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.
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate…
Generate complete, valid A2UI JSON for FlowLike frontends. Use when asked to create, design, or build an interface, dashboard, form, page, responsive layout, reusable widget, chart, calendar, Gantt view, media experience, game UI, map, or other visual UI as A2UI JSON. Covers all 71 runtime component types, BoundValue…
Run, monitor, inspect, debug, and author HomeRail DAG workflows through the CLI or Manager Tools, including supervised multi-Actor runs with stable live Surfaces and later per-Actor follow-ups. Use when: (1) listing templates, (2) starting a DAG run, (3) supervising or watching a run, (4) inspecting chats, handoffs…
Design a UI component spec to the house quality bar — anatomy, variants, sizes, the 8 states, token mapping, and accessibility. Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…
Integrate digital health data sources (Apple Health, Fitbit, Oura Ring) and connect to WellAlly.tech knowledge base. Import external health device data, standardize to local format, and recommend relevant WellAlly.tech knowledge base articles based on health data. Support generic CSV/JSON import, provide intelligent…
A development workflow and coding-standard skill for Python, PyTorch, deep-learning code, shell scripts, and configuration files. It requires understanding the project, proposing a plan for approval, writing tests, simplifying code, and reviewing the result.
Search and answer questions from the local AI-Compass AI knowledge base. Use when the user asks about AI models, tools, agents, RAG, multimodal systems, evaluation, learning paths, project resources, or recent AI developments covered by this repository; distinguish weekly updates from long-term topic knowledge…
A set of rules for detecting signals that may suggest a browser user is in China. It scans browser information locally and also reuses scoring functions in a server endpoint called /api/check.
★not rated 938▲
+14 3d agoASkillSpector: pass69 tokens
originalMIT
Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, scientific workflows, or other expensive black-box evaluations where reading the project can improve trial selection.
How to write and maintain DESIGN.md as the visual specification layer for Cavekit projects. Nine-section format, design tokens, accessibility, integration with kits/plans. Use when defining or revising visual identity, importing a third-party design system, or auditing UI code against design tokens.
A presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then…
Build a premium PRESENTED slide deck — classic one-slide-at-a-time slides you advance with a clicker — as a Vite + React app. It keeps the Slidev navigation UI (floating glass dock + thumbnail rail + click-builds + presenter) but slides are RESPONSIVE React (reflow to any screen, no fixed canvas) and fully…
Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind judge per question grading two answers X/Y…
Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion research, or any browser-only work. Load chrome:control-chrome first, then computer-use:computer-use for fallback. Save verified…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
ET Excel MCP workflow for reading, writing, styling, transforming, and inspecting xlsx data. Use when operating Excel cells, ranges, sheets, formulas, charts, merges, batch data import/export, or editing Luban source spreadsheets before export.
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: