Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,730 indexed, measured the same four ways as everything else here.
Distills the current Claude Code session into a structured Obsidian note with queryable YAML frontmatter. Use when the user wants to capture, summarize, or archive a coding session, for example at the end of a session, when wrapping up work, when asked to save session notes, or when using the /distill command.…
Build production-feel HTML prototypes for sales demos and reviews. Runs a discovery Q&A, scaffolds a zero-dep static site (HTML + Tailwind CDN + theme/layout switchers + URL-state + feedback overlay + control bar) and runs a design-quality loop. Use when the user says "prototype", "mockup", "demo", "pitch page"…
Query this repo's code graph instead of ls/grep/reading files blindly. Use whenever you are understanding the codebase or its architecture, tracing how something works, or searching for a symbol or term; before changing a symbol, to get its blast radius (dependent symbols, tests to run, API surface, and other indexed…
Find and download real, non-AI, public-domain artwork from museum open-access collections (The Met, Art Institute of Chicago, Cleveland Museum of Art, Rijksmuseum, Getty, SMK, Smithsonian) without leaving the CLI. Use when the user wants an image, artwork, painting, hero image, background, or visual for their project…
Use Supadata to fetch transcripts, captions, or subtitles from YouTube, TikTok, Instagram, X (Twitter), Facebook, or video file URLs; pull metadata for social videos and YouTube channels/playlists; scrape web pages to clean Markdown; crawl entire sites; map a site's URLs; or use AI to extract structured data (JSON)…
Write skillprobe YAML tests for LLM skills. Use when asked to write tests, create test scenarios, test a skill, generate skillprobe tests, or check whether a skill activates correctly.
Orchestrate coding agents through Herdr as the user's authorized proxy from Codex CLI, Claude Code CLI, or Grok Build CLI. Use only when the current CLI is already running inside Herdr and the user explicitly asks to use Herdr to delegate, parallelize, coordinate, monitor, redirect, test, review, or collect work from…
Reference Claude Code's prompt engineering patterns for AI/Agent development. Provides best practices for system prompts, tool design, agent orchestration, and safety.
A Chinese-language product decision assistant for internet businesses in mainland China. It helps turn business questions into a clear judgment, actions, risks, and only the most important follow-up questions.
Use this skill when the user is debugging a bug, error, crash, or issue that might be tied to a specific point in time (e.g., "crash from 3 hours ago", "bug in v2.4.1", "last night's deploy"). It guides the agent to reconstruct the historical code state and analyze the bug in that context.
A daily report of popular short-drama articles from WeChat public accounts, a Chinese publishing platform, grouped by story themes and accompanied by writing insights.
Use Lantern's application MCP to create, draw, compose, revise, organize, inspect, or review a creator's comics through the domain capabilities Lantern currently exposes. Use for comic work in Lantern; do not use for developing the Lantern source repository.
Codex-native Teaching Skills suite for university professors — the full teaching lifecycle: course design, lesson building, assessment, student mentoring, submission auditing, reflection, plus slide-deck rendering, executable labs, video scripting, course publishing, TA coordination, accreditation mapping, bilingual…
Author, validate, consume, and navigate Open Knowledge Format (OKF) knowledge bundles — directories of markdown files with YAML frontmatter that describe datasets, tables, metrics, APIs, playbooks, and attested computations. Use this skill whenever the user mentions OKF, knowledge bundles, a knowledge catalog…
Cycling training plans, power zones, FTP testing, intervals, periodization, indoor/outdoor training, race preparation, training-load analysis, and recovery guidance. Use when Codex needs to design cycling workouts, calculate FTP-based zones or TSS, analyze training data, manage CTL/ATL/TSB, or answer cyclist training…
Generate source-backed Chinese PDF reports for World Cup or international football match previews, combining viewing guide, mobile-friendly squads, tactical lineups, referee and environment effects, odds, score modeling, risks, and a concentrated fixed-budget lottery plan. Use when the user asks in Chinese or English…
Design and scaffold a new trapstreet.run task to evaluate a given agent/skill/tool -- the reverse of trapstreet-solution-scaffold (a solution for an existing task). Generates the mechanical parts (traptask.yaml, judge.py/grader.py on the TRAPTASKMANIFEST contract, buildcases.py's validate-then-render pipeline) and…
A tool for creating structured GitHub Issues in Chinese, with one section written for people and another organized for AI tools. GitHub Issues are records for bugs, tasks, and feature requests, and sub-issues break larger work into linked parts.
Control Unreal Engine Editor via OpenClaw Unreal Plugin. Use for Unreal development tasks including level/actor management, transforms, PIE control, debugging, input simulation, and console commands. Can create/delete actors, save levels, run console commands, simulate input, and capture viewport screenshots and logs.…
Voice-style remote control for the Logitech Harmony Hub. Translate natural-language requests ("schalte Pro7 ein", "lauter", "Apple TV") into the matching hub command via MCP or the harmony CLI.
★not rated 6 1mo agoA48 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: