[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718TASXWF076M98PNETGMA4":3,"skill-same:01M718TASXWF076M98PNETGMA4":107},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M718TASXWF076M98PNETGMA4","oma-backend",null,"Backend specialist for APIs, databases, authentication with clean architecture (Repository\u002FService\u002FRouter pattern). Use for API, endpoint, REST, database, server, migration, and auth work.","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-backend\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"backend","oma backend","REST","with","use","for","endpoint","pattern","repository","clean architecture","work","server","router","api","architecture","database","clean","authentication","auth","databases","2026-11-10 10:12:30",false,"---\nname: oma-backend\ndescription: Backend specialist for APIs, databases, authentication with clean\n  architecture (Repository\u002FService\u002FRouter pattern). Use for API, endpoint, REST,\n  database, server, migration, and auth work.\n---\n\n# Backend Agent - API & Server Specialist\n\n## Scheduling\n\n### Goal\nImplement or review backend APIs, authentication, database integration, server-side business logic, and migrations using the project's existing backend stack and clean architecture boundaries.\n\n### Intent signature\n- User asks for API, endpoint, REST, GraphQL, auth, server, migration, repository, service, router, or background job work.\n- User needs backend code that coordinates validation, business logic, persistence, transactions, and backing services.\n\n### When to use\n- Building REST APIs or GraphQL endpoints\n- Database design and migrations\n- Authentication and authorization\n- Server-side business logic\n- Background jobs and queues\n\n### When NOT to use\n- Frontend UI -> use Frontend Agent\n- Mobile-specific code -> use Mobile Agent\n\n### Expected inputs\n- Target feature, endpoint, migration, auth flow, or server behavior\n- Existing backend stack files such as manifests, routes, services, models, and database config\n- API contracts, schemas, validation rules, and persistence requirements\n- Required verification commands or project conventions\n\n### Expected outputs\n- Backend code changes in router, service, repository, model, migration, or test files\n- Validated inputs, safe queries, transaction boundaries, and error handling\n- Verification results from the execution checklist\n\n### Dependencies\n- Project stack manifests and existing backend conventions\n- `resources\u002Fexecution-protocol.md`, `resources\u002Fchecklist.md`, and `resources\u002Form-reference.md`\n\u003C!-- oma-docs:ignore-start -->\n- Optional `stack\u002Fstack.yaml`, `stack\u002Ftech-stack.md`, snippets, and API templates\n\u003C!-- oma-docs:ignore-end -->\n- Database, queue, cache, mail, auth, or external API resources configured through environment or secret managers\n\n### Control-flow features\n- Branches by detected stack, ORM\u002Fquery pattern, auth requirement, migration impact, and transaction scope\n- Reads and writes codebase files\n- May touch local database migrations or generated code\n- Must not hardcode secrets or share unsafe ORM lifecycle objects across concurrent work\n\n## Structural Flow\n\n### Entry\n1. Detect the backend stack from project files first.\n2. Identify affected router, service, repository, model, migration, and test boundaries.\n3. Load stack-specific references only when needed.\n\n### Scenes\n1. **PREPARE**: Determine stack, architecture boundaries, and acceptance criteria.\n2. **ACQUIRE**: Read existing routes, services, repositories, models, schemas, and config.\n3. **ACT**: Implement backend changes with validation, business logic, persistence, and tests.\n4. **VERIFY**: Run relevant lint, type, test, migration, and checklist commands.\n5. **FINALIZE**: Report changed behavior, verification, and unresolved risks.\n\n### Transitions\n- If stack files exist, follow them before generic guidance.\n- If ORM performance, relationship loading, transactions, or N+1 risk appears, use `resources\u002Form-reference.md`.\n- If database schema impact is primary and API work is secondary, coordinate with `oma-db`.\n- If auth server setup touches DB adapters or server libraries, keep it in backend scope.\n\n### Failure and recovery\n- If stack cannot be determined, ask the user or suggest running `\u002Fstack-set`.\n- If verification fails, fix root cause before handoff.\n- If required secrets or services are unavailable, document the blocker and keep code configurable.\n\n### Exit\n- Success: backend change is implemented, tested, and aligned with local architecture.\n- Partial success: blocker, missing dependency, or verification gap is explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Detect stack and conventions | `READ` | Manifests, stack files, existing code |\n| Select implementation boundary | `SELECT` | Router\u002Fservice\u002Frepository pattern |\n| Validate inputs and schemas | `VALIDATE` | Stack validation library |\n| Implement business logic | `WRITE` | Service layer code |\n| Implement persistence | `WRITE` | Repository\u002Fmodel\u002Fmigration code |\n| Call external\u002Fbacking services | `CALL_TOOL` | DB, queue, cache, auth, or API clients |\n| Run verification | `CALL_TOOL` | Tests, typecheck, lint, migrations |\n| Report result | `NOTIFY` | Final summary |\n\n### Tools and instruments\n- Project language\u002Fframework toolchain\n- ORM or database client\n- Test, lint, typecheck, and migration commands\n- Stack-specific templates and snippets when present\n\n### Canonical workflow path\n```bash\nrg --files\nrg \"route|router|service|repository|model|schema|migration\" .\n```\n\n\u003C!-- oma-docs:ignore-start -->\nThen run the project's discovered verification commands, usually lint\u002Ftypecheck\u002Ftests and migrations when schema changes are involved. Prefer `stack\u002Fstack.yaml` `verify:` commands when present.\n\u003C!-- oma-docs:ignore-end -->\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `CODEBASE` | Backend source, tests, schemas, migrations |\n| `LOCAL_FS` | Stack references and generated artifacts |\n| `PROCESS` | Test, lint, typecheck, migration commands |\n| `CREDENTIALS` | Environment-managed DB URLs, API keys, secrets |\n| `NETWORK` | External APIs or backing services when required |\n\n### Preconditions\n- Target behavior and affected backend boundary are identifiable.\n- Project stack and verification commands can be inferred or are provided.\n- Required credentials remain outside source code.\n\n### Effects and side effects\n- Mutates backend source files, tests, and possibly migrations.\n- May change database schema, API behavior, auth behavior, or service contracts.\n- May require generated clients or migration artifacts.\n\n### Guardrails\n\n1. **DRY (Don't Repeat Yourself)**: Business logic in `Service`, data access logic in `Repository`\n2. **SOLID**:\n   - **Single Responsibility**: Classes and functions should have one responsibility\n   - **Dependency Inversion**: Use your framework's DI mechanism\n3. **KISS**: Keep it simple and clear\n\n### Architecture Pattern\n\n```\nRouter (HTTP) → Service (Business Logic) → Repository (Data Access) → Models\n```\n\n### Repository Layer\n- Encapsulate DB CRUD and query logic\n- No business logic, return ORM entities\n\n### Service Layer\n- Business logic, Repository composition, external API calls\n- Business decisions only here\n\n### Router Layer\n- Receive HTTP requests, input validation, call Service, return response\n- No business logic, inject Service via DI\n\n### Core Rules\n\n1. **Clean architecture**: router → service → repository → models\n2. **No business logic in route handlers**\n3. **All inputs validated** with your stack's validation library\n4. **Parameterized queries only** (never string interpolation)\n5. **JWT + Argon2id for auth** (bcrypt acceptable for legacy compatibility); rate limit auth endpoints\n6. **Async where supported**; type annotations on all signatures\n7. **Custom exceptions** via centralized error module (not raw HTTP exceptions)\n8. **Explicit ORM loading strategy**: do not rely on default relation loading when query shape matters\n9. **Explicit transaction boundaries**: group one business operation into one request\u002Fservice-scoped unit of work\n10. **Safe ORM lifecycle**: do not share mutable ORM session\u002Fentity manager\u002Fclient objects across concurrent work unless the ORM explicitly supports it\n11. **Config from environment, with graceful fallback**: DB URLs, API keys, secrets, and feature flags come from env vars or secret managers; never hardcode in source. When integrating a third-party API (OpenAI, Anthropic, Stripe, etc.), write BOTH paths: (a) real call when the env key is present, (b) deterministic local fallback when absent, marked with `\u002F\u002F TODO(oma-deferred): integrate \u003Cvendor> when key is provisioned`. Fallback-only leaves the spec unmet; real-call-only breaks demos when the key is missing\n12. **Stateless services**: no in-memory session or user state between requests; use external stores (DB, Redis, cache) for shared state\n13. **Backing services as resources**: DB, queue, cache, mail are swappable attached resources connected via config; Repository layer must not assume a specific instance\n\n### Stack Detection\n\n1. **Project files first**: Read existing code, package manifests (pyproject.toml, package.json, Cargo.toml, go.mod, pom.xml, etc.) to determine the tech stack\n2. **stack\u002F second**: If `stack\u002F` exists, use it as supplementary reference for coding conventions and snippet templates\n3. **Neither exists**: Ask the user or suggest running `\u002Fstack-set`\n\n### Stack-Specific Reference\n\n\u003C!-- oma-docs:ignore-start -->\n- **Stack manifest (SSOT)**: `stack\u002Fstack.yaml`: structured declaration (`language`, `framework`, `orm`) and `verify:` contract consumed by `oma verify backend`. Schema: `variants\u002Fstack.schema.json`.\n- Tech stack narrative: `stack\u002Ftech-stack.md`: human-readable reference only; `stack.yaml` wins on conflict.\n- Code snippets (copy-paste ready): `stack\u002Fsnippets.md`\n- API template: `stack\u002Fapi-template.*`\n\u003C!-- oma-docs:ignore-end -->\n\n## References\n- Local code tools: `..\u002F_shared\u002Fcore\u002Fcode-intelligence.md` (code search\u002Fnavigation)\n\n- Execution steps (follow for the selected task): `resources\u002Fexecution-protocol.md`\n- Checklist (run before handoff): `resources\u002Fchecklist.md`\n- ORM reference: `resources\u002Form-reference.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 — propagators\u002Fbaggage, span conventions, log correlation, PII redaction","# Backend Agent - API & Server Specialist\n\n## Scheduling\n\n### Goal\nImplement or review backend APIs, authentication, database integration, server-side business logic, and migrations using the project's existing backend stack and clean architecture boundaries.\n\n### Intent signature\n- User asks for API, endpoint, REST, GraphQL, auth, server, migration, repository, service, router, or background job work.\n- User needs backend code that coordinates validation, business logic, persistence, transactions, and backing services.\n\n### When to use\n- Building REST APIs or GraphQL endpoints\n- Database design and migrations\n- Authentication and authorization\n- Server-side business logic\n- Background jobs and queues\n\n### When NOT to use\n- Frontend UI -> use Frontend Agent\n- Mobile-specific code -> use Mobile Agent\n\n### Expected inputs\n- Target feature, endpoint, migration, auth flow, or server behavior\n- Existing backend stack files such as manifests, routes, services, models, and database config\n- API contracts, schemas, validation rules, and persistence requirements\n- Required verification commands or project conventions\n\n### Expected outputs\n- Backend code changes in router, service, repository, model, migration, or test files\n- Validated inputs, safe queries, transaction boundaries, and error handling\n- Verification results from the execution checklist\n\n### Dependencies\n- Project stack manifests and existing backend conventions\n- `resources\u002Fexecution-protocol.md`, `resources\u002Fchecklist.md`, and `resources\u002Form-reference.md`\n\u003C!-- oma-docs:ignore-start -->\n- Optional `stack\u002Fstack.yaml`, `stack\u002Ftech-stack.md`, snippets, and API templates\n\u003C!-- oma-docs:ignore-end -->\n- Database, queue, cache, mail, auth, or external API resources configured through environment or secret managers\n\n### Control-flow features\n- Branches by detected stack, ORM\u002Fquery pattern, auth requirement, migration impact, and transaction scope\n- Reads and writes codebase files\n- May touch local database migrations or generated code\n- Must not hardcode secrets or share unsafe ORM lifecycle objects across concurrent work\n\n## Structural Flow\n\n### Entry\n1. Detect the backend stack from project files first.\n2. Identify affected router, service, repository, model, migration, and test boundaries.\n3. Load stack-specific references only when needed.\n\n### Scenes\n1. **PREPARE**: Determine stack, architecture boundaries, and acceptance criteria.\n2. **ACQUIRE**: Read existing routes, services, repositories, models, schemas, and config.\n3. **ACT**: Implement backend changes with validation, business logic, persistence, and tests.\n4. **VERIFY**: Run relevant lint, type, test, migration, and checklist commands.\n5. **FINALIZE**: Report changed behavior, verification, and unresolved risks.\n\n### Transitions\n- If stack files exist, follow them before generic guidance.\n- If ORM performance, relationship loading, transactions, or N+1 risk appears, use `resources\u002Form-reference.md`.\n- If database schema impact is primary and API work is secondary, coordinate with `oma-db`.\n- If auth server setup touches DB adapters or server libraries, keep it in backend scope.\n\n### Failure and recovery\n- If stack cannot be determined, ask the user or suggest running `\u002Fstack-set`.\n- If verification fails, fix root cause before handoff.\n- If required secrets or services are unavailable, document the blocker and keep code configurable.\n\n### Exit\n- Success: backend change is implemented, tested, and aligned with local architecture.\n- Partial success: blocker, missing dependency, or verification gap is explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Detect stack and conventions | `READ` | Manifests, stack files, existing code |\n| Select implementation boundary | `SELECT` | Router\u002Fservice\u002Frepository pattern |\n| Validate inputs and schemas | `VALIDATE` | Stack validation library |\n| Implement business logic | `WRITE` | Service layer code |\n| Implement persistence | `WRITE` | Repository\u002Fmodel\u002Fmigration code |\n| Call external\u002Fbacking services | `CALL_TOOL` | DB, queue, cache, auth, or API clients |\n| Run verification | `CALL_TOOL` | Tests, typecheck, lint, migrations |\n| Report result | `NOTIFY` | Final summary |\n\n### Tools and instruments\n- Project language\u002Fframework toolchain\n- ORM or database client\n- Test, lint, typecheck, and migration commands\n- Stack-specific templates and snippets when present\n\n### Canonical workflow path\n```bash\nrg --files\nrg \"route|router|service|repository|model|schema|migration\" .\n```\n\n\u003C!-- oma-docs:ignore-start -->\nThen run the project's discovered verification commands, usually lint\u002Ftypecheck\u002Ftests and migrations when schema changes are involved. Prefer `stack\u002Fstack.yaml` `verify:` commands when present.\n\u003C!-- oma-docs:ignore-end -->\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `CODEBASE` | Backend source, tests, schemas, migrations |\n| `LOCAL_FS` | Stack references and generated artifacts |\n| `PROCESS` | Test, lint, typecheck, migration commands |\n| `CREDENTIALS` | Environment-managed DB URLs, API keys, secrets |\n| `NETWORK` | External APIs or backing services when required |\n\n### Preconditions\n- Target behavior and affected backend boundary are identifiable.\n- Project stack and verification commands can be inferred or are provided.\n- Required credentials remain outside source code.\n\n### Effects and side effects\n- Mutates backend source files, tests, and possibly migrations.\n- May change database schema, API behavior, auth behavior, or service contracts.\n- May require generated clients or migration artifacts.\n\n### Guardrails\n\n1. **DRY (Don't Repeat Yourself)**: Business logic in `Service`, data access logic in `Repository`\n2. **SOLID**:\n   - **Single Responsibility**: Classes and functions should have one responsibility\n   - **Dependency Inversion**: Use your framework's DI mechanism\n3. **KISS**: Keep it simple and clear\n\n### Architecture Pattern\n\n```\nRouter (HTTP) → Service (Business Logic) → Repository (Data Access) → Models\n```\n\n### Repository Layer\n- Encapsulate DB CRUD and query logic\n- No business logic, return ORM entities\n\n### Service Layer\n- Business logic, Repository composition, external API calls\n- Business decisions only here\n\n### Router Layer\n- Receive HTTP requests, input validation, call Service, return response\n- No business logic, inject Service via DI\n\n### Core Rules\n\n1. **Clean architecture**: router → service → repository → models\n2. **No business logic in route handlers**\n3. **All inputs validated** with your stack's validation library\n4. **Parameterized queries only** (never string interpolation)\n5. **JWT + Argon2id for auth** (bcrypt acceptable for legacy compatibility); rate limit auth endpoints\n6. **Async where supported**; type annotations on all signatures\n7. **Custom exceptions** via centralized error module (not raw HTTP exceptions)\n8. **Explicit ORM loading strategy**: do not rely on default relation loading when query shape matters\n9. **Explicit transaction boundaries**: group one business operation into one request\u002Fservice-scoped unit of work\n10. **Safe ORM lifecycle**: do not share mutable ORM session\u002Fentity manager\u002Fclient objects across concurrent work unless the ORM explicitly supports it\n11. **Config from environment, with graceful fallback**: DB URLs, API keys, secrets, and feature flags come from env vars or secret managers; never hardcode in source. When integrating a third-party API (OpenAI, Anthropic, Stripe, etc.), write BOTH paths: (a) real call when the env key is present, (b) deterministic local fallback when absent, marked with `\u002F\u002F TODO(oma-deferred): integrate \u003Cvendor> when key is provisioned`. Fallback-only leaves the spec unmet; real-call-only breaks demos when the key is missing\n12. **Stateless services**: no in-memory session or user state between requests; use external stores (DB, Redis, cache) for shared state\n13. **Backing services as resources**: DB, queue, cache, mail are swappable attached resources connected via config; Repository layer must not assume a specific instance\n\n### Stack Detection\n\n1. **Project files first**: Read existing code, package manifests (pyproject.toml, package.json, Cargo.toml, go.mod, pom.xml, etc.) to determine the tech stack\n2. **stack\u002F second**: If `stack\u002F` exists, use it as supplementary reference for coding conventions and snippet templates\n3. **Neither exists**: Ask the user or suggest running `\u002Fstack-set`\n\n### Stack-Specific Reference\n\n\u003C!-- oma-docs:ignore-start -->\n- **Stack manifest (SSOT)**: `stack\u002Fstack.yaml`: structured declaration (`language`, `framework`, `orm`) and `verify:` contract consumed by `oma verify backend`. Schema: `variants\u002Fstack.schema.json`.\n- Tech stack narrative: `stack\u002Ftech-stack.md`: human-readable reference only; `stack.yaml` wins on conflict.\n- Code snippets (copy-paste ready): `stack\u002Fsnippets.md`\n- API template: `stack\u002Fapi-template.*`\n\u003C!-- oma-docs:ignore-end -->\n\n## References\n- Local code tools: `..\u002F_shared\u002Fcore\u002Fcode-intelligence.md` (code search\u002Fnavigation)\n\n- Execution steps (follow for the selected task): `resources\u002Fexecution-protocol.md`\n- Checklist (run before handoff): `resources\u002Fchecklist.md`\n- ORM reference: `resources\u002Form-reference.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 — propagators\u002Fbaggage, span conventions, log correlation, PII redaction",{"name":5,"description":7},"master","5fab8004af1390aa17b3447f2780766c8bf2482c",".agents\u002Fskills\u002Foma-backend",0,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate","https:\u002F\u002Fgithub.com\u002Fvasceannie","thingswithstuff.io","2026-11-10 23:25:49",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add vasceannie\u002Fslopgate --skill oma-backend",{"tool":63,"command":64},"bunx","bunx skills add vasceannie\u002Fslopgate --skill oma-backend",{"tool":66,"command":67},"pnpm","pnpm dlx skills add vasceannie\u002Fslopgate --skill oma-backend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002FSKILL.md",true,[71,77,81,85,89,95,99,103],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"resources\u002Fchecklist.md","REFERENCE","参考文档",2152,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fresources\u002Fchecklist.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"resources\u002Ferror-playbook.md",3888,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fresources\u002Ferror-playbook.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"resources\u002Fexecution-protocol.md",2674,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fresources\u002Fexecution-protocol.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"resources\u002Form-reference.md",3976,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fresources\u002Form-reference.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"stack\u002Fapi-template.py","SCRIPT","脚本",10409,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fstack\u002Fapi-template.py",{"path":96,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":97,"sourceHtmlUrl":98},"stack\u002Fsnippets.md",5128,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fstack\u002Fsnippets.md",{"path":100,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":101,"sourceHtmlUrl":102},"stack\u002Fstack.yaml",32,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fstack\u002Fstack.yaml",{"path":104,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":105,"sourceHtmlUrl":106},"stack\u002Ftech-stack.md",1694,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-backend\u002Fstack\u002Ftech-stack.md",[108,138,165,202,226,247],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":117,"publishedAt":44},"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",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"type","type strictness","typing","types","remove","code review","fix","errors","inspection","when","code","review","reports","libraries","casting","pyrefly","mypy","pyright","library","patterns",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":148,"publishedAt":44},"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",[144,145],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[149,150,151,152,153,124,154,155,156,157,158,159,127,128,160,161,130,162,163,164],"slopgate test extender","test","coverage","fixture","testing","issues","write tests","improve","only","cleanup","loop","candidate","consolidate","references","opencode","orchestrator",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":186,"publishedAt":44},"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",[171,172,175,178,183],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":184,"categoryName":185,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000032","设计师",[187,188,137,189,190,191,192,193,194,195,196,197,198,157,158,199,200,127,201,128],"coding patterns","slopgate intelligent coding patterns","coding","stateful","complexity","branch","which","chain","parsers","pipeline","selection","design","utility","workflows","reduce",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":210,"publishedAt":44},"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",[208,209],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},[211,212,164,213,124,214,215,40,216,217,158,201,218,219,220,221,222,223,224,225],"slopgate hygiene orchestrator","hygiene","project","ci","local","never run","files","run","lint check","systematic","config","typescript","debt","quality-gates","hook",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":234,"publishedAt":44},"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",[232,233],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},[199,235,128,236,151,237,238,239,240,157,241,127,242,161,163,243,244,221,245,246],"slopgate code smell utility locator","shared","reviews","inventory","search","hooks","new","coordination","radar","code-quality","Utilities","dataclass",{"skillNo":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":251,"categories":252,"keywords":255,"publishedAt":44},"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",[253,254],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},[256,257,128,258,212,259,191,260,261,213,262,238,263,124,157,199,127,201,242,161],"code hygiene","slopgate code hygiene refactor","refactor","modules","duplicates","retry","move","structural"]