5232 个 · 按相关度排序
Guides building chatbots and tool-using agents with LangChain. Covers conversation history, model provider integration, and RAG, which retrieves relevant documents to inform answers, plus tracing to inspect application behavior.
中文简介正在准备中。当前显示英语简介。
Use Meta's Prompt Guard to detect malicious instructions in user prompts and external data. This skill guides input filtering, batch checks for retrieved documents, detection threshold adjustments, and splitting long text for inspection.
中文简介正在准备中。当前显示英语简介。
Measure which code fuzzing reaches as it tries many generated inputs. Use coverage reports to find unreachable areas, compare progress, and guide improvements to test harnesses, starting inputs, or dictionaries of useful input values.
中文简介正在准备中。当前显示英语简介。
Design features such as CRM around reusable database storage and a shared editor. It guides ownership, permissions, API contracts, and update behavior so different applications can use the same database components while enforcing their own access rules.
中文简介正在准备中。当前显示英语简介。
Audit changed code by tracing execution paths and matching them to existing tests. Show coverage gaps and test quality, then generate tests for high-priority gaps using the project's current framework, helpers, and naming conventions.
中文简介正在准备中。当前显示英语简介。
Build production systems for machine learning models, from deployment to monitoring and retraining. The skill also guides LLM integration and retrieval augmented generation, which uses retrieved information to support answers, with scripts and architecture references.
中文简介正在准备中。当前显示英语简介。
Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations, and analyzes storage metrics using S3 Metadata system tables (journal, inventory, annotation) and S3 Storage Lens tables via Athena SQL. Applies when counting objects, finding recent uploads or deletions, identifying who wrote to a prefix, breaking down storage classes, finding objects by tag, searching annotation content, analyzing storage lens metrics, or enabling S3 Metadata tracking. Prefers system tables over raw S3 APIs (list-objects-v2, head-object) at scale. Trigger phrases: bucket activity, object count, who uploaded, track deletions, storage class breakdown, find by tag, search annotations, storage lens metrics, audit bucket changes.
中文简介正在准备中。当前显示原文说明。
Use this skill when the user asks to summarize, or asks why Simulink Coverage objectives are missing, unsatisfied, or uncovered on a coverage result they already have — why specific decision, condition, MCDC, relational-boundary, or saturation/overflow outcomes weren't exercised, whether uncovered logic is dead code, or how to close the gap (a test, a coverage filter, or a design change). It reads an existing cvdata, .cvt file, sim-with-coverage output, or Simulink Test result; it never runs cvsim to collect coverage.
中文简介正在准备中。当前显示原文说明。
Use the open-source free `coverlet` toolchain for .NET code coverage. Use when a repo needs line and branch coverage, collector versus MSBuild driver selection, or CI-safe coverage commands. USE FOR: coverlet setup; CI line or branch coverage; choosing between collector and MSBuild drivers. DO NOT USE FOR: coverage report rendering by itself; repos that intentionally use a different coverage engine. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
中文简介正在准备中。当前显示原文说明。
Use ManagedCode.Storage when a .NET application needs a provider-agnostic storage abstraction with explicit configuration, container selection, upload and download flows, and backend-specific integration kept. USE FOR: integrating ManagedCode.Storage into a .NET application; reviewing how a project abstracts file or object storage; deciding whether to centralize storage provider. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
中文简介正在准备中。当前显示原文说明。
Write effective unit tests with Jest, Vitest, or pytest. Covers the test-doubles taxonomy (stub/spy/mock/fake), Arrange-Act-Assert, coverage threshold configuration and CI gating, snapshot testing, fake timers, and mutation testing with Stryker/mutmut. Use when: "unit test," "Jest," "Vitest," "pytest," "mock," "coverage threshold," "test doubles," "mutation testing," "fake timers," "snapshot test." Not for: interpreting coverage reports or finding coverage gaps — use coverage-analysis; AI generating the test code for you — use ai-test-generation; auditing existing tests for smells — use ai-qa-review; browser/component rendering assertions — use cypress-automation or visual-testing. Related: coverage-analysis, ci-cd-integration, ai-test-generation, shift-left-testing.
中文简介正在准备中。当前显示原文说明。
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, Gemini/VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-skill.
中文简介正在准备中。当前显示原文说明。
Use when choosing, implementing, or reviewing browser storage such as localStorage, sessionStorage, IndexedDB, cookies, client persistence, offline data, secure storage, or cleanup strategy; Chinese triggers include browser storage, client persistence.
中文简介正在准备中。当前显示原文说明。
S3, multipart uploads, CDN integration, and presigned URLs for file storage. Activate on: file upload, S3, presigned URL, multipart upload, CDN, blob storage, image upload, media storage. NOT for: data warehouse storage (use lakehouse-architect), database design (use dimensional-modeler).
中文简介正在准备中。当前显示原文说明。
Europe PMC RESTful Web Service 多源文献聚合检索原子 skill。**使用本 skill 进行医学文献广召回 / RAG 知识库构建 / 跨库聚合 / 预印本扫描 / 全文链接发现**。一次调用同时召回 PubMed (MED) + PMC + AGRICOLA + CABI + 预印本(bioRxiv / medRxiv / ChemRxiv / Research Square)+ NCBI Bookshelf + 专利,自动按 PMID/PMCID/DOI 三级去重,返回完整元数据(全文 OA 链接、citations、grants 资助信息)。**定位:广召回 · 多源 · RAG 友好**(与 pubmed-eutils 互补 — 后者做单源精准官方检索 + Clinical Queries;本 skill 做"撒网"式多源聚合)。触发词:Europe PMC / EuropePMC / 多源文献聚合 / 广召回 / RAG 召回 / RAG 知识库 / 预印本搜索 / preprint search / bioRxiv / medRxiv / ChemRxiv / DOI 检索 / DOI lookup / 全文链接 / full-text links / OA 全文 / PMCID / 灰色文献 / grey literature / 跨库去重 / 资助检索 / grant search / NIH funded / Wellcome funded / citations metadata。**不做**:NCBI E-utilities 直检(→ pubmed-eutils)、临床试验注册(→ clinical-trials-v2)、全文 XML 抽取(→ bioc-fulltext-fetch)、实体识别(→ pubtator-entity-search)、证据分级(→ medical-evidence-grading)、参考文献终态写入(→ evidence-appendix-sync)。
中文简介正在准备中。当前显示原文说明。
Audit Azure Blob and ADLS storage accounts for public access exposure, weak or long-lived SAS tokens, missing encryption at rest, disabled HTTPS-only traffic, and outdated TLS versions using the azure-mgmt-storage Python SDK.
中文简介正在准备中。当前显示原文说明。
Repository または subsystem を対象に、source-only で明示的なセキュリティ監査を行う entry skill。 通常の PR セキュリティレビューとは分離し、reconnaissance、scope 固定、既存 security skill への委譲、 evidence と unresolved hypothesis、observe-only SecurityAuditCoverage、coverage critic、 structured audit artifact と repeat-run coverage を扱う。target-controlled code は実行しない。
中文简介正在准备中。当前显示原文说明。
Use when working with Codecov — codecov coverage tracking management. Covers coverage reporting, PR comments, flag management, component analysis, and coverage trend tracking. Use when managing Codecov configuration, analyzing coverage reports, debugging coverage uploads, or configuring coverage thresholds.
中文简介正在准备中。当前显示原文说明。
Audit Azure Blob and ADLS storage accounts for public access exposure, weak or long-lived SAS tokens, missing encryption at rest, disabled HTTPS-only traffic, and outdated TLS versions using the azure-mgmt-storage Python SDK.
中文简介正在准备中。当前显示原文说明。
Audit Azure Blob and ADLS storage accounts for public access exposure, weak or long-lived SAS tokens, missing encryption at rest, disabled HTTPS-only traffic, and outdated TLS versions using the azure-mgmt-storage Python SDK.
中文简介正在准备中。当前显示原文说明。
Windows アプリ開発 (Windows App SDK / WinRT) のファイル・設定・データ保存リファレンス。 Windows.Storage の StorageFile, StorageFolder, IStorageItem, FileIO, PathIO, CachedFileManager, DataReader, DataWriter, BasicProperties。ApplicationData, ApplicationDataContainer, ApplicationDataCompositeValue のローカル・ローミング設定。 FileOpenPicker, FileSavePicker, FolderPicker, KnownFolders, StorageApplicationPermissions (FutureAccessList / MostRecentlyUsedList)。 JsonObject, JsonArray, XmlDocument, SQLite, EF Core, Microsoft.Data.SqlClient (SQL Server), Cosmos DB, MySQL, MongoDB 接続。
中文简介正在准备中。当前显示原文说明。
S3, multipart uploads, CDN integration, and presigned URLs for file storage. Activate on: file upload, S3, presigned URL, multipart upload, CDN, blob storage, image upload, media storage. NOT for: data warehouse storage (use lakehouse-architect), database design (use dimensional-modeler).
中文简介正在准备中。当前显示原文说明。
Adopt a virtual Ragdoll cat at animalhouse.ai. Goes limp when held. Maximum trust potential. Fragile if neglected. Feeding every 6 hours. Rare tier cat.
中文简介正在准备中。当前显示原文说明。
Adopt a virtual Dragon exotic animal at animalhouse.ai. Mythical. Eats concepts. Feed it "courage" or "patience." Feeding every 24 hours. Extreme tier animal.
中文简介正在准备中。当前显示原文说明。