Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Create native Obsidian Canvas files (.canvas) from text content, supporting both MindMap and freeform layouts. This skill MUST be used when the user names Obsidian Canvas, and SHOULD be used when they want spatial organization of notes and cards. For hand-drawn whiteboard style, use excalidraw-diagram. For standard flowcharts/sequence diagrams, use mermaid-visualizer. Triggers on "Canvas", "Obsidian Canvas", "畫Canvas", "Canvas心智圖", "Canvas佈局".
Agent-ready Bambu print monitoring with exact plate previews and start/finish payloads. Trigger phrases: `what is my Bambu printer doing`, `post when this print starts and finishes`, `send this Bambu print to Discord`, `show my Bambu plate preview`, `when will the Bambu print finish`, `monitor my Bambu print`.
Research prediction-market odds, order books, price history, and public market-rule context from Polymarket, Kalshi, Metaculus, and DraftKings Predictions. DraftKings routes expose categories, availability maps, and rules, not live quote data. Use when the user asks what a market or forecasting community reports.
Reads, validates, and exports protocols.io data using the documented REST v3/v4 endpoints and the official MCP endpoint, and builds non-executing mutation plans. The bundled client makes bounded GET requests to official hosts only with --execute, and also validates saved protocol JSON offline for step order, version, DOI, and attribution metadata. Use when fetching a protocol, its steps, materials, or PDF from protocols.io by exact version. Use when validating a saved protocol snapshot for provenance before reuse. Use when planning a protocol create, update, publish, upload, or organization export without running it. Use when checking protocols.io rate limits, pagination, or authentication. Do not use for other protocol repositories or general literature search.
Hardens a Python repository's supply chain — Dependabot update automation, pip-audit vulnerability scanning, secret scanning and push protection, CodeQL, OpenSSF Scorecard, SBOMs, CODEOWNERS. Use for 'set up dependabot', 'audit dependencies', 'someone committed a key — stop that happening again', 'protect paths with CODEOWNERS', 'harden this repo'. Not for CI quality gates, workflow hardening, or PyPI publishing.
Build, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime. Use for Qiskit 2.x circuits and operators, V2 Sampler or Estimator primitives, target-aware transpilation, local or noisy simulation, IBM QPU execution, Runtime sessions or batches, error mitigation, and Qiskit ecosystem packages.
Use when building trust with people who don't yet know or trust you — new teams, new roles, hostile audiences, or strained relationships where the goal is connection before any ask. Applies Tactical Empathy through mirroring, labeling, and belonging cues. Not for confrontation (use difficult-conversations) or giving feedback (use feedback-coach).
Use when a Claude Code or Codex session ends or is declared finished, a friction needs fixing, a reusable learning needs capturing, local memory needs promoting upward, or for cross-session audits — detect friction AND learnings, route each to the right destination, and gate 'done'. Triggers: /retro, /retro done, 'retrospective', 'capture this learning', 'fix this skill', 'promote memory', 'audit', 'alles erledigt'.
Review and approve (or reject) pending update proposals from the review guideline monitoring agent, and apply approved changes to the practice-area configuration. Use when the review guideline monitoring agent proposes suggestions, or when the user says "review review guideline suggestions," "what pending review guideline updates are there," or wants to work through deviation-driven review guideline changes one by one.
Use when designing, building, reviewing, or fixing any right-to-left (RTL) user interface—Persian/Farsi (فارسی), Arabic, Hebrew, Urdu—on the web (React, Next.js, Vue, Tailwind, plain CSS) or Flutter, even if the user only says the app is Persian/Iranian without mentioning RTL. Covers layout direction and mirroring, which icons flip and which never do, bidirectional (bidi) text with LTR islands (URLs, emails, phone numbers, code), Persian vs Arabic-Indic vs Latin digits, Jalali (Shamsi) dates, Persian typography (font pairing, line height, the letter-spacing trap, ZWNJ نیمفاصله), font licensing, logical CSS properties, form input direction, and long-text overflow. Also use when Persian/Arabic text renders incorrectly or looks “off,” when localizing an LTR app to RTL, or to audit existing code for RTL violations with the bundled zero-dependency detector. Not for backend-only or non-UI tasks.
Design a Rust public API — trait design, generics versus dyn, sealed traits, what is exported, and which changes break semver. Use when designing or reviewing a crate public surface, when choosing between a generic parameter and a trait object, when adding a trait method or enum variant to a released crate, or when the user asks whether a change is a breaking change.
Review Rust changes on two axes at once — standards (idioms, ownership, errors, API surface, unsafe) and spec (does the change do what was asked) — with a Rust smell baseline layered on the repo lint configuration. Use when reviewing a Rust diff, pull request, or branch, when asked whether a change is ready to merge, or when a review needs to cover more than what clippy already reports.
Pick the concurrency model from the workload shape — rayon for data parallelism, scoped threads for borrowed stack data, channels for handoff, shared state last — and use the weakest correct atomic ordering. Use when writing or reviewing threaded Rust, when Mutex, RwLock, atomics, or manual Send/Sync appear, when a deadlock or data race is suspected, or when the user asks how to parallelize Rust code.
Transfer tokens from OpenAnt wallet on Solana or Base. Use when the user wants to send, transfer, or pay tokens via OpenAnt. Supports native coins (SOL, ETH) and tokens (USDC) by name, plus arbitrary tokens by mint/contract address. Covers "send SOL", "transfer USDC", "send tokens", "pay someone", "send ETH on Base", "transfer to address", "OpenAnt wallet send".
Guided entry point for using Sentry through your agent. Orients you to your current setup and, for a new project, sets up Sentry end to end with sane defaults — provision a project, install the SDK (errors, tracing, and whatever it enables by default), and confirm real telemetry reaches Sentry. Routes other intents (adding more signals, fixing issues) to the right skill.
Judge board subskill for simmer. Dispatches a panel of judges with different lenses, runs one deliberation round in which they challenge each other's scores, then synthesizes consensus scores and a single ASI. Drop-in replacement for simmer-judge that produces the identical output format. Do not invoke directly; the simmer orchestrator dispatches it when JUDGE_MODE is board.
Reflect subskill for simmer. Records iteration results in a trajectory table, tracks the best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly; called by the simmer orchestrator after each judge round.
Setup subskill for simmer. Inspects the artifact or workspace, infers evaluation contracts and search space, proposes a complete assessment to the user, and produces a setup brief after confirmation. Conversational rather than form-based: the agent works to understand the problem, then presents its findings. Do not invoke directly; called by the simmer orchestrator.
Generate a polished, presentation-ready HTML slide deck from a topic, document, or set of notes. Use this whenever the user says 'make a slide deck,' 'build a presentation,' 'turn this into slides,' 'create a deck for,' 'pitch deck,' 'investor deck,' 'training deck,' or asks for slides on any topic. Outputs a single self-contained HTML file with scroll-snap navigation and a clean visual system. The deck should look like a designer made it, not a default template.
Structures feature work for AI coding agents into gated phases — research, spec, plan, tasks, implement, validate — each producing a short reviewable artifact that constrains the next. Use when requirements are informal or drift-prone, when the same prompt produces different implementations across sessions, or when a feature touches auth, database schema, or API contracts. Keywords: spec-driven development, SDD, spec.md, plan.md, tasks.md, constitution.md, acceptance criteria, drift detection.
Pulls sports scores, standings, rosters, player/team stats, public sports news, editorial, wiki/video content, and betting odds through the Crawlora API — ESPN, SofaScore, MLB, Strava, DraftKings Sportsbook, Cricinfo, and Sportskeeda. Use for scores/stats or explicitly requested public sports-media research; Strava routes and clubs can reveal location-sensitive patterns.
Design and audit support deflection, knowledge bases, help-center search, article quality, macros, chatbots, in-product help, diagnostics, escalation paths, unresolved-user recovery, support analytics, and product feedback loops. Use when reducing tickets while preserving customer trust and fast human help for high-stakes issues.
Forecast and audit customer support workforce plans across channels, languages, queues, SLAs, severity tiers, launches, incidents, seasonality, shrinkage, occupancy, escalation, QA, macros, deflection, BPO/vendor coverage, and burnout risk. Use when support demand must be staffed without sacrificing quality or trust.
Researches public Threads (Meta) profiles, posts, replies, and search results via the Crawlora API, returning clean JSON. Use when the user wants a Threads profile's stats, a post's content/replies, a profile's recent posts, or a keyword search on Threads — instead of scraping the app.
Research public TikTok profiles, videos, comments, hashtags, search results, trending feeds, and Creative Center signals through Crawlora. Use for TikTok-specific discovery or verification instead of scraping TikTok directly; use tiktok-ad-research for ad-only comparisons and influencer-discovery for cross-platform creator shortlists.
Jurisdiction-aware employment Q&A — working-hours system classification, overtime pay, minimum wage, annual leave, maternity leave, sick leave/medical period, final wage payment — answered for a specific province/municipality, grounded in researched current rules rather than stated from memory. Use when the user asks any employment law question, or says "what are the rules in [place]," "does this role qualify for the flexible working hours system," "do we need to pay overtime," or "can we classify this role as."
Manages the walletconnect CLI for wallet connection, session management, message signing, transaction sending, and cross-chain bridging (swidge). Use when the user wants to connect a wallet, check session status, sign messages, send transactions, bridge tokens across chains, or disconnect.
General-purpose web-intelligence utilities via the Crawlora API — scrape any URL to clean markdown/HTML, extract schema-conforming JSON from a page, fingerprint a site's tech stack, geocode addresses, compare cost of living between cities/countries (Numbeo), look up a company's import/export trade records (ImportYeti), check a domain's traffic (SimilarWeb), or resolve a brand's identity from its domain. Use for one-off utility lookups that don't fit a specific platform skill.
Retrieve posts from a Weibo account. Enter a Weibo profile URL or uid to query the user's latest posts via the Redfox API, with pagination. Use when the user wants to view someone's Weibo activity or follow a blogger's latest content. Triggers: search user posts, user Weibo, Weibo profile, search blogger, Weibo activity.
Weibo post search tool. Searches Weibo posts through the Redfox API using user-provided keywords, with filters for search category (relevance, popularity, or real-time ranking) and authentication type. Use when users need to search Weibo content or find popular Weibo posts. Triggers: Weibo search, search Weibo, popular Weibo, Weibo posts, Weibo account search.
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.