Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Control the hinge (fold) angle of a foldable iPhone Simulator such as iPhone Duo. Use when you need to fold, unfold, half-open, or animate the fold of a running simulator, read its current hinge angle, or test how an app reacts to hinge and display changes.
Digital pathology image processing toolkit for whole slide images (WSI). Use when working with histopathology slides, processing H&E- or IHC-stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.
Entry skill for HarmonyOS multi-device adaptation. Use when the task broadly concerns HarmonyOS multi-device adaptation, or when the correct scenario is still unclear. This skill classifies the request by phase and scenario type, then routes to one or more scenario files for screen and window size, fold state, avoid areas, interaction methods, natural orientation, or hardware access.
Generate attention-grabbing hooks from 5 investor archetype perspectives. Use when writing headlines, social media openers, email subject lines, or ad copy and need multiple angle options. Each archetype surfaces different audience motivations to find what resonates.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
When the user wants to solve hub location problems, design hub-and-spoke networks, optimize hub placement for logistics networks. Also use when the user mentions "hub location," "hub-and-spoke," "p-hub median," "hub covering," "single allocation hub," "multiple allocation hub," "airline hub network," "postal hub network," or "consolidation center location." For general facility location, see facility-location-problem. For distribution centers, see distribution-center-network.
Read, create, update, search, and associate HubSpot CRM records — contacts, companies, deals, tickets, and custom objects. Use this whenever the user wants to look up a contact, create a deal, update a company, search the CRM, link two records, or asks "what's in HubSpot" — even if they don't say "API". Also use it for any URL under app.hubspot.com or a mention of a HubSpot object/record ID. Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Scores and ranks outbound hypotheses before launch and turns them into a launch queue—the pre-launch evaluation method from Victor Shulga's guide on testing cold-outreach hypotheses: a stop-filter gate, canonical hypothesis format with the number N, channel-capacity check, six-factor weighted score on the 0/1/3/5 scale, priority queue where the top three go into work, and a journal skeleton for the facts. Trigger when the user says "оціни гіпотези", "оцінка гіпотез", "пріоритизуй гіпотези", "яку гіпотезу запускати першою", "черга запуску", "відбери 3 гіпотези", "score these hypotheses", "prioritize hypotheses", "which hypothesis do we run first", or provides a list of campaign ideas or a hypothesis matrix and asks what goes into work. Also use to rescore a hypothesis matrix before launch, or audit a hypothesis list the team wrote itself. NOT for generating hypotheses from scratch (use hypo-generator), NOT for reading results after a test has already run
Define the ICP, size and tier an ABM target-account list, and map the buying committee — the strategy layer before list-building and enrichment. Use when defining an Ideal Customer Profile and scoring criteria, deciding how many accounts to target for a revenue goal, tiering accounts (A/B/C/D), mapping personas/buying committee (champion, economic buyer, end user, technical evaluator), or planning persona-based messaging. Triggers on "ICP", "ideal customer profile", "who to target", "scoring criteria", "ABM accounts", "how many accounts", "account tiering", "buying committee", "persona mapping", "champion", "economic buyer", "revenue reverse-engineering". Do NOT use for actually sourcing companies/contacts (see apollo-search / coldiq-search-enrich), scoring math on an export (see tam-scoring), or writing copy (see crawford-method / cold-email-copy).
Identifies the local user's GitHub account and git identity before performing code reviews. Load this skill at the start of any PR review, code review, or commit log analysis so findings can be framed relative to the user's own prior comments, commits, and approval status.
Get animated video clips ready to post, without touching a single slider. Upload your still images (JPG, PNG, WEBP, HEIC, up to 200MB), say something like "turn these photos into a 15-second video with smooth transitions", and download 1080p MP4 when it's done. Built for social media creators who move fast and want to make videos from photos without editing software.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a smooth 5-second video clip — and get animated video clips back in 30-60 seconds. Upload JPG, PNG, WEBP, HEIC files up to 200MB, and the AI handles AI video creation automatically. Ideal for social media creators who want to bring static images to life without manual animation skills.
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale
Find deepening opportunities in a codebase, informed by whatever domain language and architectural decisions are already documented in the repo. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Kazuo Inamori's management philosophy and life wisdom. Based on in-depth research of 30+ sources including A Compass to Fulfillment, A Passion for Success, Amoeba Management, The Heart, the Six Endeavors, the Kyocera philosophy manual, the KDDI founding history, the JAL reconstruction account, and Seiwa Juku lecture records, it distills 5 core thought models, 7 life heuristics, and a complete expression DNA. Purpose: as a thinking advisor, analyze problems such as business decisions, life choices, team management, and self-cultivation from Kazuo Inamori's perspective. Use when the user mentions "Inamori's perspective", "what would Kazuo Inamori think", "the Inamori model", or "inamori perspective". Also applies to: business management, startup decisions, balancing altruism and self-interest, the equation of life, Amoeba Management, and team motivation. Triggered even when the user merely says "how should I run this business", "altruism", "respect heaven and love people", "amoeba", or "equation of life". Do not trigger when the user is only asking general questions such as "is this decision sound" or "help me think it through" — activate only when core Inamori methodologies such as management philosophy, altruism, Amoeba Management, or respect heaven and love people are involved.
Make a single KBAC authorization decision via the IndyKite AuthZEN REST API (`POST /access/v1/evaluation`) - returns a boolean `decision` for one (subject, action, resource) triple, optionally with per-request `context.input_params`. Use for a single yes/no question - "can ada PROVISION gpu-node-7?", "is this user allowed to delete this document?", "gate this operation on a live check", or debugging why one decision is false. Not for many checks at once (use indykite-authzen-evaluations), not for enumerating which actions/resources/subjects are allowed (use indykite-authzen-search-action / -search-resource / -search-subject), and not for authoring the policy behind the decision (use indykite-authzen-kbac-policies). For the same decision over MCP/JSON-RPC see indykite-mcp-server (`authzen_evaluate`).
Run many KBAC authorization decisions in one call via the IndyKite AuthZEN REST API (`POST /access/v1/evaluations`), with top-level subject/action/resource/context as defaults overridden per entry; returns one `decision` per entry, in order. Use when checking a known, fixed set of checks at once - one subject against many resources, one action across many subjects, or any mix of triples - e.g. "of these servers, which can grace provision?", "for each of these users, can they deploy gpu-node-7?". For a single check use indykite-authzen-evaluation; to enumerate ALL allowed actions/resources/subjects (open-ended, not a fixed list) use indykite-authzen-search-action / -search-resource / -search-subject; to author the policy use indykite-authzen-kbac-policies.
List the actions a subject is allowed to perform on a resource via the IndyKite AuthZEN REST API (`POST /access/v1/search/action`) - returns the granted action names for one pinned (subject, resource) pair. Use to enumerate permitted operations - "what can linus do with gpu-node-7?", "which actions does this user have on this item?" (e.g. to render only allowed UI controls). Not for a specific-action yes/no ("can linus DEPLOY gpu-node-7?" -> indykite-authzen-evaluation); to enumerate the other axes use indykite-authzen-search-resource (which resources) or indykite-authzen-search-subject (which subjects); to author the policy use indykite-authzen-kbac-policies.
List the resources a subject is allowed to perform a given action on via the IndyKite AuthZEN REST API (`POST /access/v1/search/resource`) - given a subject and an action, returns the matching resource instances of a type. Use to enumerate permitted resources - "which servers can linus provision?", "list the documents this user can read" (access-filtered feeds). Returns `{type,id}` references, not a yes/no decision and not the resource data itself (for graph data use indykite-ciq-read). For a single-resource yes/no use indykite-authzen-evaluation; to enumerate the other axes use indykite-authzen-search-action (which actions) or indykite-authzen-search-subject (which subjects); to author the policy use indykite-authzen-kbac-policies.
List the subjects allowed to perform a given action on a resource via the IndyKite AuthZEN REST API (`POST /access/v1/search/subject`) - given a resource and an action, returns the matching subject instances of a type. Use to enumerate who has access - "who can provision gpu-node-7?", "list the people allowed to approve this document" (audit / reviewer views). Not for a specific-subject yes/no ("can grace provision gpu-node-7?" -> indykite-authzen-evaluation); to enumerate the other axes use indykite-authzen-search-action (which actions) or indykite-authzen-search-resource (which resources); to author the policy use indykite-authzen-kbac-policies.
Initialize, update or overwrite the Claude Code status line configuration files (.claude/settings.json and .claude/statusline.sh). Use to quickly set up status line display in any project, showing directory, Git branch, model, version and context window usage.
Load and manage a personal agent rulebook. Use when asked to reload agent rules at session start or after compaction, set up agent rules, fine-tune rule loading, check rulebook status or diagnose unrelated rules being loaded, link dotfiles, configure a host startup pointer to the rulebook, or update this skill or its rulebook. Not for project `.agent-memory/` or repository instruction-file pointers.
Set up PostHog in a user's GitHub repository from a chat, without a terminal. Wizard, PostHog's setup agent, runs in the cloud, adds the SDK and first events, and opens a pull request. Use only when you can't read or edit the user's code, which is common in web chat apps such as ChatGPT on the web or Claude on the web. Typical requests: install, add, or set up PostHog in their app or repository, or open a pull request that adds PostHog. When you're working in the user's repository, use installing-posthog-in-a-codebase instead. Covers connecting GitHub, picking the repository, starting the run, polling it, and sharing the pull request.
Create and run cold email campaigns in Instantly through the ColdIQ marketplace — campaigns, leads, sequences, analytics, and accounts. Use when creating a campaign, loading/adding leads, setting ColdIQ default campaign settings, pulling reply/open/bounce analytics, activating or pausing a campaign, or formatting email HTML for Instantly. Triggers on "Instantly campaign", "load leads", "create campaign", "campaign analytics", "activate campaign", "add leads to Instantly", "reply rate", "campaign settings". Do NOT use for writing the copy itself (see cold-email-copy / crawford-method), email-finding/enrichment (see contact-enrichment), Lemlist or EmailBison sending (see those skills).
Guide an ISV developer or merchant through integrating Payroc's Hosted Fields from credential setup to first successful UAT test transaction. Use this skill whenever someone asks about integrating Payroc Hosted Fields, embedding card input fields or a payment form in their own checkout page, using the Payroc JS payment library, generating a Payroc session token, tokenizing payment details with Payroc, or getting Payroc embedded payments working in their application — even if they don't explicitly mention "integration" or ask for step-by-step guidance. Also use it when a developer has HPP working and asks about the embedded alternative.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Generate every iOS and Android app icon and splash screen size from a single source PNG using @capacitor/assets. Trigger when adding app icons, generating splash screens, replacing the default Capacitor icon, or shipping any Ionic Capacitor app to a store (icons are non-optional).
Framework-agnostic Capacitor concerns shared by Ionic Angular, React, and Vue apps — AdMob, RevenueCat, push notifications, @capacitor/preferences storage, theme switching, localization content, and App/Play store submission notes. Referenced by ionic-angular, ionic-react, and ionic-vue.
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.