Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Search and access the Tor dark web and .onion hidden services. Use when user asks to search dark web, investigate .onion sites, check for dark web data leaks, fetch onion URLs, hunt ransomware groups, look up leaked credentials, conduct Tor-based OSINT, or monitor dark web activity. Provides 12 search engines, batch scraping, entity extraction, relevance scoring, and export to CSV/JSON/STIX/MISP. Requires Tor running locally (socks://127.0.0.1:9050).
Burn styled, animated captions into a short clip with OpenClip using caption presets (beast, pop, kendrick, mozi, dan, sara, lucy and more) or a custom caption style and position. Use when asked to "add captions", "add subtitles to this short", "burn in the text", "make it look like MrBeast captions", "restyle the captions", "put words on screen", or "caption this clip".
Turn one long video into a full batch of platform-ready short clips for TikTok, Reels, and YouTube Shorts with OpenClip — find the moments, reframe to vertical, burn in captions, and write the post copy for each. Use when asked to “repurpose this podcast”, “turn this into a week of content”, “make a content batch from this webinar”, “get 10 shorts out of this”, “cut this up for social”, or “give me clips ready to post”.
Hyperliquid perps + spot trading via the OpenFinance backend. Use for any Hyperliquid task — orders (perp, spot, TWAP, HIP-3 stocks/commodities/FX/preipo, HIP-4 binary outcomes), leverage/margin, account balance, market data (REST + WebSocket), OHLCV candles, deposits/withdrawals. Hyperliquid is its **own L1**, chain. Hyperliquid accepts **only USDC** (not USDT, not USDC.e). INR funding route — Onramp.money INR → USDC on Polygon/BSC → Relay bridge → Arbitrum → deposit. Hyperliquid runs **unifiedAccount** so spot+perp USDC share one margin pool — agents MUST sum `account.withdrawable + spot.USDC.total` and present it as ONE figure (NEVER "Perp withdrawable $0" or "Spot USDC" as separate lines). On first balance read, if `account.withdrawable > 0` and `GET /agent/trading/abstraction` returns `"default"` or `"disabled"`, POST `{abstraction:"u"}` to upgrade (one-shot, idempotent). Triggers — "buy/long/short/sell BTC/ETH/SOL/NVDA/TSLA/...", "perp/spot order", "Gtc/Ioc/Alo/FrontendMarket", "TP/SL", "TWAP", "leverage/cross/isolated", "deposit to Hyperliquid", "withdraw to Arbitrum", "HL balance", "HIP-3", "HIP-4", "outcome / split / merge / negate", "Yes/No shares", "HLP". Covers /agent/trading/* (market/{mids,metas,perp-metas,perp-categories,spot-metas,l2-book,token,all-dexs-asset-ctxs,outcome-meta}, deposit-address, account, portfolio, batch-portfolio-states, rate-limit, orders, orders/details, orders/history, orders/:oid/status, twap, twap/fills, twap/:id, fills, fills/by-time, funding, leverage, margin, withdraw, abstraction, outcome/{split,merge,merge-question,negate}). Every user-scoped read accepts an optional `?address=0x…` query — falls back to caller; `/deposit-address` is deliberately caller-only.. Prerequisite — openfin-setup.
Error → fix lookup for the OpenFinance backend (Polymarket, Relay, Hyperliquid, Solana RPC, account-setup). Use the moment a call fails or returns an unexpected status. Triggers on the error signatures verbatim or paraphrased — Polymarket — "maker address not allowed", post-migration balance/allowance both reading 0, "allowance max but CLOB returns 0", "tick size", "order size below minimum"; Relay — "InstructionFallbackNotFound / Custom:101", "Blockhash not found", "401 No valid authorization signatures" or 412 on Solana execute, "User has no Solana wallet provisioned", "topupGas forced off"; Hyperliquid — "Insufficient margin / account value too low", "withdrawal not arriving on Arbitrum", WebSocket stale data, "price out of bounds". Read this BEFORE assuming a bug.
Turn the main session into a dispatcher that never blocks. Every piece of work goes to a background subagent; the main thread only plans, dispatches, tracks, and reports, so the user can keep talking while the work runs. Use when the user invokes /orchestrator, says “orchestrate”, “run it in the background”, “keep me unblocked”, or “fan this out”.
Decision framework for particle system projects. Routes to specialized particle skills (gpu, physics, lifecycle) based on task requirements. Use when building particle effects or needing guidance on which particle techniques to combine.
Write clear, plain-English patient communications for any healthcare context. Use when asked to write a patient letter, patient information leaflet, appointment letter, test-results letter, discharge summary for patients, or health education content. Produces an accessible patient communication at an appropriate reading level with clear next steps.
Authentication and authorization security assessment for sessions, tokens, MFA, account takeover, IDOR, BOLA, BFLA, privilege escalation, tenant isolation, and identity boundary validation. Hands off to recon, input/protocol, access-control deep dive, exploit, or reporting workflows when those become the owner phase.
Master personal finance planning including budgeting, debt management, savings strategies, retirement planning, investment allocation, and financial goal setting. Use when helping individuals manage money, build wealth, reduce debt, or plan for financial milestones.
Create distinctive, crafted TUI components for pi using @mariozechner/pi-tui and @mariozechner/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi extensions or custom tools. Triggers on: 'build a TUI component', 'make a dashboard', 'create an overlay', 'interactive widget', 'terminal UI', 'custom component', 'pi-tui', or any request to create visual, interactive terminal interfaces. Also use when beautifying or redesigning existing TUI components.
Find and state a market positioning that differentiates the user's offer: match the message to the market's maturity stage, name the unique mechanism, choose one psychological angle, and pressure-test the result. Use when the user asks 'how do I position this', 'how do I stand out', 'why should anyone pick us', 'write my value prop / tagline / headline claim', 'our marketing sounds like everyone else's', or when any copy or content work stalls because there's no clear core claim — even if they never say the word positioning. Also works in audit mode on an existing positioning. Produces a Positioning Statement: market stage, named mechanism, chosen angle with the claim written out, and a pass/fail test record.
Every Apple framework, indexed locally, with deprecation analysis and an MCP server no other Apple-docs tool has. Trigger phrases: `look up an Apple API`, `what's deprecated in iOS`, `find a SwiftUI symbol`, `port this from UIKit to SwiftUI`, `what changed at WWDC`, `use apple-docs`, `run apple-docs-pp-cli`.
Keyword Tool data from eRank, plus local scoring, drift, and listing-gap analysis for Etsy sellers. Trigger phrases: `research dad mug on eRank`, `score an Etsy keyword`, `find eRank top listings`, `compare Etsy listing tags`, `use eRank`, `run eRank`.
Every ExchangeRate-API endpoint, plus a local rate history, watchlists, drift alerts, and an MCP server no one else... Trigger phrases: `convert USD to EUR`, `what's the exchange rate for`, `check my FX quota`, `sync exchange rates`, `what was USD/EUR last week`, `use exchangerate-api`, `run exchangerate-api`.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
When the user wants to plan PR, write a press release, or manage media relations. Also use when the user mentions "PR," "press release," "media relations," "news release," "journalist," "media coverage," "product announcement," or "earned media."
Write platform-optimized social media copy for Instagram, Facebook, LinkedIn, and X/Twitter with hooks, CTAs, and hashtag strategies. Use this skill when the user needs to create social media posts, adapt content across platforms, improve engagement rates, or develop a social content strategy — even if they say 'write a post for IG', 'our social engagement is low', 'adapt this for LinkedIn', or 'how do we write better captions'.
Preview a single Flutter widget in isolation using the built-in Flutter Widget Previewer (`flutter widget-preview`) — wires up a project-specific `previewWrapper` so the widget renders against the app's real theme and providers, launches the local preview server, and lets the agent take headless-Chrome screenshots of the live preview while a human follows along in their own browser. Use whenever the user wants to design, iterate on, dogfood, share, audit, or sanity-check a standalone Flutter widget — even when they don't say "previewer" (e.g. "let me see the new button", "show me dark mode for this card", "throw this widget on a preview", "iterate on the empty state", "preview just the badge", "what does this look like at tablet width"). For full-screen design polish on a running app, use `design-polish` + `android-emulator` instead. Skips — non-Flutter UIs, full-app QA flows, projects on Flutter < 3.35.
This skill MUST be used for product conjoint analysis (商品聯合分析、屬性偏好分析) to study trade-offs among product attributes using ratings, stated choices, or observed choices. It SHOULD be used for attribute importance, willingness-to-pay (願付價格), or product configuration questions when multi-attribute preference data is available. It MUST NOT treat review mentions as observed choices or produce pricing and probability claims unsupported by the data and fitted model.
Assist with core product management activities including writing PRDs, analyzing features, synthesizing user research, planning roadmaps, and communicating product decisions. Use when you need help with PM documentation, analysis, or planning workflows that integrate with your codebase.
Use when adding service-wide Spring Boot 3 Actuator, Micrometer metrics, distributed tracing, OpenTelemetry export, structured logging, health probes, dashboards, or alerts. Combine with ai-observability only for Spring AI-specific token, prompt, and model telemetry.
When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit.
Make an answer easier to start, scan, pause, and resume without making it shallower: a reply that is correct but too dense to enter, a wall of text with the useful part buried, a summary that dropped the caveat that mattered, or prose that reads as machine-generated. Covers useful-answer-first ordering, short paragraphs, literal headings, preserved nuance, and a small diagram where structure is the difficulty. Use when the user says "I do not understand", "explain this more simply", "make this clearer", "too dense", "break it into parts", "step by step", or "without losing the details". Not for shortening at the cost of accuracy, not for compressing an ordered procedure or a security warning, and not for a draft that sounds generated rather than dense, which is a question about voice and belongs elsewhere. An answer nobody can get into was not delivered, and one shortened until it is wrong was not either.
Export your entire Prospeo people search to CSV. Build filters in Prospeo's UI, then use this skill to extract every result via the API — even searches over 25K. Handles pagination, rate limiting, deduplication, and state-by-state splitting automatically. Pair with /icp-prompt-builder on a 50-person sample to tune a qualification prompt BEFORE exporting 25K.
This skill should be used when searching for people/leads using the Prospeo Search Person API. It provides the correct API format, filter types, rate limiting patterns, and state-by-state crawling techniques to overcome the 25K result limit. Use when building lead lists, searching by job title/industry/location, or integrating with Prospeo.
Prove it for debugging, performance investigation, bottleneck analysis, profiling, and optimization work. When reading code does not prove the cause, run a minimal reproduction, add temporary traces, measure bottlenecks, and verify the fix or improvement.
Creates, syncs, audits and manages Prowler compliance frameworks end-to-end. Covers the two supported JSON schemas (universal multi-provider and legacy per-provider), the SDK model tree (legacy attribute classes, universal ComplianceFramework, ConfigRequirements guardrails), output formatters (legacy per-framework + universal data-driven), API/UI consumption, upstream sync workflows, and cloud-auditor check-mapping reviews. Trigger: When working with compliance frameworks (CIS, CIS Controls, NIST, PCI-DSS, SOC2, GDPR, ISO27001, ENS, MITRE ATT&CK, CCC, C5, CSA CCM, DORA, KISA ISMS-P, ASD Essential Eight, DISA STIG, CISA SCuBA, SecNumCloud, FedRAMP, HIPAA, NIS2, Prowler ThreatScore), creating a universal multi-provider framework, adding ConfigRequirements guardrails, syncing with upstream catalogs, auditing check-to-requirement mappings, adding output formatters, or fixing compliance JSON bugs (duplicate IDs, empty Version, wrong Section, stale check refs).
Geochemistry data analysis and visualization for igneous, metamorphic, and sedimentary rocks. Use when the agent needs to: (1) Create ternary diagrams for compositional data, (2) Plot REE spider diagrams with normalization, (3) Build TAS or other classification diagrams, (4) Apply log-ratio transforms to compositional data, (5) Calculate CIPW norms, (6) Generate Harker variation diagrams, (7) Compute element ratios and anomalies.
Execute a micro-level Python code quality audit. Validates code against live GitHub standards for typing, code style, function design, data validation, error handling, module structure, and testing. Produces a detailed violations report with prioritized action plan. Use when the user asks to check Python code quality, validate best practices, or review Python code standards. Triggers on: 'python best practices', 'python code quality', 'code review', 'python standards', 'type hints review', 'pytest review', 'pydantic validation'.
Sets up static type checking for a Python package — choosing mypy, pyright, basedpyright or ty, strict configuration, per-module overrides, shipping py.typed — and fixes type-check errors. Use when the user says 'add type checking', 'set up mypy', 'pyright errors', 'make this package typed'. Not for lint or format failures, failing tests, runtime bugs, or the CI workflow that runs the checker.
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.