Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,987 indexed, measured the same four ways as everything else here.
Use this skill whenever Claude needs to name, call, or validate a FileMaker function or script step — writing a calculation, writing a script, checking whether a function or script step exists, checking parameter order or count, or checking whether a script step is supported on a given platform (Pro, Go, WebDirect…
Reconstruct a geometric PNG (logo, icon, monogram) as a clean native SVG with exact geometry and gradients, using an analyse -> measure -> model -> check -> residuals iteration loop scored by perceptual metrics. Use when asked to vectorise, trace or convert a PNG/WebP logo to SVG, recreate a logo's geometry, rebuild a…
Reviews an existing MOSS wallet integration for security and correctness before launch on MegaETH. Use when auditing partner code rather than building it: produces findings grouped as Critical, Risky defaults, and Recommendations with concrete remediations. Checks for frontend-owned trust decisions, missing backend…
Convert Android XML layouts to Jetpack Compose. Use when asked to migrate Views to Compose, convert XML to Composables, or modernize UI from View system to Compose.
Perform a two-phase codebase rationalization on a Lovable project — a comprehensive read-only audit to find dead code, unused code, obsolete dependencies, duplicated implementations, and maintainability risks, followed by a strictly-scoped, approval-gated cleanup of only the batches the user explicitly approves. Use…
Deploy, run, troubleshoot, and quality-optimize MiniMax H3 local text-to-video, image-to-video, reference-to-video, native audio, and social-media video workflows on Windows PCs with constrained NVIDIA VRAM or system RAM. Use when users mention MiniMax H3/Hailuo H3 local deployment, ComfyUI H3 models, 8GB GPUs…
Draw math geometry diagrams as PNG or SVG images using the Geometry DSL compiler. Use when the user asks to draw, shade, label, illustrate, or visually explain geometry, recreate a reference diagram, produce or repair Geometry DSL, or diagnose a diagram that looks wrong. Write DSL source, validate it with the bundled…
Build structured short-form videos in Remotion from a brief or source material. Use when the user wants a reusable workflow covering storyboard structure, brand elements, music, ratio adaptation, cover linkage, render, and output verification.
A local, offline tool for comparing financial transaction records, such as bank statements and payment ledgers, and preparing differences for human review.
Use when the user asks for an idea generator, conceptual crossbreeding, mutation, evolution, recombination of existing ideas, or novel concepts derived from unlike sources; also use for follow-ups that evolve, cross, or lock elements of previously generated ideas. Do not trigger for generic brainstorming with no…
Fetches MDN Web Docs as raw Markdown by mapping the developer.mozilla.org URL to its source file in mdn/content (en-US) or mdn/translated-content (other locales) on GitHub and curl-ing the raw blob. Cleaner and more compact than rendering the SPA page; falls back to WebFetch on the original URL when the path mapping…
Cook raw brandbooks into agent-ready skills. Use when a user wants to convert brand guidelines, a Figma library, PDF, presentation, website, asset archive, interview, or loose identity system into a reusable brand-specific Agent Skill, update or audit one, or prepare a brand skill for presentations, documents…
A process for turning a book into a practical, reusable method guide rather than a simple summary. It researches the book’s methods, decision rules, examples, limits, and supporting criticism.
MCP server for AllRatesToday — let AI coding tools (Claude Code, Cursor, Claude Desktop) fetch real-time and historical currency exchange rates. Runs locally from the @allratestoday/mcp-server npm package. Needs 1 environment variable to run.
★not rated 4 yesterdayA
tokens not measured
originalMIT
A set of rules for coordinating coding work between multiple AI agents. It turns a request into an agreed plan, defines what counts as success, and supports work that can pause and continue later.
A Chinese-language workflow assistant for AMOS structural equation modeling, a method for testing relationships among measured and hidden variables using survey data.
★not rated 4 2mo agoA385 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: