Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Orchestrate high-quality front-end page generation from short product prompts. Use when Codex needs a single main skill that coordinates UI structure, visual hierarchy, and natural product copy for landing pages, dashboards, app screens, workspaces, settings pages, analytics views, tables, and similar interfaces.
Diagnose AI-generated or AI-assisted images that "look off", feel generic, fail commercially, or need prompt/image-to-image repair. Use when the user uploads or references an image and asks why it is not good enough, how it differs from better references, which professional roles would critique it, how to improve…
WeChat Mini Program automated build + debug workflow with version-based auto-selection between official Skills (wechatide CLI) and automator (miniprogram-automator). Covers npm build, appid verify, DevTools launch, 31 automation ops via helper daemon, and enriched E2E methodology requiring console/view/style checks at…
Use when leaving a project, joining a project, or performing any project/module handover. Detects .handoff/ directory presence but always confirms intent before acting.
Create, revise, and production-letter comic strips, including generated comic art, speech balloon placement, mastheads, strip aspect ratios, readable typography, and export-ready PNGs. Use when Codex is asked to make a comic, comic strip, webcomic, recurring character strip, expression sheet, title/masthead, speech…
Checks a prompt before running it: scores prompt quality and suggests an improved version, then recommends the ideal Claude model, /effort level, and which skills/tools will be used. Use when you want to improve your prompt and plan the run configuration — type /prompt-check followed by your prompt.
A workflow for solving China’s National Undergraduate Electronic Design Contest (TI Cup), from understanding a task to designing circuits, writing code, compiling, flashing, and debugging. It can generate wiring diagrams and support MCU, FPGA, simulation, and PCB work, but physical wiring, soldering, and instrument operation still need a person.
A converter for CNNVD XML files, where CNNVD is China’s national database of information-security vulnerabilities. It changes newer XML files into the older format by renaming tags and normalising their structure.
Search the web from the shell using curl, grep, sed, and python for research, fact-checking, and data gathering. Activates when the user asks to search, research, look up, investigate, or find information online — especially when structured extraction, multi-source comparison, or automated pipeline-style research is…
AnyFinancial Backtesting pillar. Run realistic event-driven backtests with NautilusTrader, including historical data acquisition through data/SKILL.md and execution/reporting. Use for strategy simulation, signal evaluation, Sharpe/drawdown/returns, in-sample vs out-of-sample, walk-forward, or parameter comparison. Do…
Grill an app idea before any code is written — two waves of hard product questions, each with a recommended answer the user edits or accepts — then hand off to the BEFOREVIBE MCP connector for the visual storyboard, production-ready PRD, logo and screen mockups. Use when the user shares a new app or product idea, asks…
Author, edit, debug, and interpret NONMEM control streams (.ctl, .mod), datasets, and output files for population PK/PD modeling. Use whenever the user mentions NONMEM, NM-TRAN, PREDPP, control streams, $PROBLEM/$INPUT/$DATA/$SUBROUTINES/$PK/$ERROR/$THETA/$OMEGA/$SIGMA/$ESTIMATION blocks, ADVAN/TRANS routines…
Wire up the Telegram Bot API foundation. Covers how the HTTP client works (long polling vs webhook), how grammY wraps it (Bot instance, ctx, command routing, callback queries, middleware), the agntdev inlined toolkit (createBot / makeBot), the hard limits (callbackdata 64 BYTES, message 4096 chars), parsemode (HTML…
Prepare a clean Codex handoff when the user types /switch-window, including current context, memory, state, validation, and instructions for a new session without copying the old conversation. Use this skill for /switch-window, switch window, new Codex window handoff, or transferring work to another Codex session.
Use when designing, implementing, reviewing, refactoring, or maintaining software in any programming language where security is a requirement. Apply secure-by-design principles, identify vulnerabilities, and recommend industry best practices throughout the software development lifecycle.
Session wrap-up workflow for preserving current project progress and preparing handoff artifacts for a later Codex session. Use when the user expresses session-ending or handoff intent such as /end-this-session, /end-this-session --full, ending work for today, saving progress, preparing a handoff, wrap up, finish…
Automated scoping literature review generator for Health Informatics. Given a topic, an agent with websearch executes 8 sequential stages (query → search → screen → snowball → extract → rank → synthesize → write) to produce an 8-paper scoping review markdown draft aligned to the HINF 5016 grading rubric. Use when the…
Build a reusable Chinese writing-voice skill from a user's own articles. Use when the user asks to distill their writing style, create a personal writing skill, or write in their established Chinese voice.
★not rated 2 2mo agoA46 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: