection and tradeoff analysis\n- Normalization, denormalization, indexing, and partitioning\n- Transaction design, locking, isolation level, and concurrency control\n- Data standards, glossary, naming rules, and metadata governance\n- Capacity estimation, storage planning, hot\u002Fcold data separation, and backup strategy\n- Database anti-pattern review and remediation guidance\n- ISO 27001, ISO 27002, and ISO 22301-aware database design recommendations\n\n### When NOT to use\n- API-only implementation without schema impact -> use Backend Agent\n- Infra provisioning only -> use TF Infra Agent\n- Final quality\u002Fsecurity audit -> use QA Agent\n\n### Expected inputs\n- Business entities, events, access patterns, volume, latency, retention, and recovery targets\n- Existing schema, queries, migrations, indexes, data standards, or retrieval pipeline context\n- Consistency, transaction, backup, audit, and compliance constraints\n- Optional target deliverable such as ERD, migration plan, glossary, or capacity estimate\n\n### Expected outputs\n- External, conceptual, and internal schema documentation\n- Data standards, glossary, capacity estimate, indexing\u002Fpartitioning plan, and backup\u002Frecovery strategy\n- Integrity, transaction, isolation, and concurrency recommendations\n- Vector\u002FRAG-specific embedding, chunking, filtering, reranking, and re-index plans when relevant\n\n### Dependencies\n- Existing database schemas, migration files, query logs, workload descriptions, and application access paths\n- `resources\u002Fdocument-templates.md`, `resources\u002Fanti-patterns.md`, `resources\u002Fvector-db.md`, `resources\u002Fiso-controls.md`, `resources\u002Fmigration-playbook.md`, and `resources\u002Fquery-tuning.md`\n- SQL\u002FNoSQL\u002Fvector database tools or project-specific migration toolchains when implementation is requested\n\n### Control-flow features\n- Branches by workload type, database model, transaction criticality, scale, retrieval needs, and compliance posture\n- May read schemas and write documentation, migrations, indexes, or query changes\n- Treats vector DBs as retrieval infrastructure, not canonical source-of-truth storage\n\n## Structural Flow\n\n### Entry\n1. Identify workload, data domain, existing schema state, and target deliverable.\n2. Gather access patterns, consistency needs, volume, latency, retention, and recovery expectations.\n3. Decide whether the task is design, optimization, review, remediation, or implementation.\n\n### Scenes\n1. **PREPARE**: Classify workload and constraints.\n2. **ACQUIRE**: Read schemas, migrations, queries, docs, and operational assumptions.\n3. **REASON**: Model entities\u002Faggregates, integrity, transactions, indexing, capacity, and compliance tradeoffs.\n4. **ACT**: Produce schema docs, migration guidance, query\u002Findex changes, or retrieval design.\n5. **VERIFY**: Run anti-pattern, integrity, consistency, and backup\u002Frecovery checks.\n6. **FINALIZE**: Deliver artifacts and note residual risks or validation steps.\n\n### Transitions\n- If relational workload dominates, enforce 3NF unless denormalization is justified.\n- If distributed\u002Fnon-relational workload dominates, model around aggregates and access paths.\n- If vector\u002FRAG is involved, include hybrid retrieval, embedding versioning, and re-embedding migration.\n- If auditability or continuity is weakened, propose ISO-friendlier alternatives.\n\n### Failure and recovery\n- If workload or access patterns are missing, state assumptions and ask for representative queries or flows.\n- If integrity or transaction requirements conflict with chosen engine, surface the tradeoff.\n- If implementation risk is high, separate design artifact from migration execution.\n\n### Exit\n- Success: deliverables state model, constraints, integrity, transactions, capacity, and validation.\n- Partial success: missing workload evidence or unresolved tradeoffs are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Classify workload and model | `SELECT` | SQL, NoSQL, vector, cache, search, mixed |\n| Read schema\u002Fquery evidence | `READ` | Migrations, ERDs, query patterns |\n| Compare design alternatives | `COMPARE` | Engine\u002Fmodel\u002Findex tradeoffs |\n| Infer integrity and capacity risks | `INFER` | Constraints, transactions, growth assumptions |\n| Validate anti-patterns | `VALIDATE` | Checklist and anti-pattern guide |\n| Write schema docs or changes | `WRITE` | Deliverables, migrations, query\u002Findex changes |\n| Report recommendation | `NOTIFY` | Final database guidance |\n\n### Tools and instruments\n- Project DB schemas, migrations, query tools, and migration commands\n- Document templates, anti-pattern guide, vector DB guide, and ISO control guide\n- Optional spreadsheet or diagram artifacts when capacity or ERD output is requested\n\n### Canonical workflow path\n```bash\nrg --files -g '*.sql' -g '*prisma*' -g '*schema*' -g '*migration*'\nrg \"CREATE TABLE|model |index|foreign key|transaction|embedding|vector\" .\n```\n\nThen run the project's migration, query-plan, or retrieval-quality commands only after identifying the database engine and migration tool.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `CODEBASE` | Schema, migration, query, ORM, and retrieval files |\n| `LOCAL_FS` | Database design artifacts and result documents |\n| `PROCESS` | Migration, query, lint, or validation commands |\n| `USER_DATA` | Domain data definitions, retention rules, and sample access patterns |\n\n### Preconditions\n- Target database concern and scope are identifiable.\n- Existing schema\u002Fworkload evidence is available or assumptions are stated.\n\n### Effects and side effects\n- May create or change schema docs, migrations, indexes, queries, or retrieval configuration.\n- May affect data integrity, performance, recovery posture, or compliance evidence.\n- Should not execute risky migrations without explicit user intent and verification.\n\n### Guardrails\n1. Choose model first, engine second: workload, access pattern, consistency, and scale drive DB selection.\n2. For relational workloads, enforce at least **3NF** by default. Break 3NF only with explicit performance justification.\n3. For distributed\u002Fnon-relational workloads, model around aggregates and access paths; document **BASE** and consistency tradeoffs.\n4. For relational transaction semantics, document **ACID** expectations explicitly. For distributed\u002Fnon-relational tradeoffs, document consistency compromises explicitly.\n5. Always document the three schema layers: **external schema**, **conceptual schema**, **internal schema**.\n6. Treat integrity as first-class: entity, domain, referential, and business-rule integrity must be explicit.\n7. Concurrency is never implicit: define transaction boundaries, locking strategy, and isolation level per critical flow.\n8. Data standards are mandatory: naming, definition, format, allowed values, and validation rules.\n9. Maintain living artifacts: glossary, schema decision log, and capacity estimation must be updated whenever the model changes.\n10. Proactively flag anti-patterns and insecure shortcuts instead of silently implementing them.\n11. If the design weakens auditability, least privilege, traceability, backup\u002Frecovery, or data integrity, propose ISO 27001 \u002F 27002 \u002F 22301-friendlier alternatives.\n12. Vector DBs are retrieval infrastructure, not source-of-truth databases. Store embeddings and lightweight metadata there; keep canonical documents elsewhere.\n13. Never treat vector search as a drop-in replacement for lexical search. Default to hybrid retrieval when exact match, compliance filtering, or explainability matters.\n14. Embeddings are schema-like assets: version model, dimension, chunking, and preprocessing, and plan re-embedding migrations explicitly.\n15. Retrieval quality is won at chunking, filtering, reranking, and observability, not only at the vector index layer.\n16. Schema or data changes on live tables follow expand-contract (parallel change): additive expand, dual-write + batched backfill, verified read switch, delayed contract. DDL on hot tables is lock-aware with timeouts; destructive steps ship in a separate deploy after a soak window.\n17. Query tuning starts from measurement and execution plans, never guesswork: measure, explain, nominate the dominant cost node, then optimize and re-measure.\n\n### Default Workflow\n1. **Explore**\n   - Identify business entities, events, access patterns, volume, latency, retention, and recovery targets\n   - Classify workload: OLTP, analytics, eventing, cache, search, mixed\n   - Decide relational vs non-relational with explicit justification\n2. **Design**\n   - Produce external\u002Fconceptual\u002Finternal schema documentation\n   - Model SQL or NoSQL structures, keys, indexes, constraints, and lifecycle fields\n   - Define integrity, transaction scope, isolation level, and transparency requirements\n3. **Optimize**\n   - Validate 3NF or deliberate denormalization\n   - Tune indexes, partitioning, archival strategy, hot\u002Fcold split, and backup plan\n   - For vector systems, tune ANN, chunking, filtering, reranking, and observability as one pipeline\n   - Run anti-pattern review and update glossary and capacity estimation with every structural change\n\n### Required Deliverables\n- External schema summary by user\u002Fview\u002Fconsumer\n- Conceptual schema with core entities or aggregates and relationships\n- Internal schema with physical storage, indexes, partitioning, and access paths\n- Data standards table: name, definition, type\u002Fformat, rule\n- Glossary \u002F terminology dictionary\n- Capacity estimation sheet\n- Backup and recovery strategy including full + incremental backup cadence\n- For vector\u002FRAG systems: embedding version policy, chunking policy, hybrid retrieval strategy, and re-index \u002F re-embedding plan\n\n## References\n- Execution steps (follow for the selected task): `resources\u002Fexecution-protocol.md`\n- Self-check (run before handoff): `resources\u002Fchecklist.md`\n- Examples: `resources\u002Fexamples.md`\n- Deliverable templates: `resources\u002Fdocument-templates.md`\n- Anti-pattern review guide: `resources\u002Fanti-patterns.md`\n- Live migration playbook: `resources\u002Fmigration-playbook.md`\n- Query tuning and index design: `resources\u002Fquery-tuning.md`\n- Vector DB and RAG guide: `resources\u002Fvector-db.md`\n- ISO control guide: `resources\u002Fiso-controls.md`\n- Error recovery: `resources\u002Ferror-playbook.md`\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Clarification: `..\u002F_shared\u002Fcore\u002Fclarification-protocol.md`\n- Context budget: `..\u002F_shared\u002Fcore\u002Fcontext-budget.md`\n- Lessons learned: `..\u002F_shared\u002Fcore\u002Flessons-learned.md`\n- Observability handoff: `..\u002Foma-observability\u002FSKILL.md` §Integrations — DB span conventions (N+1, lock-wait, pool), cardinality budgets","# DB Agent - Data Modeling & Database Architecture Specialist\n\n## Scheduling\n\n### Goal\nDesign, review, optimize, and document SQL, NoSQL, vector, and retrieval-oriented data systems with explicit schema layers, integrity rules, transaction behavior, capacity assumptions, and audit-aware tradeoffs.\n\n### Intent signature\n- User asks about database, schema, ERD, table design, document model, vector index, RAG retrieval, migration, query tuning, glossary, backup, capacity, or database anti-patterns.\n- User needs database recommendations aligned with security, continuity, integrity, or compliance concerns.\n\n### When to use\n- Relational database modeling, ERD, and schema design\n- NoSQL document, key-value, wide-column, or graph data modeling\n- Vector database and retrieval architecture design for semantic search and RAG\n- SQL\u002FNoSQL technology selection and tradeoff analysis\n- Normalization, denormalization, indexing, and partitioning\n- Transaction design, locking, isolation level, and concurrency control\n- Data standards, glossary, naming rules, and metadata governance\n- Capacity estimation, storage planning, hot\u002Fcold data separation, and backup strategy\n- Database anti-pattern review and remediation guidance\n- ISO 27001, ISO 27002, and ISO 22301-aware database design recommendations\n\n### When NOT to use\n- API-only implementation without schema impact -> use Backend Agent\n- Infra provisioning only -> use TF Infra Agent\n- Final quality\u002Fsecurity audit -> use QA Agent\n\n### Expected inputs\n- Business entities, events, access patterns, volume, latency, retention, and recovery targets\n- Existing schema, queries, migrations, indexes, data standards, or retrieval pipeline context\n- Consistency, transaction, backup, audit, and compliance constraints\n- Optional target deliverable such as ERD, migration plan, glossary, or capacity estimate\n\n### Expected outputs\n- External, conceptual, and internal schema documentation\n- Data standards, glossary, capacity estimate, indexing\u002Fpartitioning plan, and backup\u002Frecovery strategy\n- Integrity, transaction, isolation, and concurrency recommendations\n- Vector\u002FRAG-specific embedding, chunking, filtering, reranking, and re-index plans when relevant\n\n### Dependencies\n- Existing database schemas, migration files, query logs, workload descriptions, and application access paths\n- `resources\u002Fdocument-templates.md`, `resources\u002Fanti-patterns.md`, `resources\u002Fvector-db.md`, `resources\u002Fiso-controls.md`, `resources\u002Fmigration-playbook.md`, and `resources\u002Fquery-tuning.md`\n- SQL\u002FNoSQL\u002Fvector database tools or project-specific migration toolchains when implementation is requested\n\n### Control-flow features\n- Branches by workload type, database model, transaction criticality, scale, retrieval needs, and compliance posture\n- May read schemas and write documentation, migrations, indexes, or query changes\n- Treats vector DBs as retrieval infrastructure, not canonical source-of-truth storage\n\n## Structural Flow\n\n### Entry\n1. Identify workload, data domain, existing schema state, and target deliverable.\n2. Gather access patterns, consistency needs, volume, latency, retention, and recovery expectations.\n3. Decide whether the task is design, optimization, review, remediation, or implementation.\n\n### Scenes\n1. **PREPARE**: Classify workload and constraints.\n2. **ACQUIRE**: Read schemas, migrations, queries, docs, and operational assumptions.\n3. **REASON**: Model entities\u002Faggregates, integrity, transactions, indexing, capacity, and compliance tradeoffs.\n4. **ACT**: Produce schema docs, migration guidance, query\u002Findex changes, or retrieval design.\n5. **VERIFY**: Run anti-pattern, integrity, consistency, and backup\u002Frecovery checks.\n6. **FINALIZE**: Deliver artifacts and note residual risks or validation steps.\n\n### Transitions\n- If relational workload dominates, enforce 3NF unless denormalization is justified.\n- If distributed\u002Fnon-relational workload dominates, model around aggregates and access paths.\n- If vector\u002FRAG is involved, include hybrid retrieval, embedding versioning, and re-embedding migration.\n- If auditability or continuity is weakened, propose ISO-friendlier alternatives.\n\n### Failure and recovery\n- If workload or access patterns are missing, state assumptions and ask for representative queries or flows.\n- If integrity or transaction requirements conflict with chosen engine, surface the tradeoff.\n- If implementation risk is high, separate design artifact from migration execution.\n\n### Exit\n- Success: deliverables state model, constraints, integrity, transactions, capacity, and validation.\n- Partial success: missing workload evidence or unresolved tradeoffs are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Classify workload and model | `SELECT` | SQL, NoSQL, vector, cache, search, mixed |\n| Read schema\u002Fquery evidence | `READ` | Migrations, ERDs, query patterns |\n| Compare design alternatives | `COMPARE` | Engine\u002Fmodel\u002Findex tradeoffs |\n| Infer integrity and capacity risks | `INFER` | Constraints, transactions, growth assumptions |\n| Validate anti-patterns | `VALIDATE` | Checklist and anti-pattern guide |\n| Write schema docs or changes | `WRITE` | Deliverables, migrations, query\u002Findex changes |\n| Report recommendation | `NOTIFY` | Final database guidance |\n\n### Tools and instruments\n- Project DB schemas, migrations, query tools, and migration commands\n- Document templates, anti-pattern guide, vector DB guide, and ISO control guide\n- Optional spreadsheet or diagram artifacts when capacity or ERD output is requested\n\n### Canonical workflow path\n```bash\nrg --files -g '*.sql' -g '*prisma*' -g '*schema*' -g '*migration*'\nrg \"CREATE TABLE|model |index|foreign key|transaction|embedding|vector\" .\n```\n\nThen run the project's migration, query-plan, or retrieval-quality commands only after identifying the database engine and migration tool.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `CODEBASE` | Schema, migration, query, ORM, and retrieval files |\n| `LOCAL_FS` | Database design artifacts and result documents |\n| `PROCESS` | Migration, query, lint, or validation commands |\n| `USER_DATA` | Domain data definitions, retention rules, and sample access patterns |\n\n### Preconditions\n- Target database concern and scope are identifiable.\n- Existing schema\u002Fworkload evidence is available or assumptions are stated.\n\n### Effects and side effects\n- May create or change schema docs, migrations, indexes, queries, or retrieval configuration.\n- May affect data integrity, performance, recovery posture, or compliance evidence.\n- Should not execute risky migrations without explicit user intent and verification.\n\n### Guardrails\n1. Choose model first, engine second: workload, access pattern, consistency, and scale drive DB selection.\n2. For relational workloads, enforce at least **3NF** by default. Break 3NF only with explicit performance justification.\n3. For distributed\u002Fnon-relational workloads, model around aggregates and access paths; document **BASE** and consistency tradeoffs.\n4. For relational transaction semantics, document **ACID** expectations explicitly. For distributed\u002Fnon-relational tradeoffs, document consistency compromises explicitly.\n5. Always document the three schema layers: **external schema**, **conceptual schema**, **internal schema**.\n6. Treat integrity as first-class: entity, domain, referential, and business-rule integrity must be explicit.\n7. Concurrency is never implicit: define transaction boundaries, locking strategy, and isolation level per critical flow.\n8. Data standards are mandatory: naming, definition, format, allowed values, and validation rules.\n9. Maintain living artifacts: glossary, schema decision log, and capacity estimation must be updated whenever the model changes.\n10. Proactively flag anti-patterns and insecure shortcuts instead of silently implementing them.\n11. If the design weakens auditability, least privilege, traceability, backup\u002Frecovery, or data integrity, propose ISO 27001 \u002F 27002 \u002F 22301-friendlier alternatives.\n12. Vector DBs are retrieval infrastructure, not source-of-truth databases. Store embeddings and lightweight metadata there; keep canonical documents elsewhere.\n13. Never treat vector search as a drop-in replacement for lexical search. Default to hybrid retrieval when exact match, compliance filtering, or explainability matters.\n14. Embeddings are schema-like assets: version model, dimension, chunking, and preprocessing, and plan re-embedding migrations explicitly.\n15. Retrieval quality is won at chunking, filtering, reranking, and observability, not only at the vector index layer.\n16. Schema or data changes on live tables follow expand-contract (parallel change): additive expand, dual-write + batched backfill, verified read switch, delayed contract. DDL on hot tables is lock-aware with timeouts; destructive steps ship in a separate deploy after a soak window.\n17. Query tuning starts from measurement and execution plans, never guesswork: measure, explain, nominate the dominant cost node, then optimize and re-measure.\n\n### Default Workflow\n1. **Explore**\n   - Identify business entities, events, access patterns, volume, latency, retention, and recovery targets\n   - Classify workload: OLTP, analytics, eventing, cache, search, mixed\n   - Decide relational vs non-relational with explicit justification\n2. **Design**\n   - Produce external\u002Fconceptual\u002Finternal schema documentation\n   - Model SQL or NoSQL structures, keys, indexes, constraints, and lifecycle fields\n   - Define integrity, transaction scope, isolation level, and transparency requirements\n3. **Optimize**\n   - Validate 3NF or deliberate denormalization\n   - Tune indexes, partitioning, archival strategy, hot\u002Fcold split, and backup plan\n   - For vector systems, tune ANN, chunking, filtering, reranking, and observability as one pipeline\n   - Run anti-pattern review and update glossary and capacity estimation with every structural change\n\n### Required Deliverables\n- External schema summary by user\u002Fview\u002Fconsumer\n- Conceptual schema with core entities or aggregates and relationships\n- Internal schema with physical storage, indexes, partitioning, and access paths\n- Data standards table: name, definition, type\u002Fformat, rule\n- Glossary \u002F terminology dictionary\n- Capacity estimation sheet\n- Backup and recovery strategy including full + incremental backup cadence\n- For vector\u002FRAG systems: embedding version policy, chunking policy, hybrid retrieval strategy, and re-index \u002F re-embedding plan\n\n## References\n- Execution steps (follow for the selected task): `resources\u002Fexecution-protocol.md`\n- Self-check (run before handoff): `resources\u002Fchecklist.md`\n- Examples: `resources\u002Fexamples.md`\n- Deliverable templates: `resources\u002Fdocument-templates.md`\n- Anti-pattern review guide: `resources\u002Fanti-patterns.md`\n- Live migration playbook: `resources\u002Fmigration-playbook.md`\n- Query tuning and index design: `resources\u002Fquery-tuning.md`\n- Vector DB and RAG guide: `resources\u002Fvector-db.md`\n- ISO control guide: `resources\u002Fiso-controls.md`\n- Error recovery: `resources\u002Ferror-playbook.md`\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Clarification: `..\u002F_shared\u002Fcore\u002Fclarification-protocol.md`\n- Context budget: `..\u002F_shared\u002Fcore\u002Fcontext-budget.md`\n- Lessons learned: `..\u002F_shared\u002Fcore\u002Flessons-learned.md`\n- Observability handoff: `..\u002Foma-observability\u002FSKILL.md` §Integrations — DB span conventions (N+1, lock-wait, pool), cardinality budgets",{"name":5,"description":7},"master","5fab8004af1390aa17b3447f2780766c8bf2482c",".agents\u002Fskills\u002Foma-db",0,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate","https:\u002F\u002Fgithub.com\u002Fvasceannie","thingswithstuff.io","2026-11-12 20:22:46",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add vasceannie\u002Fslopgate --skill oma-db",{"tool":68,"command":69},"bunx","bunx skills add vasceannie\u002Fslopgate --skill oma-db",{"tool":71,"command":72},"pnpm","pnpm dlx skills add vasceannie\u002Fslopgate --skill oma-db","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002FSKILL.md",true,[76,82,86,90,94,98,102,106,110,114],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"resources\u002Fanti-patterns.md","REFERENCE","参考文档",7064,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fanti-patterns.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"resources\u002Fchecklist.md",3468,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fchecklist.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"resources\u002Fdocument-templates.md",2124,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fdocument-templates.md",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"resources\u002Ferror-playbook.md",3152,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Ferror-playbook.md",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"resources\u002Fexamples.md",5712,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fexamples.md",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"resources\u002Fexecution-protocol.md",6248,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fexecution-protocol.md",{"path":103,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":104,"sourceHtmlUrl":105},"resources\u002Fiso-controls.md",3313,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fiso-controls.md",{"path":107,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":108,"sourceHtmlUrl":109},"resources\u002Fmigration-playbook.md",5294,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fmigration-playbook.md",{"path":111,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":112,"sourceHtmlUrl":113},"resources\u002Fquery-tuning.md",4458,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fquery-tuning.md",{"path":115,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":116,"sourceHtmlUrl":117},"resources\u002Fvector-db.md",4036,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fvector-db.md",[119,148,175,209,234,255],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":128,"publishedAt":49},"01M71951JDWCYMS8GDC2C7395D","type-strictness","Enforce strict type compliance by eliminating `Any` types and `# type: ignore` comments. Use when:\n(1) Editing code that contains `Any` as a type annotation\n(2) Code has `# type: ignore` or `# pyright: ignore` comments\n(3) User requests type fixes or type strictness enforcement\n(4) Importing from untyped third-party libraries\n(5) User asks to \"fix types\", \"remove Any\", or \"add proper typing\"\n(6) Pyrefly or mypy reports type errors that need resolution\n(7) Code review reveals weak typing patterns\nFollows hierarchical resolution: codebase inference → type stubs → library inspection → type guards → casting (last resort).","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Ftype-strictness\u002FSKILL.md",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[129,130,131,132,133,134,135,136,137,138,139,37,140,141,142,143,144,145,146,147],"type","type strictness","typing","types","remove","code review","fix","errors","inspection","when","code","reports","libraries","casting","pyrefly","mypy","pyright","library","patterns",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":158,"publishedAt":49},"01M7194XGBQXSE7Y5BZ4K5CSTK","slopgate-test-extender","Extend Python test suites with parametrization, fixture reuse, and quality enforcement. Use when asked to add tests, extend existing tests, improve test coverage, consolidate duplicate tests, fix test quality issues, or when Slopgate reports untested-production-code, missing test references, or coverage gaps. Triggers on requests like \"add tests for X\", \"extend these tests\", \"parametrize tests\", \"consolidate tests\", \"fix test quality\", \"improve test coverage\", \"write tests for this function\", \"test this module\", \"behavior tests\", \"integration tests\", \"missing tests\", \"coverage holes\", \"untested code\", or when a hook denies with test-related findings.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-test-extender\u002FSKILL.md",[154,155],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[159,160,161,162,163,135,164,165,166,167,168,169,138,139,170,171,140,172,173,174],"slopgate test extender","test","coverage","fixture","testing","issues","write tests","improve","only","cleanup","loop","candidate","consolidate","references","opencode","orchestrator",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":194,"publishedAt":49},"01M7194RMVQS5YJJ4ZEFXX20VS","slopgate-intelligent-coding-patterns","Pattern-selection playbook for agents editing code with complex branching, stateful parsers\u002Fworkflows, duplicated skeletons, policy checks, or ordered transforms. Load before refactoring if\u002Felif dispatch chains, boolean-flag state machines, repeated validation predicates, parallel provider\u002Flanguage implementations, or regex\u002Fcontent transformation pipelines. Also load when asked to \"apply a design pattern\", \"which pattern should I use here\", \"refactor this switch statement\", \"replace if-elif chain\", \"state machine pattern\", \"strategy pattern\", \"template method\", \"pipeline pattern\", \"specification pattern\", \"dispatch table\", \"guard clause refactor\", \"reduce cyclomatic complexity\", or when Slopgate fires PY-CODE-014, PY-CODE-017, PY-CODE-018, QUALITY-LINT-001, or PY-QUALITY-010. Use with behavior-locking tests and avoid pattern theater for simple one-off code.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-intelligent-coding-patterns\u002FSKILL.md",[181,182,185,188,191],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":183,"categoryName":184,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":189,"categoryName":190,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",{"categoryNo":192,"categoryName":193,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[195,196,147,197,198,199,200,201,202,203,204,205,43,167,168,206,207,138,208,139],"coding patterns","slopgate intelligent coding patterns","coding","stateful","complexity","branch","which","chain","parsers","pipeline","selection","utility","workflows","reduce",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":217,"publishedAt":49},"01M7194KTXBM85GB0W7JKFQD55","slopgate-hygiene-orchestrator","Orchestrate systematic elimination of linter warnings and errors across Python, TypeScript, and Rust codebases. Use when asked to \"clean up lints\", \"fix all warnings\", \"run hygiene\", \"eliminate type errors\", \"orchestrate code quality fixes\", \"fix lint errors\", \"resolve quality gate failures\", \"pass CI checks\", \"reduce tech debt\", \"refactor to pass hooks\", or when a Slopgate hook denies with QUALITY-LINT-001, PY-CODE-017, PY-CODE-018, or any collector finding. This skill coordinates multiple code-hygiene-enforcer agents working in parallel on non-conflicting file groupings, tracks progress persistently via JSON exports, and loops until all issues are resolved. CRITICAL: Never run linters directly—always use `slopgate lint check` as the primary gate, discover project-specific tools from config files, and export findings to JSON for tracking.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-hygiene-orchestrator\u002FSKILL.md",[215,216],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},[218,219,174,220,135,221,222,223,224,225,168,208,226,227,228,229,230,231,232,233],"slopgate hygiene orchestrator","hygiene","project","ci","local","clean","never run","files","run","lint check","systematic","config","typescript","debt","quality-gates","hook",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":242,"publishedAt":49},"01M7194G50FZYXXT8VNK360RPA","slopgate-code-smell-utility-locator","Autoactivate when code-smell hooks or reviews mention feature envy, thin wrappers, duplicate helpers, duplicate code,\nscattered helpers, builders\u002Ffactories\u002Fconfig\u002Fconstants\u002Fdataclass reuse, PY-CODE-012, PY-CODE-013, QUALITY-LINT-001,\nor repeated slopgate code-quality denials. Also load when asked to \"find existing helpers\", \"consolidate utilities\",\n\"search for duplicate code\", \"where is this already implemented\", \"reuse existing logic\", \"don't duplicate this\",\n\"find similar functions\", \"utility inventory\", \"code smell radar\", or before adding new helpers\u002Fwrappers so agents can\nfind existing shared utilities and consolidate instead of duplicating.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-code-smell-utility-locator\u002FSKILL.md",[240,241],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":189,"categoryName":190,"taxonomyType":26,"taxonomyTypeDesc":27},[206,243,139,244,161,245,246,247,248,167,249,138,250,171,173,251,252,229,253,254],"slopgate code smell utility locator","shared","reviews","inventory","search","hooks","new","coordination","radar","code-quality","Utilities","dataclass",{"skillNo":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":259,"categories":260,"keywords":263,"publishedAt":49},"01M7194AWG1Q37F9756H4SFDH9","slopgate-code-hygiene-refactor","Recovery playbook for Slopgate and project quality failures. Load after hook\u002Flint denials such as PY-CODE-017 flat sibling modules, PY-CODE-018 oversized modules, QUALITY-LINT-001 post-edit quality backstops, PY-QUALITY-010 magic numbers \u002F repeated literals, PY-CODE-012\u002FPY-CODE-013 smell findings, type-suppression bans, duplicate helpers, or repeated hygiene retry loops. Also load when asked to \"refactor this module\", \"split this file\", \"extract a class\", \"reduce complexity\", \"fix god class\", \"flatten module hierarchy\", \"move code to a package\", \"extract helpers\", \"consolidate duplicates\", \"replace magic numbers with constants\", or when a hook blocks an edit with structural complaints. Focuses on preserving public APIs while refactoring toward packages, cohesive modules, typed seams, and focused tests.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-code-hygiene-refactor\u002FSKILL.md",[261,262],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":189,"categoryName":190,"taxonomyType":26,"taxonomyTypeDesc":27},[264,265,139,266,219,267,199,268,269,220,270,246,271,135,167,206,138,208,250,171],"code hygiene","slopgate code hygiene refactor","refactor","modules","duplicates","retry","move","structural"]