Skill Claude CodeCodex
A code-review add-on that checks selected changes for defects before they are merged. It can also run a separate audit path.
5,073 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
A code-review add-on that checks selected changes for defects before they are merged. It can also run a separate audit path.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 118 tokens together
SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx proxy configurations with auth integration.
Plugin Claude Code
Skills for Python/FastAPI development and git workflows.
Peaky8linders/eu-ai-act-scanner
Command Claude Code
Show real-world and research-demonstrated security incidents that map to a scanner dimension, EU AI Act article, or threat category. Surfaces OWASP LLM/ASI, NIST AI RMF, and MITRE ATLAS cross-references alongside published mitigations.
bestdeejay-design/agent-skills
Skill Claude Code
End-to-end presentations from a topic — outline -> JSON spec -> 16:9 HTML slides (with mandatory Playwright verification) and real .pptx (full 14-type design system), plus strategy presets, PDF export, and deck-quality audits. One command per stage.
Skill Claude CodeCodex
Create, storyboard, render, resume, repair, and export finished original manga/anime comics from a short prompt, prose story, pasted narrative, or local .txt/.md source. Use when the active agent should produce editable plans, consistent panel PNGs, composed page PNGs, a PDF, manifest, and transparent QA report…
Skill Claude CodeCodex
Execute Python code in an E2B Firecracker sandbox with human review.
Skill Codex
Run bounded SELECT queries through an Apache Superset SQL Lab connection on Windows. Use when a user wants an Agent to configure a supported Superset instance, test connectivity, inspect tables or columns, execute SELECT queries, export small results, preserve query evidence, or diagnose authentication, permission…
MCP server Claude CodeCodexCursor +2
MCP server "pathfinder" as configured in himkt/pathfinder. Launched with pathfinder -w . -e py -e pyi -s uvx ty server. Needs 1 environment variable to run.
Skill Claude CodeCodex
Use this skill when adding a new feature vertical to this template — a domain aggregate with its port, repository, application service, DTOs, endpoint, and tests. Trigger it for requests like "add an endpoint", "add a new entity", "build the X feature", or "wire up a new service".
Skill Claude CodeCodex
A development rule for a FastAPI and SQLite project that requires tests to run with `pytest -v`, then requires failures to be fixed and tests rerun until coverage reaches 100%. FastAPI is a Python web framework, and pytest is a Python testing tool.
Skill Claude CodeCodex
Use this skill when the user asks to use GalSpec to fit a spectrum, do spectral fitting with GalSpec, or fit AGN or galaxy emission-line or absorption-line spectra with GalSpec.
Skill Claude CodeCodex
Execute approved Hardproof tasks during IMPLEMENT with focused tests, durable task updates, and scope-controlled code changes.
Skill Claude CodeCodex
Personal code, documentation, architecture, and GUI conventions for TypeScript and Python work.
Skill Claude CodeCodex
Plan a Python 3 modernization sweep (f-strings, super(), type hints) as a series of mechanical PRs, not one mega-PR.
Skill Claude CodeCodex
Convert a PowerPoint .pptx into a browser presentation using the bundled converter, preserving supported formatting and media while reporting conversion gaps. Use when the requested output is HTML, not when editing the source deck.
adrunkhuman/marimo-opencode-skill
Skill Claude CodeCodex
Author interactive reactive Python notebooks with marimo. Covers interactive cell execution, reactive UI, SQL, state management, deployment, and export. For interactive notebooks, NOT Cell.run() API.
Cursor rule Cursor
You are a Python programming assistant. You will be given a function implementation and a series of unit test results. Your goal is to write a few sentences to explain why your implementation is wrong, as indicated by the tests. You will need this as guidance when you try again later. Only provide the few sentence…
Cursor rule Cursor
Rules for writing clean python code.
Skill Claude CodeCodex
Use when authoring or diagnosing DataLens JavaScript Editor table, Gravity, Advanced, Markdown, or selector charts.
MCP server Claude CodeCodexCursor +2
MCP server "regula" as configured in kuzivaai/getregula. Runs locally from the regula-ai Python package.
MCP server Claude CodeCodexCursor +2
MCP server for M-Pesa Daraja API and Africa's Talking. 23 tools including getmodelhint(). Tested with claude-sonnet-5. Runs locally from the mpesa-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP Permission Auditor — scan, enumerate, and risk-score all locally configured MCP servers. Runs locally from the mcp-audits Python package.
Skill Claude CodeCodex
Use only when the user explicitly mentions "rapids-first" or "RAPIDS first", to prefer the RAPIDS GPU stack (cudf, cuml, cupy, cupyx) and its zero-code accelerators over pandas, scikit-learn, numpy and scipy when writing Python data-science, ML, ETL or numerical code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: