Encontre a capacidade ideal para o seu agente.
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
Converts JSON data snippets into Python Pydantic data models.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
A fundamental skill that demonstrates the basic execution of a Python script. It serves as a "Hello, World!" example for the skill system, verifying that the environment is correctly set up and that the agent can execute scripts.
Python and wxPython development reference patterns, common pitfalls, framework-specific guides, desktop accessibility APIs, and cross-platform considerations. Use when building, debugging, packaging, or reviewing Python desktop applications.
Your intelligent developer command center -- start here for any Python, wxPython, desktop app, NVDA addon, accessibility tool building, desktop accessibility, or general software engineering task. Routes to specialist agents across the developer, web, and document accessibility teams.
Python and wxPython development reference patterns, common pitfalls, framework-specific guides, desktop accessibility APIs, and cross-platform considerations. Use when building, debugging, packaging, or reviewing Python desktop applications.
Build Python applications using Beanie, the async MongoDB ODM built on Pydantic. Use when writing or modifying Beanie Document models, queries, updates, linked/embedded documents, aggregations, or init_beanie setup. Also use when the user mentions Beanie, MongoDB with Pydantic, Link[], BackLink, fetch_links, beanie.operators, or any Beanie ODM patterns — even if they don't explicitly say "Beanie." Covers the full lifecycle: document definition, CRUD, relations, query operators, update operators, aggregation, and state management.
Use when the user asks to refactor Python code, restructure modules, improve code organization, extract functions/classes, simplify complex logic, or reduce duplication — without changing external behavior. Also use when the user mentions "clean up this code", "make this more readable", "break this apart", or asks to reorganize Python files, even if they don't say "refactor" explicitly.
Create and execute temporary scripts (Python, Node.js, shell) during workflow execution for API integrations, data processing, and custom tools. Use when user needs to interact with external APIs, process data with specific libraries, or create temporary executable code.
Execute AI-generated Python/Bash/Node.js on remote servers via the appmesh Python SDK.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation.
Automatically generate Excel reports from data sources including CSV, databases, or Python data structures. Supports data analysis reports, business reports, data export, and template-based report generation using pandas and openpyxl. Activate when users mention Excel, spreadsheet, report generation, data export, or business reporting.
Write or modify CuTe DSL GPU kernels for the Surogate framework. Use when the user wants to create CUDA kernels using CuTe DSL/Python (e.g., "write a CuTe kernel", "implement a fused kernel", "optimize kernel with CuTe DSL"). Guides through kernel implementation, compilation, and integration with Surogate's JIT pipeline.
Generate or change idiomatic minimal Bash and Python scripts that use bzfs and bzfs_jobrunner for ZFS snapshot
Scaffold production-ready Python MCP servers using FastMCP. Use when creating new MCP servers, initializing MCP projects, generating server boilerplate, or setting up MCP development environments. Supports all MCP primitives (tools, resources, prompts) with Pydantic validation, async patterns, and proper project structure.
Provides AWS Lambda integration patterns for Python with cold start optimization. Use when deploying Python functions to AWS Lambda, choosing between AWS Chalice and raw Python approaches, optimizing cold starts, configuring API Gateway or ALB integration, or implementing serverless Python applications. Triggers include "create lambda python", "deploy python lambda", "chalice lambda aws", "python lambda cold start", "aws lambda python performance", "python serverless framework".
Apply production-ready Supabase SDK patterns for TypeScript and Python projects.
Develops data processing pipelines, integrations, and machine learning scenarios in SAP Data Intelligence Cloud. Use when building graphs/pipelines with operators, integrating ABAP/S4HANA systems, creating replication flows, developing ML scenarios with JupyterLab, or using Data Transformation Language functions. Covers Gen1/Gen2 operators, subengines (Python, Node.js, C++), structured data operators, and repository objects.
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送".
