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.
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
How to run domain-decomposed (multi-GPU) MLIP simulations with DomainParallel — choose between the halo and graph-partition strategies, author a distributionspec so a bring-your-own model runs under domain decomposition, and write a custom dynamics integrator that stays correct across ranks.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Authoritative guide for implementing stunning, accessible, performant UI. Synthesizes design engineering philosophy, accessibility standards, animation principles, spatial design, typography, color systems, and component craft into a single actionable reference. Complements the design-system skill (which covers…
A skill for generating the detailed contents of one document from a planned documentation structure and the user's goals. It can include navigation, code examples, and technical diagrams.
A procedure for turning a trading strategy or research report into a QMT daily factor backtest script. QMT is a Chinese trading-platform environment, and a backtest simulates how a strategy would have traded using historical data.
Orchestrate the full planning lifecycle — from input assessment through architecture, plan writing, review cycles with convergence, and sign-off. Designed for concierge/scheduler agents coordinating multi-agent planning work.
Use when the user invokes /learn or asks to remember, save, or capture a pattern, decision, gotcha, procedure, or feature dossier from this session for later re-use ("please remember", "what did we learn?"). Captures durable project knowledge as a canonical user-level record. Do NOT trigger for simple personal…
A board-based way to explain ideas through written Markdown, a simple text-formatting language, with the writing appearing progressively like a live lecture.
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses the AGENTS.md paper architect/reviewer role with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches…
A tool for creating new slide decks or editing existing PowerPoint presentations while keeping unrelated content unchanged. It produces offline HTML slides that can be edited in a browser and exported to PPTX or PDF.
A website diagnosis that crawls one public site, reviews up to ten representative page types, and produces a visual HTML report about its readiness for generative search engines.
Turn a script into MiniMax H3 shot lists with working emotional performance — beat tables, shot counts, expression direction, and the acting techniques that actually render. Use when breaking a script or scene into H3 shots, writing beat timings, directing a character's face or emotion, fixing flat/wooden performance…
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
A complete workflow guide for solving China Undergraduate Mathematical Contest in Modeling problems, from checking the computer environment through submitting the final paper.
Translate a single Epic into clear, actionable User Stories with explicit acceptance criteria. Activate when an Epic is defined and work needs to be prepared for Delivery execution.
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.
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: