Loading...
Loading...
Found 49 Skills
Apply when deciding where and how a VTEX IO app should store and read data. Covers when to use app settings, configuration apps, Master Data, VBase, VTEX core APIs, or external stores, and how to avoid duplicating sources of truth or abusing configuration stores for operational data. Use for new data flows, caching decisions, refactors, or reviewing suspicious storage and access patterns in VTEX IO apps.
MUST activate when a uiBundles/*/src/ project does ANY Salesforce record operation — reading, creating, updating, deleting, or caching/refreshing query results. Triggers: code importing @salesforce/platform-sdk, calls to sdk.graphql.query / sdk.graphql.mutate / sdk.fetch, *.graphql files, stale data needing a force-refresh, or wiring up a UI bundle's data layer to read, write, or refresh Salesforce records. The default for new read/write work is the Read/Write workflow with the current @salesforce/platform-sdk API; only follow the migration path when EXISTING code already uses the old @salesforce/sdk-data callable form. Not for building app shell/UI, styling, file upload, or auth/search scaffolding — use the other ui-bundle-* skills. DO NOT TRIGGER when: OAuth setup, schema changes, Bulk/Tooling/Metadata API, or declarative automation.
Audit and improve SQL quality systematically — catch performance smells in raw SQL, ORM-generated queries, schema/modeling decisions, migrations, or PR diffs, explain the database-level impact, give a corrected version, and make the tradeoff explicit. Generic by design: no project, domain, ORM, or language config — any context it needs (is this table transactional? is the scan intentional? what volume is expected?) is raised during analysis, never assumed. Reach for it whenever someone writes, reviews, or optimizes a query or data-access code — "review this query", "why is this slow", "check my migration", "is this index right", or when you see N+1, SELECT *, a cartesian/row explosion, three-plus joins, a missing date filter on a growing table, OFFSET pagination, LIKE '%term%', NOT IN with nullable columns, an unindexed ORDER BY, an unbounded list, or a long transaction — even when they never say the word "SQL". Use it both to validate new code and designs and to audit existing ones.
MUST activate to localize / internationalize a uiBundles/*/src/ React project: extract hardcoded user-facing strings into Custom Labels, wire i18next over the Platform SDK GraphQL backend, add a language to a localized bundle, or troubleshoot label rendering across locales. Triggers: user-facing string literals in .tsx/.jsx, a CustomLabels.labels-meta.xml, a src/i18n/ directory or label-manifest.ts, t(…) calls, or requests to 'translate / localize / internationalize / support another language.' Scope: authenticated UI Bundles only (B2E CustomApplication-bound, or in-core accessCheck-bound apps). DO NOT TRIGGER when: the bundle is a site (B2C/B2B) app bound to a DigitalExperienceConfig (site localization not yet supported), building app shell/UI or styling, reading/writing/refreshing records (use experience-ui-bundle-salesforce-data-access), generating a new bundle (use experience-ui-bundle-frontend-generate), deploying (use experience-ui-bundle-deploy), or authoring translations in Translation Workbench.
Design the operator-side review and approval process for third-party apps on a B2B SaaS marketplace - review-pipeline shape scaled to data sensitivity, permission and data-access audit checkpoints, automated pre-screening with human triage, objective re-review-on-update triggers, publish-channel hardening against supply-chain attacks, appeal paths, and a severity-tiered revocation policy. Use whenever the user mentions app review, marketplace approval criteria, third-party app permission audits, re-review after an app update, rejection appeals, or delisting and revocation - even if they never say "app review". Operator side only. Do NOT use for submitter onboarding - use samber/developer-platform-skills@partner-app-onboarding instead.
Read-only audit of a database layer — schema anti-patterns (EAV, generic keys, imprecise types), query and index fit (SELECT *, N+1, unindexable predicates), integrity and concurrency, migration and tenancy hygiene — with evidence per finding and a SHIP / FIX / BLOCK verdict. Use when asked to audit the database, review the schema or migrations, judge a data model, or 'проверь схему базы'. Never edits schema or data. Do not use for runtime profiling (awesome-performance-audit), SQL injection (awesome-security-audit), or data-access style (awesome-code-standards).
Tushare is a financial data interface package with rich data content, such as market data of stocks, funds, futures, digital currencies, etc., and fundamental data including corporate finance, fund managers, etc. This module unifies the external service mode of data assets through standardized APIs, helping technical users in need to access relevant data in a more real-time, concise and lightweight way.
Provides comprehensive guidance for Spring Boot development including project creation, auto-configuration, dependency injection, web development, data access, security, testing, and deployment. Use when the user asks about Spring Boot, needs to create Spring Boot applications, configure Spring Boot, or implement Spring Boot features.
Execute read-only T-SQL queries against Fabric Data Warehouse, Lakehouse SQL Endpoints, and Mirrored Databases via CLI. Default skill for any lakehouse data query (row counts, SELECT, filtering, aggregation) unless the user explicitly requests PySpark or Spark DataFrames. Use when the user wants to: (1) query warehouse/lakehouse data, (2) count rows or explore lakehouse tables, (3) discover schemas/columns, (4) generate T-SQL scripts, (5) monitor SQL performance, (6) export results to CSV/JSON. Triggers: "warehouse", "SQL query", "T-SQL", "query warehouse", "show warehouse tables", "show lakehouse tables", "query lakehouse", "lakehouse table", "how many rows", "count rows", "SQL endpoint", "describe warehouse schema", "generate T-SQL script", "warehouse performance", "export SQL data", "connect to warehouse", "lakehouse data", "explore lakehouse".
Get best practices for Entity Framework Core
Attempt to read data from exposed tables to verify actual data exposure and RLS effectiveness.
通过专利ID或公开号从智慧芽专利数据库获取专利说明书（描述）数据。当用户提到专利说明书、专利全文、专利技术描述、专利实施方式详情、智慧芽说明书数据、patent specification, patent full text, technical description, embodiment details, PatSnap, patent detailed description时触发此技能。即使用户未明确说"智慧芽"，只要其需要查看一项或多项专利的完整说明书/描述内容，也应触发此技能。