Use when the user accepts, reviews, or asks about non-trivial code — their own or AI-generated — and should understand it rather than just ship it. Triggers on "mentor", "teach me", "explain this", "quiz me", or right after generating concurrency / security / DB-query / algorithm / auth code. Runs a comprehension loop…
A test-suite generation workflow for software projects. It includes static checks, unit tests, integration tests, end-to-end tests, coverage reports, type checking, linting, security scanning, and dead-code detection.
A Chinese-language guide for finding free-to-use images, illustrations, icons, mockups, textures, and video for design work, with notes about licences and access in China.
Build a 90-day marketing + content tracker Excel file for a SaaS product or indie app, pre-filled with 180 main weekday tweets + 50 weekend bonus tweets across 9 content pillars, a Media Production Queue, Content Mix Rules, and an automated QA Check sheet. Use this whenever the user asks to create a marketing plan…
Test an Android app on a real phone or an emulator using adb. Use when the user wants to install an APK they just compiled, walk through the app's screens, check the on-screen text, reproduce a bug, capture screenshots, read crash logs, or set up an Android testing environment from scratch. Covers both a physical…
Enforces the official Rust API Guidelines (https://rust-lang.github.io/api-guidelines/) when writing, reviewing, or refactoring Rust library code. Use this skill whenever you are writing new Rust structs, enums, traits, functions, or modules that form a public API — including when designing error types, implementing…
Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini…
A writing skill for AI-facing documentation such as llms.txt, full versions of that file, FAQs, and glossaries. It structures content so AI search tools and AI agents can find and reference it.
A review process for evaluating a scientific article for publication. It applies when an uploaded PDF or DOCX article needs a peer review or publication assessment.
Build Zalo Mini Apps - lightweight React web apps running inside the Zalo super-app. Use for Zalo Mini App setup, zmp-cli/devtools, ZaUI 1.11.x components, zmp-sdk APIs, permissions, token-based phone number flow, user info, storage, local file storage, camera/media, document preview, payment/Checkout, Open APIs…
Use this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS SDKs plus equivalent raw HTTP) and decide which calls can be replaced with deterministic logic. Activates on phrases like 'audit LLM usage', 'bust LLM calls', 'bust the LLM here', 'llm-bust this', 'do I…
Run one request through several skills in parallel, isolated subagents, then merge their answers or judge the single best one. Use when the user invokes /council (or /council manage), or uses clear multi-skill-comparison language like "try this with a few different skills", "compare how different skills answer this"…
A daily work-log tool that turns a short progress update into a dated note and updates the day's task list. It can also bring unfinished tasks forward.
Build a 30-second cinematic marketing video for any website URL using the Causal AI Digital pipeline (Playwright iframe scroll tour + ElevenLabs voice off + whisper.cpp word-level synced subtitles + FFmpeg audio mux). Use when the user asks to generate a promotional/marketing video for a website, create a cinematic…
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
Run the pytest suite, report pass/fail counts and coverage, and identify untested code. Use when the user asks to run tests, check test coverage, or verify that changes didn't break anything.
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: