NeVibeCode · 245 items
Skills and MCP tagged “python”
python-pro subagent A subagent for type-safe Python code across web APIs, system utilities, and complex applications. Use it when async patterns and broad type coverage matter.
Claude Code
11,689installs
python-resilience skill A Python skill for retries, timeouts, backoff, and transient failure handling. Use it when external services or network calls need bounded recovery.
Claude Code CX Codex Cursor
11,755installs
python-pro subagent A subagent for modern Python 3.12+ development, async code, testing, APIs, and performance work. Use it when a project needs deeper Python guidance.
Claude Code CX Codex Cursor
11,689installs
xlsx-author
official skill Skill to create .xlsx files on disk without a running Excel when an agent operates headless. Use it to deliver a finished workbook as a file artifact instead of editing live.
Claude Code CX Codex Cursor +1
1,400installs
python-observability skill A skill that gives your agent Python observability patterns: structured logging, Prometheus metrics, distributed tracing. Useful when production breaks and the logs don't tell you where.
Claude Code CX Codex Cursor
11,547installs
python-configuration skill This skill moves Python settings into environment variables and validates typed configuration. Use it for secrets and environment-specific behavior.
Claude Code CX Codex Cursor
11,508installs
developing-genkit-python
official skill A skill for building Genkit apps in Python: generation, streaming, tools, flows and agents. Useful when your agent fumbles imports or Genkit API calls.
Claude Code Gemini CLI CX Codex
3,600installs
python-background-jobs skill This skill shows how to move long-running Python work out of request handling and into workers. Use it for queues, exports, notifications, and event-driven flows.
Claude Code CX Codex Cursor
11,137installs
python-resource-management skill This skill guides Python resource handling with context managers, cleanup, and streaming state. Use it when code opens files, database connections, or other resources.
Claude Code CX Codex Cursor
11,000installs
airflow-dag-patterns skill This skill helps design Apache Airflow DAGs, connect tasks, and test pipelines. Use it for ETL workflows, batch jobs, and failed-run debugging.
Claude Code CX Codex Cursor
11,000installs
temporal-python-testing skill Guidance for testing Temporal workflows in Python with pytest, time-skipping, activity mocks, and replay checks. Use it while building workflow tests or investigating failures.
Claude Code CX Codex Cursor
10,900installs
scope-creep-detector skill Compares a git diff against a stated intent and flags files that don't belong: stray dependencies, API renames, config edits, oversized hunks, and formatting. Runs locally, offline, no network calls.
Claude Code CX Codex Cursor +1
605installs
eval-driven-dev
official skill This skill sets up evaluations for Python apps that call an LLM, from defining criteria to scoring real application runs. Use it when you need to investigate answer quality or add end-to-end QA.
GitHub Copilot
3,900installs
acquire-codebase-knowledge
official skill This skill maps an existing repository and creates docs for its stack, architecture, tests, and risks. Use it when you are onboarding into a codebase.
GitHub Copilot
2,200installs
microsoft-agent-framework
official skill Guides GitHub Copilot through building, updating, reviewing, and explaining Microsoft Agent Framework applications. It also covers migrations from Semantic Kernel and AutoGen.
GitHub Copilot
1,900installs
semantic-kernel
official skill This skill helps build and inspect Semantic Kernel applications using current documentation. Use it for projects involving plugins, function calling, or AI integrations.
GitHub Copilot
1,700installs
aws-cdk-python-setup
official skill This skill prepares an AWS CDK project in Python, covering prerequisites, project creation, dependencies, and deployment to AWS.
GitHub Copilot
1,600installs
ruff-recursive-fix
official skill Runs Ruff in a chosen scope, applies safe and unsafe fixes in passes, and asks for a decision when an automated correction is ambiguous.
GitHub Copilot
1,500installs
agent-owasp-compliance
official skill Checks an AI agent codebase against the 10 OWASP ASI risks. Use it before production deployment, for security review, or when preparing an audit report.
GitHub Copilot
1,500installs
data-scientist subagent Subagent for exploratory data analysis, hypothesis testing, and building machine learning models directly in Claude Code.
Claude Code
3,342installs
geofeed-tuner
official skill Validates and refines CSV IP geolocation feeds against RFC 8805 standards. Useful for network operators and cloud providers publishing geofeeds.
GitHub Copilot
1,300installs
data-scientist subagent This subagent explores datasets, tests statistical hypotheses, and builds predictive models. It can be added to Claude Code, Codex, or Cursor.
Claude Code CX Codex Cursor
3,342installs
freecad-scripts
official skill Writes FreeCAD Python scripts and macros: 3D geometry, parametric objects, PySide dialogs. Useful when you automate CAD work.
GitHub Copilot
1,200installs
file-conversion skill Converts local media, documents, and data formats using tools already installed on your machine. Prevents uploading files to third-party APIs.
Claude Code CX Codex Cursor
3,100installs
backend-developer subagent Subagent for building backend APIs and microservices in Node.js, Python, and Go. Helps implement relational schemas, caching, and OWASP security rules.
Claude Code
2,724installs
arize-annotation
official skill Creates annotation schemas and review queues in Arize, then updates span labels through the Python SDK. Use it for human review workflows.
GitHub Copilot
1,100installs
phoenix-tracing
official skill This skill guides OpenInference tracing for LLM apps with Phoenix. Use it to set up instrumentation, define custom spans, or prepare tracing for production.
GitHub Copilot
1,000installs
phoenix-evals
official skill Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output.
GitHub Copilot
1,000installs
python-pypi-package-builder
official skill This skill guides Python package creation, testing, versioning, and PyPI publishing. Use it for libraries, SDKs, CLI tools, and framework plugins.
GitHub Copilot
943installs
marketing-skills skill A directory and router for marketing skills in Claude Code. It picks the right specialist skill for SEO, content, CRO, channels, and related tasks.
Claude Code
2,264installs
quant-analyst subagent Builds financial models, tests trading strategies against historical data, and calculates risk metrics. Built for algorithmic trading workflows.
Claude Code CX Codex Cursor
1,366installs
loop skill This skill runs recurring autoresearch experiments through CronCreate. Use it when an experiment should be checked on a schedule.
Claude Code
1,557installs
senior-architect skill Generates architecture diagrams, checks coupling, and detects dependency cycles in codebases. Helps teams make technical decisions and document ADRs.
Claude Code
1,494installs
research-summarizer skill Turns academic papers, whitepapers, and reports into structured briefs, extracts citations, and builds comparative matrices across documents.
Claude Code
1,190installs
code-reviewer skill Analyzes pull requests for risks and complexity, detects SOLID violations, and generates review reports. Helps inspect code changes before merging.
Claude Code
1,130installs
financial-analyst skill A Claude skill that runs financial ratio analysis, DCF valuation, budget variance checks and rolling forecasts from JSON data.
Claude Code
1,060installs
karpathy-coder skill Enforces Andrej Karpathy's 4 coding principles to prevent LLM over-engineering. Catches assumptions, keeps diffs surgical, and strips out unrequested abstractions.
Claude Code
1,053installs
gdpr-dsgvo-expert skill Scans code for GDPR and German BDSG privacy risks, builds DPIA reports, and tracks data subject rights deadlines.
Claude Code
980installs
senior-prompt-engineer skill Tests prompts against baselines, measures RAG retrieval metrics, and validates agent configs using three Python stdlib tools. Useful for disciplined prompt iteration without guess-driven edits.
Claude Code
970installs
senior-data-scientist skill Provides structured templates for A/B testing, feature pipelines, and machine learning validation. Designed for experiment analysis and tabular model workflows.
Claude Code
942installs
81–120 of 245