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.
Understand images — read screenshot text (OCR), interpret charts and diagrams, and describe photos, UI mockups, or document scans using a vision model. Use whenever the user shares or points to an image, screenshot, photo, chart, diagram, or asks "what's in this picture", "read the text in this image", or to analyze…
Call CoTerm, the AI-native terminal session runtime, over its local HTTP API to run commands in real, shared terminal sessions. CoTerm owns long-lived PTY sessions (local PowerShell/cmd/bash, SSH, WSL, Docker). Use this skill to execute shell commands, read output, wait for command completion, inspect session state…
Read, inspect, modify, validate, or repair Canvas LMS .imscc / IMS Common Cartridge course export files. Use whenever the user has a .imscc (or Common Cartridge .zip) file and wants to see what's inside, add/edit/remove pages, assignments, quizzes, or modules, fix a cartridge that fails to import into Canvas, or do…
Use AutoDL safely through its official developer APIs and documentation. Trigger for AutoDL balance, Container Instance Pro, elastic deployment, images, GPU stock, NFS, duration packages, WeChat notifications, container metrics, billing, storage, data retention, SSH/JupyterLab/VSCode, CUDA environments…
Use for a GitHub pull request review run to inspect the exact head revision, changed files, and checks, then publish one evidence-backed managed review comment without approving or modifying the pull request.
A guide for connecting an MCP client to a Cocos Creator project, a game project made with the Cocos editor. It covers editor selection, scenes, assets, prefabs, animations, previews, and project extensions.
Delegate well-bounded coding tasks, resilient current web/X research, read-only investigations, code reviews, adversarial critiques, independent second opinions, approved Grok 4.5 image/video generation, and xAI TTS from Codex or Claude Code through the local Grok Build installation. Use when the user names Grok or…
Operate an already configured burp-mcp server for authorized web application security testing, penetration testing, vulnerability assessment, and Burp Suite automation: inspect Proxy HTTP/WebSocket history, scope, and site map; craft and replay requests in Repeater; run bounded parallel fuzzing, race condition jobs…
Codebase search and context retrieval for any programming language. Hybrid semantic/lexical search with neural reranking. Use for code lookup, finding implementations, understanding codebases, Q&A grounded in source code, and persistent memory across sessions.
Test and operate the Resolume MCP server (resolume-mcp-server) end-to-end against a live Resolume Arena. Use when verifying tool behavior, running smoke tests, doing safe live VJ demos, or validating new tools added to the project. Includes white-out prevention rules, state restoration patterns, and agent invocation…
Stepwise scaffolding, brainstorming, and draft-generation for literary novels using interactive interviews. TRIGGERS - Use this skill when user says: "create a novel project" / "start a new novel" "help me brainstorm my novel" / "plan my story" "/novel-architect [language] novel named [name] [core idea]" "set up novel…
Give your agent eyes on the web — screenshot any URL as an image file, or extract page content as markdown/text/HTML. Supports device emulation (iPhone, iPad, Pixel, MacBook), dark mode, full-page scroll, ad blocking. Uses exec tool with curl (NEVER the browser tool). $SNAPRENDERAPIKEY is pre-set. See instructions…
Deprecated: this skill has been deprecated. Use this when working with InStreet forum or Playground flows. It restores account state from /.instreet, can auto-register when no local account exists, and routes all InStreet API requests through the bundled Python client. It has first-class commands for forum, groups…
Create, localize, validate, and render App Store or Google Play screenshot sets with the local Truepane MCP server. Use when an agent should produce or update store screenshots from local captures; do not use for direct store publishing.
A design skill for planning how websites, dashboards, mobile screens, and agent interfaces look and move, including cinematic pages with layered motion.
A skill and command-line workflow for collecting academic literature from CNKI, Elsevier, and international open-access sources. It provides commands for checking access, preparing searches, listing results, and downloading papers.
Use when building or restyling a website that should look like ordinary, long-running commercial web rather than a freshly art-directed product — B2B and professional services, online shops and catalogues, news and publishing, corporate and institutional sites, directories and portals. Covers the plain 2012–2020…
Rewrite a rough, vague prompt into a precise, context-enriched prompt. Explores the codebase read-only and weaves real file paths and symbols into the rewritten prompt — never implements the task itself. Use when the user asks to optimize, enrich, or improve a prompt before running it.
Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
Audit a repository's AI-agent readiness with the agentlint CLI and fix the findings. Use when the user asks to score, audit, or improve how well a repo works with AI coding agents (AGENTS.md, build/test docs, conventions, guardrails), or mentions agentlint.
★not rated 3 3d agoA60 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: