Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Given a grouchygiraffe media file path, find the associated YAML, identify the recipe from the thumbnail, locate the author's home base, and return the recipe URL. Use when the user provides a path to a grouchygiraffe .mp4 or .jpg file and wants to know what recipe it is and where to find it.
Discover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".
Use when the user's task involves HiUI (@hi-ui/*) — writing HiUI components, debugging HiUI issues, querying HiUI props/docs, migrating from HiUI V4 to V5, or setting up React 19 compatibility with @hi-ui/patch-for-react. Triggers on imports from '@hi-ui/*', hi-ui/hiui mentions, or explicit HiUI questions.
IHttpClientFactory patterns with Polly for retries, circuit breakers, timeouts, and resilient HTTP communication. Includes best practices for HTTP client configuration and error handling. Use when configuring resilient HTTP clients in ASP.NET Core, implementing retry policies with Polly, or setting up circuit breakers for external service calls.
Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving. Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces. This skill helps discover and use resources via `datasets`, `transformers`, the HF Inference API, `gradio_client`, and methodology citations.
Provides the HuggingFace Tokenizers library (Rust core with Python and Node.js bindings) for training and using BPE, WordPiece, and Unigram tokenizers. Covers the pipeline of normalizers, pre-tokenizers, models, post-processors and decoders, padding and truncation, batch encoding, alignment tracking, and conversion to transformers PreTrainedTokenizerFast. Use when training a custom tokenizer or vocabulary on a new corpus, tokenizing large text corpora quickly, mapping tokens back to character offsets for NER or question answering, or configuring normalization and special tokens. Use when wrapping a custom tokenizer for transformers. For SentencePiece models or tiktoken, use those tools instead; for loading a pretrained tokenizer only, AutoTokenizer is enough.
Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic structure, and formatting artifacts. Also clean suspicious invisible Unicode and copy-paste residue conservatively, without treating them as proof of authorship. Use whenever a user wants to humanize, de-AI, de-slop, or de-robotify text; fix prose that sounds corporate, generic, like ChatGPT, or otherwise off; match a draft to a writer or named author; edit for authentic voice and rhythm; or clean zero-width characters, exotic spaces, bidi controls, and similar hidden text residue.
Report delta-adjusted notional exposure across all IBKR accounts. Calculates option deltas using Black-Scholes and reports long/short exposure by account and underlying. Use when user asks about delta exposure, portfolio risk, or directional exposure.
Deploys and configures Wazuh SIEM/XDR for endpoint detection, covering agent authentication and management, custom decoder and rule XML creation, alert querying via the Wazuh REST API, rule testing with wazuh-logtest, and automated active-response actions. Use when setting up endpoint detection and response, writing or testing custom Wazuh rules, or querying and triaging Wazuh alerts.
Write user stories that account for disability and diverse abilities from the start. Use when writing user stories, acceptance criteria, jobs to be done, or requirements. Triggers on: user story, user stories, acceptance criteria, jobs to be done, JTBD, requirements, as a user I want, definition of done, story writing.
Use when choosing, proposing, reviewing, or declaring a new dependency or development tool, including temporary package runner acquisitions. Also use when declaring an existing dependency for an additional workspace consumer or changing a dependency’s or tool’s prescribed features, source, or version. Don’t use merely to reuse an existing project dependency without adding or changing a declaration, install or restore already prescribed dependencies, incorporate existing dependency declarations through authorized history integration, or conduct a general dependency inventory or security audit without a selection decision.
This skill MUST be used when a bug's root cause is unknown and requires investigation, or when the user explicitly requests investigate or root-cause analysis. SHOULD be used for unexplained failures, regressions, or intermittent behavior: 根因調查, 為什麼會這樣, 壞掉了, failing, broken, flaky. MUST NOT treat an apparently obvious cause as confirmed without evidence. When evidence already establishes the cause, proceed to targeted verification and repair without restarting the investigation.
Fix JavaScript package security vulnerabilities or upgrade outdated npm/yarn/pnpm/bun dependencies. Use when the user wants to patch CVEs, resolve npm audit findings, bump package versions, modernize node_modules, or update specific packages across a JS project or monorepo. Handles any project with package.json files. Also triggers for "/js-deps" with or without specific package names or glob patterns. Not for non-JS ecosystems, adding brand-new packages, creating package.json from scratch, switching package managers, or debugging runtime errors.
Audit one or more existing Kestra flows and add production-hardening controls — retries, timeouts, concurrency limits, error/finally/afterExecution handlers, SLAs, checks, and idempotency guards. Produces a severity-ranked findings report, then applies confirmed edits. Use when users ask to harden, audit, review, or make a flow more production-ready, resilient, or idempotent — not for authoring new flows (use kestra-flow).
Kuaishou comment analysis tool. Enter a work link to fetch first-level comment data, with paged browsing and comment sentiment analysis (positive/negative/demand/competitor), generating a polished HTML report. Use when the user needs to view Kuaishou work comments, analyze comment sentiment, or understand user feedback. Triggers: 快手评论, 作品评论, 评论查询, 评论分析, 评论舆情, 看评论.
Kuaishou short-video operations growth assistant, suitable for content creators, operators, brands, and e-commerce when the user provides a Kuaishou content link; helps generate sentiment, personas and discussion focal points, public-opinion and conversion leads, and optimization suggestions based on the input material.
Turn a rough idea for a language into a complete, implementable specification — a DSL, query, config/data, template, or protocol language — by interviewing the author dimension by dimension until another developer could build a conforming implementation from the document alone. It grills for the decisions authors skip: lexical rules (whitespace, case, comments, literals), grammar with precedence and ambiguity resolution, a semantic/type model, validation rules with counter-examples, execution algorithms and the error model, the output/serialization format, and RFC 2119 conformance. The completeness bar and formal notation (lexical vs syntactic grammar, function-style algorithms) are distilled from the GraphQL specification. Trigger on "spec out my language", "design a DSL / query language", "write a language or grammar spec", "formalize this syntax", or when someone has a language idea that needs to become an implementable spec — even if they only say "spec" or "grammar".
Build production-grade Laravel REST APIs using opinionated architecture patterns with Laravel best practices. Use when building, scaffolding, or reviewing Laravel APIs, with specifications for stateless design, versioned endpoints, invokable controllers, Form Request DTOs, Action classes, JWT authentication, and PSR-12 code quality standards. Triggers on “build a Laravel API”, “create Laravel endpoints”, “add API authentication”, “review Laravel API code”, “refactor Laravel API”, or “improve Laravel code quality”.
Lavarage Protocol — leveraged trading on Solana for any SPL token. Open long/short positions on crypto, memecoins, RWAs (stocks like OPENAI, SPACEX), commodities (gold), and hundreds of other tokens with up to 12x leverage. Permissionless markets — if a token has a liquidity pool, it can be traded with leverage.
Review and guide UI implementations using the 21 Laws of UX. Identifies usability issues in HTML, CSS, and JavaScript by applying established cognitive, visual, and behavioral principles. Use when reviewing UI code, building new interfaces, or auditing user experience.
Lightweight headless browser automation via Lightpanda and agent-browser CLI: 9x lower memory, 11x faster than Chromium, for scraping and DOM interaction without rendering. Triggers on: "lightpanda", "lightweight browser", "fast headless browser", "headless scraping", "low memory browser", "browser without rendering".
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
Insert AI illustrations into documents in place. After reading the document, plan insertion points globally, generate all images in parallel, and insert them back into the original text asynchronously. Supports cover images, custom aspect ratios, and three styles. Use when: the user asks to generate illustrations or images for a document/article/note. Also trigger when the user mentions: 配图, 插图, illustration, generate images, document images, 为文章加图.
BLOCKING REQUIREMENT. Invoke before writing or editing any PR title/body, issue body, GitHub Discussion post/comment/answer, PR review comment, README/docs prose, inline code comment, design doc/RFC/retrospective, or requirement/acceptance-criterion, including requests to edit, copy edit, revise, rewrite, reword, redo, polish, or refactor any of those artifacts, and before calling create_pull_request, update_pull_request, add_pr_review_comment, edit_pr_review_comment, reply_to_comment, reply_to_review_thread, or reply_and_resolve_review_thread.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.