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.
Use when planning, drafting, continuing, revising, or reviewing Chinese long-form narrative projects that need persistent harness control for characters, abilities, inventory, quests, world rules, timelines, outlines, continuity, or author directives.
Locate and read exact files across generated or versioned artifact roots, with stale-input detection and bounded output. Use when guessed paths, partial overlays, or oversized evidence repeatedly interrupt work; simple known-file reads can use ordinary tools.
Use when a task needs connected MCP servers, external services, dynamic MCP tool discovery, schema inspection, sandboxed MCP execution, or routing across many possible MCP tools.
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
Work a remote RAD Studio (Delphi IDE) machine through the Delphi IDE Remote MCP Server (delphi / vault tools). Load when connected to an MCP server exposing delphiworkspace, delphibuild, delphiedit and friends - it teaches the path model, the safe-editing contract, the build/deploy chains (Windows, Linux via PAServer…
Build or adapt a TypeScript LangGraph.js project with skein-js for a server, desktop app, CLI, or daemon. Use for scaffolding, serving an existing langgraph.json, embedding graphs with memory, SQLite, or Postgres, or connecting Agent Protocol clients.
Use when building or changing Blade views that use WireKit components ( ) in a Laravel Livewire application: forms, layout, navigation, overlays, tables, charts and theming. Covers looking up props and their values, the intent and surface conventions, design tokens, and the WireKit MCP tools.
Write, edit, or debug Beagle source and work in /code/beagle. Query the compiler for current profiles and syntax; use code-as-facts for relational analysis.
Detects technosignatures in telescope data and classifies each candidate signal with a confidence percentage. Rejects signals explained by known natural phenomena.
Trace a transaction or system flow end-to-end from an entry point (e.g. a BPMN/Camunda/Operaton process, HTTP endpoint, message listener) and document it as an evidence-backed markdown doc with one Mermaid swimlane flowchart, numbered time-ordered steps, thread/transaction boundaries, and findings on race conditions…
Drive Google NotebookLM from the agent through the notebooklm-mcp server — create and manage notebooks, add sources (URLs, text, local files, Google Drive), ask questions answered only from those sources, run web/Drive research, and generate Studio content (audio overviews, video overviews, slide decks, reports…
Apply Effect v4 conventions for services, layers, tagged errors, boundary runners, resources, retries, deadlines, HTTP, and tests. Use when writing or reviewing TypeScript that imports effect, adds a service or error class, chooses where to run a program, bounds external I/O, or tests Effect code.
Create, adapt, and review GLSL effects for Umbriel, including community shader presets, activation examples, and validation. Use for Umbriel animation, border, window, screen, and cursor shaders.
Look up Java/Kotlin classes, method signatures, source code, implementations, callers and dependencies inside the local Maven (/.m2) and Gradle caches with the maven-indexer-cli command. Use when code imports a class from a library you cannot see in the workspace (internal company packages, less-known open-source…
Mastermind monitor — long-running executor that watches Linear, GitHub, Monotask boards and folders for new tasks, claims and runs them with the right agent, and reports progress.
A reference library of 124 Jev examples from social posts and open-source projects. It includes summaries, links, screenshots for posts, ratings, and tags for different use cases.
A web-page troubleshooting guide for finding why an HTML page, report, or browser game looks or behaves incorrectly. It covers issues such as blank areas, misplaced elements, faint content, missing movement, and ignored clicks or keys.
This skill should be used when the user asks to "create a diagram", "draw a flowchart", "make a swimlane diagram", "create WBS", "generate RACI matrix", "build network diagram", "create org chart", or mentions draw.io, diagrams.net, BPMN, UML, Gantt, PERT, or project management diagrams. Integrates with…
Review and structure auto insurance bodily injury claims, including intake triage, evidence completeness, injury causation, treatment chronology, medical necessity, wage-loss support, negotiation risks, and human escalation. Use when analyzing bodily injury claim files, designing claims-agent workflows, drafting…
A Markdown editing tool that finds common unnecessary words, repeated headings, and padded explanations, then rewrites the marked sections with a language model. Markdown is a plain-text format commonly used for documentation.
Browser automation guidance and patterns. Trigger this skill BEFORE starting any browser interaction (navigating pages, logging in, scraping, filling forms, testing UI) to learn the correct workflow and avoid common pitfalls. Also trigger when browser MCP tools misbehave: element not found, click does nothing, page…
★not rated 22
changed 8d agoA117 tokens
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: