Loading...
Loading...
Found 2,708 Skills
Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically (weekly) or on demand.
Alibaba Cloud Tablestore Agent Storage Skill. Use for building and managing Tablestore-based knowledge bases with the `tablestore-agent-storage` Python SDK. Capabilities: - Install and configure the `tablestore-agent-storage` SDK - Create, describe and list knowledge bases (with subspace and custom metadata support) - Upload local files or import OSS documents into a knowledge base - Query document status and list documents - Perform hybrid retrieval (dense vector + full-text) with metadata filtering - Set up local directory sync scripts and scheduled tasks for automatic knowledge base updates Triggers: "知识库", "tablestore", "ots", "表格存储", "agent storage", "knowledge base", "向量检索", "文档上传", "文档导入", "知识库同步", "tablestore-agent-storage", "AgentStorageClient"
Test coverage analysis, identify gaps, and generate missing tests to achieve over 80% coverage. Trigger conditions: user requests for test coverage analysis, test coverage improvement, and test writing.
[Pragmatic DDD Architecture] Guide for Server and Client components in Next.js App Router. Use when creating any .tsx file under presentation/components/, pages, or layouts — also when deciding whether to add "use client" to an existing component, passing data from a Server Component to a Client Component, composing Server content inside a Client slot, handling the VO serialization boundary, creating Compound Components, separating logic for Mobile/Desktop screens, or styling with `cva` and `cn`. Covers: Server vs Client decision, async Server Component patterns, creating getSession callbacks for Use Cases, Client Component restrictions, toBranded() boundary pattern, children slot composition, and props interface rules. Depends on 'use-cases' and 'server-actions'.
Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking strategies, hybrid search, re-ranking, vector databases, evaluation, agentic RAG, multimodal RAG...
Use the Paragraph REST API or TypeScript SDK to manage posts, publications, subscribers, and coins on paragraph.com. No installation required — just HTTP requests or `npm install @paragraph-com/sdk`. Trigger when the user asks to integrate with, build on, or call the Paragraph API.
Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.
Kubernetes storage management for PVCs, storage classes, and persistent volumes. Use when provisioning storage, managing volumes, or troubleshooting storage issues.
RAG, embedding, vector search를 통해 사내/최신 데이터를 LLM 응답에 연결하는 방법과 선택 기준을 다루는 모듈.
Comprehensive toolkit for validating, linting, testing, and automating Terragrunt configurations, HCL files, and Stacks. Use this skill when working with Terragrunt files (.hcl, terragrunt.hcl, terragrunt.stack.hcl), validating infrastructure-as-code, debugging Terragrunt configurations, performing dry-run testing with terragrunt plan, working with Terragrunt Stacks, or working with custom providers and modules.
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
Minimal OSSUTIL 2.0 smoke tests. Validate config, list bucket, and upload/download with OSS.