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.
Write publication-ready papers for top security, privacy, and cryptography venues (IEEE S&P, ACM CCS, USENIX Security, NDSS, PETS, CRYPTO, Eurocrypt, TCC). Use when drafting papers from research repos in these areas, structuring threat models and security claims, writing game-based or simulation-based proofs, or…
Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.
A local reference skill for LF/LFM2, also called the Mir200 game server engine. It uses manuals, example server files, and known scripting patterns to answer questions about the engine and its scripts.
Scaffold a Spec Kit (spec-driven development) project for GitHub Copilot by running specify init --integration copilot --integration-options="--skills". USE FOR: starting a new spec-kit project, bootstrapping spec-driven development in an existing repo, installing spec-kit templates/scripts/commands for Copilot. DO…
Codex ecommerce short-drama skill v0.8.30. Use when the user wants to create product-selling short dramas, generate product-proof scripts, subject libraries, character dossier boards, filed role assets, Seedance2 production references, storyboard grids, first frames, salpx gpt-image-2 images, MiniMax H3 video…
Create, redesign, critique, or plan audience-ready presentations and PowerPoint decks from a short prompt or source material. Use for portfolios, work/result reviews, proposals, sales decks, investor pitches, strategy or decision decks, research and technical talks, lessons, keynotes, reports, product launches, and…
Create complete Chinese Xiaohongshu educational carousel images from a topic, source document, notes, or an existing page concept. Use when Codex must plan every definition and meaning without compressing knowledge points, maintain a recurring character and visual system, directly render fully typeset 3:4 final pages…
An AI writing system for creating serialized animated-drama stories from a genre and character setup. It produces scripts, storyboards, voice-over text, and prompts for AI image or video tools.
A source-grounded adaptive tutor that tracks proof of mastery rather than content completion. Use it to learn a topic systematically, build a course from PDFs, webpages, transcripts or notes, practice retrieval and transfer, resume a long-running course, or verify whether the learner can recall and apply what they…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill for AI agents testing a game in the Unity Editor by simulating input — clicks, drags, swipes, key presses, and touches — through the unity-open-mcp MCP server.
Build a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents — builders never review their own work. Quality decisions are grounded in project context (identity, audience, goals) and established visual/motion design principles. Measurable criteria (text size…
Use when the user explicitly requests cccc/4C, asks to launch local Claude Code or Codex as a peer, or confirms a suggested local peer handoff for bounded implementation or a read-only second opinion. Do not use when the user or project rules prohibit external agents.
Coverage-aware agent workflow tool. Use PROACTIVELY before modifying files, making architecture decisions, debugging, or reviewing code. Reports which symbols Claude has read (Seen%) vs read in full (Full%). Use MCP tools mcpambitcoverage or mcpambitcoveragefile when available; fall back to bash.
An AI-agent skill for Xiaohongshu, also called RED, a Chinese social platform for posts, trends, and product recommendations. It supports research, original note creation, rewriting, authorized account actions, publishing, scheduling, and review after publishing.
An English-teaching guide based on Liu Xiaoyan's approach, aimed at Chinese learners preparing for CET-4, CET-6, or graduate-school English exams. CET-4 and CET-6 are China's national college English tests.
Delegate a bounded coding, research, review, debugging, or implementation task to the local Google Antigravity CLI (agy) and use its response as a second-agent result. Use when the user explicitly asks to use Antigravity as a subagent, requests a second opinion from Antigravity, or asks Codex to offload an independent…
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: