Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,940 indexed, measured the same four ways as everything else here.
Build an evidence-backed working model of an existing codebase. Use when you must orient in a large or unfamiliar repository; explain architecture or a subsystem; trace a request, runtime, control, or data flow for a concrete question or bug; analyze a branch, commit, diff, or pull request for behavioral impact and…
A Chinese-language image-creation skill for turning an article's key idea, process, or metaphor into hand-drawn illustrations. It uses a consistent brown-haired, round-glasses character on a mostly white 16:9 canvas.
Use when designing or reviewing the tools an LLM agent will call — choosing tool boundaries, argument and result shapes, retrieval/search/get decompositions, MCP or goa-ai toolset surfaces — or when an agent misuses existing tools (wrong tool picked, IDs carried between calls, wrong dates computed, confident answers…
A Chinese-language skill that claims to analyse historical results for China’s Double Color Ball lottery and suggest numbers using statistical and traditional methods. The description does not provide evidence that its predictions improve the odds of winning.
Security audit agent skills for vulnerabilities and malicious patterns. Use when asked to "scan a skill", "check if a skill is safe", "audit a skill for security", "review skill security", "is this skill malicious", or when installing/reviewing any third-party agent skill. Accepts local SKILL.md files, skill…
Provides advanced operational capabilities for TouchDesigner including snapshots, production readiness validation, enhanced monitoring, and workflow automation. Use when you need production-grade reliability, backup/restore capabilities, or systematic quality assurance for your TouchDesigner projects.
Produces a lean, paste-ready session handoff so work can continue in a new conversation without re-paying the cost of the full chat. Emits a seven-block skeleton optimized for re-entry, not archival. Trigger this skill whenever the user says any of the following (exact or close paraphrase): "context summary"…
Ìlànà is a strict software engineering process operating system for coding agents. Load it whenever work touches requirements, elicitation, SRS, user stories, traceability, architecture or interface design, UI design principles, coding standards, code review, testing (unit, integration, system, acceptance), test…
Generates a complete pre-production reference brief specifically for character assets. Covers anatomy, facial topology, deformation zones, costume, skin, hair, and rig-readiness reference — the layers ref-brief doesn't go deep enough on. Triggers on "character reference", "I'm modeling a character", "humanoid…
Start the local DeepSeek Harness Web UI, provide a clickable session link, delegate a scoped coding task into the visible Web session, then independently review and verify the workspace changes. Use when the user asks Codex to use, show, control, or hand work to DeepSeek Harness.
Interview a person who wants to start or advance an Identity and Access Management career, then create a short and evidence-based career plan with a downloadable Markdown document when file tools are available. Use when the user wants help selecting an IAM role, researching IAM opportunities or target employers…
Camada estratégico-auditorial que precede a redação de peças no contencioso brasileiro. O advogado alimenta o caso; a skill classifica fatos, monta a matriz probatória, hierarquiza teses, antecipa o adversário, controla a jurisprudência em tripla camada e calibra a firmeza do tom pela solidez real de cada tese.…
Use when you know what component, flow, or interface you need but not yet the right accessibility approach. Best for turning WCAG 2.2 requirements into an accessible implementation plan with WAI-ARIA APG patterns before code hardens bad interaction and state patterns.
MCP server for the Google Ads Transparency Center — look up any advertiser's ads without an API key. Runs locally from the google-ads-transparency-mcp Python package.
★not rated 14 2mo agoA
tokens not measured
originalMIT
Build, test, and deploy production-quality MCP (Model Context Protocol) servers. Full lifecycle -- build locally, test interactively with MCP Inspector, iterate until working, then optionally deploy to Runlayer. Triggers include "build an MCP server", "create MCP tools", "implement MCP", "add tools for [service]"…
★not rated 14 8mo agoA84 tokens
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: