Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,763 indexed, measured the same four ways as everything else here.
End-to-end agent improvement pipeline. Analyzes raw execution traces, extracts insights, manages a skillbook, gathers domain context, defines metrics, builds a rubric, creates a prioritized action plan, presents it for review, and implements approved fixes. Trigger when the user says "improve my agent", "run the…
This skill extracts construction PDF plan binders into agent-consumable formats. It should be used when a contractor or homeowner provides a PDF binder of construction plans (site plans, floor plans, structural drawings, Title 24 reports) that needs to be parsed for permit review, corrections response, or plan check…
Expert LeetCode problem solver for optimized coding interview solutions. Use when: the user pastes a LeetCode problem, asks for an optimized algorithm, wants Python LeetCode code, needs a dry run, asks for line-by-line explanation, or wants help understanding data structures and algorithms for coding interviews.
A contract-review skill from CSlawyer1985 that follows a defined seven-step review process. The description includes identifying the client and their position, then creating review state.
Run scalable, isolated live QA for nac development. In NAC orchestrator mode the top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this…
A guide to creating and maintaining character cards in the cardproject system. It explains how to read, add, change, delete, validate, and preview the cards and their sections.
Use when the user asks you to add a feature, tool, panel, command or integration to ACRYL itself (build a plugin or extension). The end-to-end workflow, from reading the docs to a live plugin.
A skill for explaining maths and physics through Manim animations and interactive web pages. Manim is a tool for creating programmatic mathematical animations.
NestJS best practices and architecture patterns for building production-ready applications. This skill should be used when writing, reviewing, or refactoring NestJS code to ensure proper patterns for modules, dependency injection, security, and performance.
Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen…
A tool for downloading public WeChat Official Account articles and collecting article histories. WeChat Official Accounts are Chinese publisher or business pages, and the tool supports login, account selection, and scheduled syncing when required.
MCP server for MikroTik integration with Claude and other AI assistants. Runs locally from the mcp-server-mikrotik Python package. Needs 5 environment variables to run.
★not rated 296 29d agoASocket: warn
tokens not measured
originalMIT
An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.
Video Jungle MCP Server for Adding, Analysing, Searching, and Editing Videos. Runs locally from the video-editor-mcp Python package. Needs 1 environment variable to run.
A context weaving tool for LLMs. Runs locally from the @hsingjui/contextweaver npm package.
★not rated 296▲
+1 2mo agoA
tokens not measured
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: