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.
Conventions every gplay command shares: credential and package resolution, output formats, exit codes, --dry-run/--confirm/GPLAYREADONLY gates, the Edit lifecycle. Use when running any gplay command, wiring gplay into CI, branching on an exit code, or introspecting the Android Publisher API offline with gplay schema.
Deep knowledge of LinkedIn, Facebook, and Twitter/X algorithms and engagement best practices. Ensures every generated post is optimized for maximum reach and engagement on each platform.
Audit and normalize formatting in university thesis and dissertation DOCX files. Use when a user asks to check, standardize, repair, or adjust graduation thesis formatting; compare a thesis against university layout requirements; create a formatted DOCX copy; or produce a thesis-format review checklist. Support Word…
A file-based handoff process for two agents named Sol and Grok to implement and review coding tasks across separate conversations. It uses shared project files to record the next actor, task details, implementation notes, and review results.
A planning guide for writing rules about generative AI in course syllabi, the documents that explain how a class works. It offers four policy levels, from unrestricted use to a complete ban, plus choices for different kinds of courses.
Skill "clawcraft" from qtzx06/clawcraft, covering clawcraft arena skill, connection, the game, getting started and 1. register your team (if not already registered).
Produces a comprehensive weekly cross-asset financial report (Word document) covering commodities, equity indices, China/US bond yields, and FX. Fetches live data from yfinance and akshare; 5 matplotlib charts embedded; 8-item macro news section from Tavily search.
Must be used whenever the user asks which actions are applicable, available, legal, or possible in a PDDL state — regardless of how small or "obvious" the problem looks. Triggers: "what actions can I take", "applicable actions", "available actions", "legal moves", "what can be done next", "possible actions from this…
Start a project-wiki — an agent-maintained knowledge base that turns scattered material (documents, meeting notes, web pages, research) into a durable, cross-linked wiki the agent builds, keeps current, and can answer questions from. This skill creates a new project-wiki in its own folder next to your current project…
A guide for planning and generating e-commerce product images, such as main product photos, detail images, selling-point graphics, and coordinated image sets. It also covers prompts and NeoSpark image-generation workflows.
Suggests GitHub Universe talk submissions based on your GitHub activity. Pulls your repos, PRs, issues, and contributions, identifies themes in your work, and generates complete CFS-ready proposals with titles, abstracts, and session details that match the Universe submission form.
Elite technical documentation architect for agent-executable implementation guides. Use when creating technical handoff documents, Claude Code guides, development playbooks, implementation plans, or documentation guiding AI agents through multi-phase builds. Triggers on "create technical guide", "implementation…
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Turn the current chat history and optional pasted agent transcripts into a reusable skill package. Use when a conversation already contains a repeatable workflow that should be drafted in the current project .temp/ folder and optionally published into a skill-marketplace-template-style marketplace. Do not use it for…
★not rated 5 1mo agoA86 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: