Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Help a person with no prior knowledge decide whether their website needs a content management system (CMS), and set it up if needed, for example Strapi in Docker on the Albatros server, accessible through a secure tunnel. Explain CMS using the image of a bulletin board. Use this skill for “CMS,” “Strapi,” “change content myself without code,” “blog,” “news,” “manage events,” “my colleague should be able to edit text,” “WordPress,” and “admin area.”
Deep, themed review of a diff: the review-diff flow and its standard lenses, plus one cheap reviewer subagent per theme, using distinctive preferences distilled from Alex North's public GitHub reviews (naming, API shape, errors, tests, coupling, and related themes). Needs the review-diff skill. Use when the user asks for a deep review, themed review, or anorth-style review.
This skill should be used when the user asks to "build electrobun app", "electrobun build", "electrobun canary", "electrobun stable", "set up code signing", "electrobun distribution", or is diagnosing electrobun build failures. Covers dev/canary/stable environments, all three platforms, toolchain prerequisites, artifact output, and CI/CD setup.
Use this skill when the user asks about the “electrobun kitchen sink,” “defineTest,” “AUTO_RUN mode,” “kitchen sink tests,” the “electrobun test runner,” navigating playground windows, or wants to add new electrobun Kitchen Sink test coverage.
This skill should be used when the user asks about cross-platform electrobun support, "electrobun Linux", "electrobun Windows", CEF requirements by platform, "electrobun platform differences", or is setting up multi-platform CI for an electrobun app.
Use this skill when the user asks about “electrobun RPC,” “defineElectrobunRPC,” “Electroview.defineRPC,” “ElectrobunRPCSchema,” bun-to-renderer communication, or renderer-to-bun communication. Activates automatically when RPC code is present.
Use this skill when the user wants to build a complete electrobun feature end to end, asks about the “electrobun SDLC,” “electrobun agent pipeline,” “8-stage electrobun pipeline,” or needs to orchestrate the researcher/architect/planner/dev-squad/QA/test/alignment/docs agents.
Use this skill when the user asks to “write electrobun tests,” “add electrobun test coverage,” “electrobun testing,” use the “defineTest” pattern, generate new electrobun test suites, or reverse-engineer electrobun component behavior from test source.
Use this skill when the user asks about the “electrobun development workflow,” “electrobun pipeline,” “electrobun lifecycle,” “where am I in the electrobun pipeline,” or needs guidance on what stage comes next in electrobun development.
Work step by step with a person who has no prior knowledge and their AI to improve a small website's usability and appearance. First review it from three perspectives (flows, access, states, and language), then fix usability, offer three clearly different directions to choose from, set fixed values for colors, typography, and spacing (tokens), and rebuild all pages with photos at mobile and desktop widths. Use this skill for “design,” “looks boring,” “looks homemade,” “make it prettier,” “colors,” “font,” “redesign,” “three options,” “looks unprofessional,” and “layout.”
Use when a Python or TypeScript app sends large tool outputs, logs, JSON, search results or long chat history to an LLM and the task is to cut input tokens, reduce token cost, fit a context window, or trim tool results without losing errors. Adds the headroom-ai compress() call; in-process, no API key, no model download.
Help the person create an honest budget for their project: Albatros subscription, domain, AI subscription, email, add-on services, and later a server of their own. Explain which costs are fixed and which are variable, how to avoid unpleasant surprises, and when moving is worthwhile. Use this skill for “what does this cost,” “costs,” “prices,” “too expensive,” “budget,” “bill,” “is it worth it,” “how much does a server cost,” and before the person adds a new paid service.
Review the diff since a fixed point along Standards and Spec axes in parallel sub-agents, reporting findings without editing the target or deciding the final verdict. Use when the user wants to review a branch, PR, or work-in-progress diff, or when review-loop or project-review requests a specialist software check
Execute one bounded, already-decided work item — code, document, configuration, research artifact, Skill, or generic project task — by inspecting relevant context, offering agent-config routing when materially useful, verifying locally, and handing the result to review-loop with the appropriate specialist reviewer
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent. Light Skills version of mattpocock/skills `research`; install one or the other, not both
Makes a minimal black-and-white line-art animation for a reel. Thin outlined steps rise one by one, a white dot hops up them, and at the top an orbit draws around it and a short second line swaps in. One quiet lowercase line of text on top. Use when the user runs /minimalistic-graphics or asks for simple black and white motion graphics, a calm self-improvement visual or line art with one moving dot.
Authoring, modifying, reviewing or building openSUSE RPM packages — .spec and .changes files, osc / OBS, and the Git packaging workflow on src.opensuse.org (Gitea). Use for a .osc/ checkout or a *.spec file; when the user mentions osc, OBS, rpmbuild, git-obs, tea, rpmlint or spec-cleaner; or asks to update, build, submit, review or fork a package, check if packages are out of date, or open a package pull request.
Check a US stock watchlist for price alerts - price above/below, % daily move, gaps, 52-week highs/lows, moving-average crosses, RSI, ATM IV, volume spikes, intraday range, stop/target hits, and upcoming earnings - with dedupe, cooldowns, NYSE market hours, optional ntfy/Slack/webhook delivery, pre/after-market, holidays and US/Eastern time. Use when the user asks "any alerts?", "check my watchlist", "alert me if AAPL drops below 200", "send alerts to ntfy", or when running a scheduled/heartbeat check
Build a personal, ranked shortlist of the PostHog Inbox reports the current user is most likely to care about right now. Combines the user's activity summary (what they work on and keep an eye on), the inbox ranking model's open, action and fix probabilities and lifts, suggested-reviewer routing, ownership, pull request state and recency, then returns the top N (25 by default) ordered from most to least relevant. Use when the user says “let's look at my inbox,” “what's in my inbox for me?,” “my top 10 inbox reports,” “what should I look at today?,” or asks to re-rank, focus, or filter that list. For browsing, filtering, drilling into, or acting on a single report, use `inbox-exploration`.
Backfill an existing product's screens into your design system's Storybook as representative page templates, rebuilt from the LOCAL design system wherever the product already uses it, with every region that isn't from the system flagged in plain sight. Use when the user says \"get this product into Storybook\", \"backfill our screens\", \"represent this product in the design system\", \"I want to see how a component change ripples across products\", \"relocate these pages into Storybook\", or names a product (a site, an app, a repo, a URL) and a Storybook. Relocation, not translation: it moves screens in and flags what isn't from the system; it never converts bespoke UI onto the system (that's vibe-killer) and never plans a migration (that's ds-adoption-plan). Also runs a refresh that reports how far the product has drifted from its Storybook copy since the last capture.
Create finished vertical short videos with Remotion and post them to TikTok, Instagram Reels, and YouTube Shorts. Turns a topic, article, URL, dataset, changelog, or list into a 1080x1920 kinetic-text short (large animated words, stat count-ups, top-N lists, launch and changelog videos, quotes), timed to reading speed and kept inside each app's safe zone, rendered locally with no paid API. Use when someone asks for a Remotion short, a Remotion video for TikTok/Reels/Shorts, kinetic typography or text animation video, a stats or data short, a top 5 list video, a product launch or changelog video, a quote video, faceless text shorts, or “make a short about X and post it.” Includes a review sheet with app overlays marked, a cover frame, and WoopSocial posting with confirmation.
Connect a Supabase project so its auth emails send through PostHog email templates via the Supabase Send Email Hook, in an order that never breaks a sign-up. Use when asked to set up, connect, test, or fix Supabase auth emails, Supabase email templates, or the Supabase Send Email Hook, or when Supabase shows “email rate limit exceeded” or an auth email error.
Coordinate root Herdr orchestrators across the local server and enabled saved machines. Ask for their current work and progress, relay messages verbatim, and route task execution through workers. Pair with the shunk031-herdr-orchestrate-workers skill for worker dispatch. Use when one session oversees multiple Herdr orchestrators; use the herdr skill for a single-pane or single-agent task.
For Japanese writing and editing, decide whether to organize from the structure, locally refine AI-like wording while preserving the original meaning and strength of claims, concisely summarize business or technical documents, or turn content into an outline, telegraphic prose, or technical slides, then choose the appropriate skill. Use as an entry point for choosing a writing approach when asked to “write something,” “make it easier to read,” or “fix the AI-like tone.” Do not use for ordinary conversation or code-only editing requests.
Help a person with no prior knowledge secure their project using the image of a house with keys, a safe, windows, and locks: never put secrets in the logbook (Git), but in .env on the server (and, if the conveyor belt needs one, in the harbor's safe); immediately regenerate accidentally published keys; use one key per purpose; leave open only the necessary doors; keep things updated. Use this skill for “security,” “password in code,” “API key,” “.env,” “Secret,” “I uploaded a key to GitHub,” “is my site secure,” “hacked,” “updates,” “firewall,” and before adding a new secret to the project.
Interview a team about its ICP, turn its account-fit rules into an explainable rubric, build and test a Clay scoring workflow, and calibrate it on five familiar accounts. Territory carving is an optional, separately reviewed proposal after scoring works. Use whenever someone asks: help us build account fit scoring, translate our ICP into scores, score our accounts for territory planning, test our rubric, or propose balanced books for reps. Do NOT use it to source a new market, score individual people, route inbound leads, launch outreach, merge records, or silently change CRM owners.
Use Virse CLI to find and organize assets, inspect existing aesthetic details, upload files or directories, replace originals, restore resources, and preview, download, and package deliveries. For asset management and resource directory tasks; canvas node layout is outside this entry point, and use virse-sharing to change sharing rules.
Produce a concise pre-market (morning) or after-close summary of a US stock watchlist - price and % change, RSI, trend, distance to stop and targets, biggest movers, upcoming earnings, and any alerts. Use when the user asks for a "morning brief", "market recap", "how did my watchlist do today", or on a scheduled morning/close run
Manage a US stock/ETF watchlist file: add, remove, update, list and validate tickers with thesis, entry, price targets, stop, tags, and per-ticker alert rules. Use when the user says things like “add NVDA to my watchlist”, “set a stop on AAPL at 210”, “what's on my watchlist”, “remove TSLA”, or “tag these as semis”.
Read AI Monitor traces, conversations, formal Bad Traces, overview and Agent/Tool/Model/Skill metrics, cost, security findings, existing diagnosis and investigation reports. Use for scoped observability queries and verified ZIP exports; never creates or cancels analysis.
MANDATORY ENTRY POINT for any tracking-related work — invoke this skill FIRST, before reading any tracking plan file, querying any tracking data, or producing any tracking analysis. Applies to generate, audit, review, optimize, increment/supplement, adjust, Q&A, data verification, troubleshooting (an event has no data / stopped reporting / data looks wrong), and TRACKING CODE GENERATION — requests like 'give me Android/iOS/Unity tracking code' or 'how do I write tracking code' MUST enter here first; this skill runs the four-step identification and then routes to the code-generation execution skill, so naming pre-checks and plan-consistency rules apply. Do NOT invoke execution skills (code generation, plan generation, verification) directly from the user request, and do NOT open tracking xlsx files with openpyxl/pandas or start ad-hoc log/file spelunking, before loading this skill. It holds the canonical naming dictionary, object-group validation rules, 29 category Markdown assets (including partial/shared caches), the no-data diagnosis flow, and the lint script that catches TE platform-import failures — none available outside this package, so ad-hoc work misses import-blocking issues and blind alleys. Costs 1-2 extra turns but prevents invalid plans and misdiagnosis. Trigger words: tracking, tracking plan, event design, tracking audit, tracking review, tracking optimization, supplement, increment, SDK tracking, tracking code, code generation, integration code, data verification, PRD, troubleshoot, diagnose, no data, missing data, event not reported.
Prüft und verbessert die Barrierefreiheit einer kleinen Webseite mit einer Person ohne Vorwissen, nach WCAG 2.2 AA in einfachen Worten: Kontrast, Schriftgrösse und Zoom, Bildbeschreibungen, Bedienung mit der Tastatur, Formulare, Vorlesen, Bewegung. Ergebnis ist ein Prüfprotokoll in docs/barrierefreiheit.md. Nutze den Skill bei «Barrierefreiheit», «barrierefrei», «Accessibility», «a11y», «WCAG», «Kontrast», «Alt-Text», «Screenreader», «für ältere Menschen lesbar», «mit Tastatur bedienen».
Send an independent judge that is not the author: a fresh evaluator subagent that checks finished work against pass criteria written before it was built (evaluator mode), or audits a batch against its source of truth (audit mode), with evidence for every verdict and never a fix. Use when the owner asks for an evaluator, reviewer, auditor or judge, or says 'send a judge', 'evaluate this', 'check my work with a fresh agent', 'get a second agent to review this', 'audit this folder', 'audit my registry', 'verify this against the source of truth', or 'LLM-as-judge'. Runs only when asked; it does not fire on its own at the end of a task. Not for checks a machine can run (tests, schema validation, a search that must return zero), not for hundreds of identical units, and not for fixing anything.
Guides the agent through enabling R8 in a Capacitor Android app so that it meets the Google Play DEX code optimization requirement (at least 25% obfuscation, optimization and shrinking from February 2027 for apps with more than 10 MB of DEX code). Covers `minifyEnabled true` with `proguard-android-optimize.txt` in `android/app/build.gradle`, the `-keep @interface com.getcapacitor.** { *; }` rule that prevents the startup crash in R8 full mode, per-plugin keep rules, resolving R8 'Missing class' build errors via `missing_rules.txt`, building a signed release APK with the debug keystore, and verifying with logcat, `mapping.txt` and the `r8.json` file inside the app bundle. Use when Play Console reports a DEX code optimization finding, when a Capacitor app crashes on startup after enabling `minifyEnabled`, or when R8 fails the release build. Do not use for iOS, resource shrinking, Capacitor plugin projects, Capacitor version upgrades, or non-Capacitor mobile frameworks.
Use when an agent needs live China travel data — geocoding, POI search, driving routes and map tiles (高德 Amap), flight schedules, transfers and fares (飞常准 Variflight), high-speed rail tickets (携程 Ctrip), weather and city coordinates (Open-Meteo) — or the planning order and mode trade-offs behind a trip. Triggers on 查航班 / 查火车票 / 查天气 / 查景点坐标 / 查驾车距离 / 行程该先定什么. Not for generating a full itinerary or shortlisting attractions.
Build a robotic cutaway of any object or creature from one reference image—a three.js scene written entirely in code that takes itself apart on camera, a page with a button for every part, and a 60 fps film with a synced procedural score. Claude matches the build to the picture, grades it line by line, measures its density and proportions, and films it only after the user approves the still. Use when someone hands over a picture of a robotic animal, machine or device and wants it built in 3D, opened up part by part, or recorded; or asks for a "cutaway", an "exploded view", a "robot animal simulator" or "make this image a 3D model that comes apart"
Finds, buys, or connects a custom domain (e.g. meinladen.ch) for the Albatros server. Explains domains and DNS with the analogy of an address and phone book, suggests names, checks availability with domain_suchen, and buys through Albatros using domain_kaufen (the person is the owner and enters their details only on the payment page). If the person already has a domain, the skill connects it with domain_verbinden: DNS records, TXT proof _albatros, and checks until the site appears with a lock in the browser. Use this skill for “custom domain,” “my address,” “buy .ch,” “which domain is available,” “search for a domain,” “DNS,” “A record,” “CNAME,” “TXT record,” “domain doesn’t point to my site,” “certificate,” and “https isn’t working.”
Group a scope of Issues into Waves that can be implemented concurrently without stepping on each other — estimate what each Issue touches, exclude the ones that need a human, and print launch lines. Use when the user has several prepared Issues and wants to know which can run in parallel unattended
Search ~1.01M computer-science papers and a curated research wiki with the `fs` command (FrontierScholar CLI). Use it whenever a task needs CS literature, even if FrontierScholar is not mentioned. This covers finding papers on a topic or before a date cut-off, building a related-work or reading list, finding papers similar to given ones, checking a paper's abstract, method, evaluation or first-version date, finding which papers use a benchmark or dataset, and finding the open problems and rising approaches of a research area. Prefer it over memory for paper ids, titles and dates.
Explains Git to someone with no prior knowledge using the analogy of a logbook aboard a ship and its copy in the harbor (Albatros's Git service, code.aufwind.sh). Gets the repo from the harbor, guides them through their first entries (Commit) with good notes, sends them to the harbor (Push), and checks that the copy arrives on the Albatros server at ~/projekt. Rules: main only, stage only your own files individually, never force-push. Use this skill for “Git,” “GitHub,” “harbor,” “commit,” “push,” “pull,” “Repo,” “what is a repository,” “save my changes,” “push rejected,” and “conflict,” and before committing anything for the person.
Helps someone with no prior knowledge write and choose text and images for their website: a homepage in three sentences, short text for people reading on mobile, their own photos instead of stock images, image rights and image size, and making AI text sound like their own voice. The result is a content list in docs/inhalte.md and the text on the site. Use this skill for “writing text,” “what should I write on the homepage,” “About us,” “images for the website,” “may I use this image,” “text sounds like AI,” and “content.”
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.