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.
A recipe for making the classic Snake game, where the player steers a growing snake toward food and loses by hitting a wall or its own body. It defines keyboard controls, scoring, collision handling, and restart behavior.
Authors, reads, and validates OKF (Open Knowledge Format) v0.2 bundles — directories of markdown files with YAML frontmatter used as agent-readable knowledge catalogs. Use when the user creates, edits, traverses, indexes, logs, migrates, or validates an OKF bundle, knowledge catalog, or agent-readable wiki, or…
Premium website builds with varied heroes, React Bits backgrounds, static index.html delivery, browser QA, and chat-only feedback. Use for Super-Web-Design or advanced landing/product/media sites.
A development skill for building HarmonyOS NEXT applications with ArkTS and ArkUI. HarmonyOS NEXT is Huawei’s application platform; ArkTS is its programming language and ArkUI is its interface framework.
Review one project for code elegance, beauty, developer joy, clarity, language conventions, naming, and locality. Evaluate the maintenance experience. Do not use this skill for defect, security, small-change, or visual UI reviews. Do not combine it with deep-codebase-review unless the user requests both skills.
Use when presenting shell commands or tool calls for user approval. Adds a human-readable explanation of intent, scope, and risk before the approval prompt.
★not rated 6 5mo agoC✓ AI review34 tokens
originalMIT
Use this when a user wants to monitor movie tickets, watch for seats, track IMAX 70mm seats, use Fandango, get notified when tickets or seats open, render a seat map PNG, or create a cron seat watch for a theater/movie/date window.
A guide and script for preparing Chinese software copyright registration documents. It produces a source-code document, a software user manual, and suggested application details.
An end-to-end assistant for mathematical modeling competitions, where participants use mathematical models and code to solve real-world problems. It supports problem breakdown, model selection and derivation, Python solving, visualizations, and paper writing in LaTeX or Word, with separate modeling, programming, and writing roles plus quality checks.
Use this skill when gameplay decisions feel flat, obvious, overwhelming, or random. Trigger on: 'choices don't matter', 'the game plays itself', 'analysis paralysis', 'players feel overwhelmed', 'combat feels random', 'players can't plan ahead', 'too much information on screen', 'nothing to think about between…
Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up…
World's most comprehensive IoT protocol engineering expert skill. Use whenever the user mentions any IoT protocol, standard, or technology across device management, messaging, LPWAN, PAN, cellular, industrial OT, security, data formats, smart energy, healthcare IoT, or automotive IoT. Trigger on: TR-069, CWMP, TR-369…
Enforce Python lint rules (Ruff), design guidelines (Google), and idiomatic Python patterns (Brandon Rhodes) for all Python code generation and edits. Rules must be applied while writing code, not only in review. Triggers on any task that writes, edits, or refactors Python code.
Production patterns for Hono v4+ backends with Bun, Drizzle ORM, Better Auth, Stoker, hono-openapi + Zod + Scalar, and TDD with Bun test runner. Use when building features, writing tests, reviewing code, or setting up auth/RBAC in modular monolith Hono projects. Apply whenever you see Hono route definitions…
Evidence-driven execution for tasks involving files, code, data, commands, tools, or concrete deliverables. Use to inspect real constraints, make minimal targeted changes, verify outcomes independently, and avoid unsafe side effects. Do not use for purely conversational tasks without external state or a deliverable.
Trigger before submitting any Slurm job (sbatch/srun), when diagnosing why a job failed to schedule, or when choosing GPU types, partitions, storage paths, or resource limits on the Duke CS compute cluster. Do NOT trigger for non-Slurm tasks or clusters other than Duke CS.
Operate Cities: Skylines 1 through the Skylines Agent Bridge mod and localhost API. Use when Codex needs to build, inspect, repair, resume, save, or continue a CS1 city using focused API calls rather than screenshot recognition, including road connectivity, service infrastructure, zoning, facilities, problem icons…
★not rated 6 4mo agoA76 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: