Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,800 indexed, measured the same four ways as everything else here.
Intent-bound action authorization for AI agents — authorise before a credential is used, require human approval for sensitive actions, and prove every action traces back to the instruction that authorised it. Runs locally from the delego Python package. Needs 1 environment variable to run.
★not rated 25 5mo agoA
tokens not measured
originalApache-2.0
NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels. MANDATORY: every optimization MUST start with NCU profiling, followed by multi-dimensional analysis, then targeted code modification, then re-profiling to verify. Supports roofline, memory hierarchy, warp stalls, instruction mix…
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Inspect Parquet file metadata with the iParq CLI, including compression, encodings, physical and logical types, row groups, sort order, statistics, geospatial statistics, dictionary pages, page indexes, page locations, Bloom filters, and storage sizes. Use when an agent needs to explain how one or more .parquet files…
An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.
Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing supported findings for a Pre-Award Agent. A…
A Codex stdio MCP server that generates repo-local tldraw diagrams and detects code graph drift. Runs locally from the codex-tldraw-mcp npm package. Needs 1 environment variable to run.
★not rated 25 10d agoA
tokens not measured
originalMIT
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Imperative Command Line Interface for AI Workload Orchestration across 17 GPU cloud providers. Runs locally from the terradev-cli Python package. Needs 3 environment variables to run.
★not rated 25 2mo agoA
tokens not measured
originalApache-2.0
A Model Context Protocol (MCP) connector for Trino, enabling seamless integration between MCP-compliant services and Trino query engine. Runs locally from the mcp-trino-python Python package.
★not rated 25 todayA
tokens not measured
originalApache-2.0
Query 47 EU regulations (GDPR, NIS2, DORA, AI Act) - 2,438 articles, 3,712 recitals, ISO 27001. Runs locally from the @ansvar/eu-regulations-mcp npm package.
★not rated 25 3mo agoA
tokens not measured
originalApache-2.0archived
MCP tool for Google search and webpage content extraction using Chrome browser. Works with Claude to enable Google search and content fetching capabilities. Runs locally from the @cmann50/mcp-chrome-google-search npm package.
★not rated 25 1y agoA
tokens not measured
originalMIT
An MCP server for your Strapi CMS that provides access to content types and entries through the MCP protocol. Runs locally from the strapi-mcp npm package.
★not rated 25 1y agoA
tokens not measured
originalMIT
Use jj (Jujutsu) for local version control instead of git. Activate when: the repo has a .jj/ directory, the user or project config mentions jj, the user says 'use jj', or any version control operation is needed in a jj-managed repo. Also use this skill when the user asks to commit, branch, stash, rebase, or perform…
A writing and decision-making style guide based on Flood Sung’s published Chinese articles, ideas, and answers. It helps an agent respond in his stated viewpoint and tone.
Use when studying, reverse-engineering, comparing, reviewing, or learning from AI skill packages, SKILL.md files, Claude/Codex skills, prompt workflows, or agent playbooks; use when the user wants reusable skill design patterns, a keep/cut review, Markdown report, structured pattern notes, or multi-page web handbook.…
World-class information architecture workflows for product and design teams: define navigation, taxonomy, labeling, content models, and page hierarchy so complex products feel obvious. Use when designing or redesigning an app/website structure, menus, docs/knowledge base IA, onboarding flows, search/filtering…
★not rated 25 9mo agoA77 tokens
originalMIT
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: