Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Compile a PDF from the main .tex file in the thesis directory (Thesis.tex by default) using XeLaTeX and BibTeX. Use for requests such as “compile thesis,” “generate PDF,” or “XeLaTeX compile.” Can also compile a Beamer presentation in the same directory (ThesisPresentation.tex by default). See the repository root README.md for path placeholders.
A government-document writing skill based on full counting statistics of real official documents. It splits into the official-document family and the Party-building family, covering six official-document genres — research reports, leadership speeches, work opinions, experience materials, work plans, and experience summaries — plus a thousand-character class of Party-building/grassroots experience materials, and provides verifiable numeric parameters, skeleton formulas, title techniques, and automated self-check scripts. Trigger scenarios: "write a research report", "draft a leadership speech", "write a work opinion", "write a Party-building experience material", "turn the material into an experience summary", "make this draft sound more like an official document", "check whether this official document's parameters are right".
Full-process management of Amazon FBA inbound and Fulfillment Inbound. Use to create and manage inbound plans, and handle packing, placement, shipments, shipment content updates, delivery windows, self-delivery appointments, transportation options, product compliance, prep, box labels, bills of lading, and async operation status. Triggered when the user mentions FBA inbound plans, Send to Amazon, creating an inbound plan, packing option, placement option, transportation option, box labels, inbound labels, delivery appointments, shipmentConfirmationId, createInboundPlan, Fulfillment Inbound API, v2024-03-20, or the v0 inbound API. Even without an explicit mention of "Fulfillment Inbound", trigger this skill whenever the goal is to send inventory to an Amazon fulfillment center and complete the steps of plan creation, packing, placement, transportation, or delivery.
Filter independent-site Shopify products by multiple dimensions via EHunt Shopify product query (gateway route `ehunt/shopify/productQuery`) (keyword/URL, price, weekly sales, listing time, Facebook ads, competition level, supply availability, shipping country, etc.). Trigger when the user mentions EHunt Shopify product, Shopify product selection, independent-site product selection, Shopify bestsellers, Shopify dropshipping, independent-site product listing, Facebook ad products, Shopify product query, or shopify items. Even if the user does not write EHunt, as long as they are searching products, checking weekly sales/revenue/competition level, or filtering products on Shopify independent sites, this skill should also be triggered.
Filter independent-site Shopify stores by multiple dimensions via EHunt Shopify store query (gateway route `ehunt/shopify/storeQuery`) (store name/domain, country, years since creation, product count, ad count, monthly visits, monthly orders, social media followers, etc.). Trigger when the user mentions EHunt Shopify store, Shopify store analysis, independent-site stores, Shopify seller, independent-site competitor stores, Shopify monthly visits, independent-site ad library, shopify stores, or Shopify store query. Even if the user does not write EHunt, as long as they are finding stores, filtering store data, or analyzing store performance on Shopify independent sites, this skill should also be triggered.
Filter Temu products by multiple dimensions via EHunt Temu product query (gateway route `ehunt/temu/productQuery`) (keyword/product ID/store ID, front-end and back-end categories, price, rating, reviews, total/weekly/daily sales, listing time, fully managed/semi-managed, semi-managed region, tags, etc.). Trigger when the user mentions EHunt Temu product, Temu product selection, Pinduoduo cross-border, Temu bestsellers, Temu semi-managed, fully managed products, Temu product query, or temu items. Even if the user does not write EHunt, as long as they are searching products, checking sales/rating/price, or filtering products on Temu, this skill should also be triggered.
Filter Temu stores by multiple dimensions via EHunt Temu store query (gateway route `ehunt/temu/storeQuery`) (store name/ID, country site, back-end category, fully managed/semi-managed, total/weekly/monthly sales and revenue, rating, reviews, followers, product count, store opening time, etc.). Trigger when the user mentions EHunt Temu store, Temu store analysis, Temu seller, Temu store rankings, Temu semi-managed stores, Temu revenue, temu stores, or Temu store query. Even if the user does not write EHunt, as long as they are finding stores, filtering store data, or analyzing store performance on Temu, this skill should also be triggered.
When the user wants to run ads that appear inside the Google Maps local pack / map pack results. Also use when the user mentions "local search ads," "map pack ads," "ads in the map results," "local pack ads," "Google Maps ads," "location extensions ads," or "promoted pins on Google Maps." For LSAs (pay-per-lead), see lsa-ads. For standard geographic PPC, see local-ppc-ads.
Local SEO and Google Business Profile audit: diagnose why a business isn't ranking in the local pack / map results and produce a fix plan. Covers GBP completeness, NAP (name/address/phone) consistency across the site and citations, local pack and "near me" ranking factors, review velocity and responses, local landing pages, service-area pages, and LocalBusiness JSON-LD. Use whenever the user asks about local rankings, map results, Google Maps ranking, NAP consistency, store/branch pages, or multi-location SEO. Trigger on: "local SEO", "Google Business Profile", "GBP audit", "rank on Google Maps", "local pack", "map pack", "near me ranking", "NAP", "local citations", "my business isn't on the map", "why don't I show up on Google Maps", "store locator SEO", "multi-location SEO", "service area pages", or any location-based ranking question. For full-site (non-local) audits use /seo-analysis; for a single URL use /seo-page.
Append a structured entry to the project's session log (`docs/LOGS.md`): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before `/clear`, before closing your agent session, or at any natural stopping point. Model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "log this session", "log-session", "write a session log", "journal what we did", "record this session before I clear", "save the session summary".
Keep WordPress sites on Hostinger web hosting updated and secure: checks core, plugin and theme versions, known vulnerabilities and install health on one site or every site in the account, reports what needs doing, applies updates in a safe order, and confirms each site still loads. Also covers cache purges, the Memcached object cache, maintenance mode and one-click wp-admin login links. Triggers: update my WordPress, update plugins, are my WordPress sites secure, WordPress vulnerabilities, outdated plugins or themes, WordPress maintenance, speed up WordPress, log me into wp-admin.
Discovers all businesses of a given type in any geography using Nimble WSAs. Two modes: Discovery finds businesses from scratch; Audit compares a user's existing list (Google Sheet, CSV, inline) against fresh discovery, categorizing entries as matched, discovered-only, or reference-only. Vertical presets (Healthcare, SaaS, Restaurants, Legal, Auto/Home) auto-select WSA routing. Triggers: "find all X in Y", "build a list of", "market sizing", "account universe", "how many X in Y", "TAM for", "discover all", "audit my list", "compare against", "what am I missing", "gap analysis", "verify my business list", "prospect list". Do NOT use for competitor monitoring — use competitor-intel instead. Do NOT use for company deep dives — use company-deep-dive instead. Do NOT use for neighborhood-level exploration with social enrichment — use local-places instead.
Run MassGen experiments and analyze logs using automation mode, logfire tracing, and SQL queries. Use this skill for performance analysis, debugging agent behavior, evaluating coordination patterns, and improving the logging structure, or whenever an ANALYSIS_REPORT.md is needed in a log directory.
Analyze microbiome and metagenomics data using MGnify, GTDB, ENA, and literature tools. Search studies by biome/keyword, retrieve taxonomic profiles and functional annotations, classify genomes with GTDB taxonomy, and find related publications. Use for human gut microbiome, soil/ocean metagenomics, and environmental microbiology research.
Move an existing website from another host to Hostinger web hosting (Shared, Cloud or Agency plans) without downtime: WordPress sites from a files archive and SQL dump, static and PHP sites from an archive, Node.js apps from source. Creates the website on the real domain, imports files and database, tests the copy before any DNS change, then switches the domain and SSL. Triggers: migrate my site to Hostinger, move my website from another host, transfer my WordPress site, import my website, switch hosting to Hostinger
Manually migrates legacy `nango.yaml` Nango projects to Zero YAML TypeScript by generating `models.ts`, `index.ts`, package/tsconfig scaffolding, and wrapping legacy scripts in `createSync()`, `createAction()`, or `createOnEvent()`. Use when a Nango repo still has `nango.yaml` and needs manual Zero YAML migration.
Mini Six Ren divination system - traditional Chinese divination and fate analysis. Use when the user asks for divination, fortune telling, or prediction using mini six ren (小六壬), or mentions keywords: 占卜、算卦、小六壬、三传、运势、占一卦、divination、fortune. Supports four input modes: numbers, date/time, Chinese characters (汉字笔画), and current time. Generates three-pass (三传) predictions with rich structured analysis: auspice grading, overall pattern, five-element flow, subject-object (体用) relation, special combinations, and timing/direction guidance. LLM interpretation follows a rigorous seven-step traditional framework.
Use when a trained medical-imaging model needs its documentation. Fills a Model Card and a Datasheet for its dataset from facts you supply, adds a METRIC-informed data-quality pass and gates that no required section is empty. Never invents numbers, provenance or licence.
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are required for each operation, how displayOptions control field visibility, and when to use patchNodeField for surgical edits vs full node updates.
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, or scheduled tasks. Always consult this skill when the user asks to create, build, or design an n8n workflow, automate a process, or connect services — even if they don't explicitly mention 'patterns'. Covers webhook, API, database, AI, batch processing, and scheduled automation architectures. Also use when optimizing a slow workflow or speeding up large-item-count processing (node count, batchSize, all-items vs per-item).
Provides guidance on using the next-devtools MCP server. Use when working with Next.js projects that have the MCP server configured, when the user encounters connection issues, or when needing help with error detection, route inspection, Server Action tracing, or Cache Components migration.
Create, inspect, retrieve, author, revise, enrich, audit, repair, research, analyze change impact, migrate, validate, and maintain knowledge for AI agents as conformant Open Knowledge Format (OKF) bundles. Use for /okf commands; work on an existing OKF bundle; documentation of tables, datasets, views, metrics, runbooks, playbooks, APIs, schemas, or join paths; exports from catalogs, metadata, websites, URLs, or source code; and any knowledge an agent will read later. Apply implicitly when editing an OKF bundle so conformance, provenance and sources, generated and verified trust signals, freshness, log.md, indexes, and cross-links remain current. Tracks OKF v0.2, including attested computations and migration from v0.1.
Operate Omnigraph graphs and deployments. Use for `.pg` schemas, `.gq` queries, Omnigraph CLI commands, `file://`/`s3://`/`az://` graph URIs, `cluster.yaml`, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema changes, bulk loads, and retries after uncertain remote outcomes
Configure OpenSpec project settings and global CLI configuration using `openspec/config.yaml` and `openspec config` commands. Use when the user says "configure OpenSpec", "project config", "add project context", or wants to set per-artifact rules.
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Fast-forward through artifact creation with `/opsx:ff`, generating all planning artifacts (proposal, specs, design, tasks) at once. Use when the user says "fast forward", "create all artifacts", "/opsx:ff", or has a clear picture of what to build.
Guided onboarding through the complete OpenSpec workflow using `/opsx:onboard`, walking the user through a real change in their codebase. Use when the user says "onboard me", "tutorial", "/opsx:onboard", "how does OpenSpec work", or is new to OpenSpec.
Create and manage custom workflow schemas using `openspec schema init/fork/validate/which`. Use when the user says "create a custom workflow", "custom schema", "fork a schema", or wants to define their own artifact types and dependencies.
General-purpose API fallback and interface exploration: when an interface has no dedicated first-class command, use openydt api <cmd> --body to directly send any callable interface, and look up cmd/parameters in catalog.json, distinguishing callable interfaces you can actively invoke from webhooks that can only receive passively. Use when a cmd has no dedicated subcommand in the domain skills, when you need to call a non-first-class interface (such as city operation coupons/third-party parking lots/residential access control/monthly pass reservations/authorized visitors/document rules/vehicle tags, etc.), or when asking "how do I call this cmd / will the platform call me back".
Parking payment transaction domain (trade): real-time/estimated fee lookup for temporary vehicles, payment info callback, batch arrears repayment, prepaid deposits and operation point presets. Use when the user wants to calculate parking fees, return/sync payment orders, batch repay arrears, or top up prepaid deposits for vehicles for automatic deduction. This domain owns "real-time fee lookup/payment"; for historical bills/payment record queries use the parking domain (openydt-record).
Data analysis domain (data): read-only statistical reports such as payment bills and bill summaries, traffic flow curves, top license plate distribution, real-time on-site statistics, daily vehicle exits/transaction counts, parking space usage (including echart heatmaps), and parking duration distribution. Use when the user wants parking lot business reports, trend analysis, or data health checks (aggregate statistics rather than per-vehicle details). Note: the three statistical interfaces for parking spaces/duration/echart are marked write in the platform contract and require --yes to call; for per-vehicle details/on-site vehicles see the parking domain (openydt-record).
Device control domain (device): remote gate open/close, changing gate mode (always open/normal), pushing text and voice announcements to displays, pushing default screen content, manual snapshots, cloud scan-code device scanning/stop/voice/config updates, and checking cloud device online status. Use when the user wants to issue on-site commands to barriers/booths/displays/scan-code devices or check device status — high-risk on-site operations; write operations require --yes, --dry-run is recommended first. Note: this domain pushes display/announcement content to devices; checking what a given vehicle "should display" belongs to the park domain.
License plate list management domain: adding, deleting and querying blacklist (blacklist: no entry/high fees), whitelist (redlist: free passage rules) and visitor (visitor: time-limited visit registration). Use when the user wants to blacklist/unblacklist, configure passage rules such as for police cars, or register or cancel visitor vehicles. The "special vehicle type ID (specialCarTypeId)" referenced by lists is created by the ticket domain (openydt-monthticket); this domain only references it as a parameter and does not create it.
Parking record domain (parking): query on-site/entry-exit/parking details/historical payments/arrears, perform supplementary entry correction/vehicle locking/self-service entry and exit, and semantically analyze business traffic, parking duration, evasion and passage types by exit events. Use when the user requests the above record-level tasks; for real-time fee queries and payments use openydt-billing, and for platform aggregate statistics use openydt-data.
openydt (Akezhibo parking open platform CLI) shared foundation: profile/credential configuration, multiple environments (test/dev/prod), v2/v3 signatures, response envelope and status/resultCode, exit codes, rate-limit retries, write operation safety rules, and parking-lot experience notes (park-notes). Read this foundation first when using openydt for the first time, configuring/switching profiles, troubleshooting signature/authentication/rate-limit issues, or before performing any write operation; all openydt domain skills should Read it before executing.
A meta-skill for creating or standardizing custom openydt (Akezhibo parking open platform CLI) Skills. Use when the user wants to create a new openydt domain skill, solidify an interface or a multi-step business process into a reusable Skill, or standardize an existing SKILL.md (frontmatter / command table / trigger words / write operation --yes guard). Comparable to Feishu's lark-skill-maker.
Options trading strategy analysis and simulation tool. Provides theoretical pricing using the Black-Scholes model, Greeks calculations, strategy P/L simulations, and risk management guidance. Use when a user requests options strategy analysis, covered calls, protective puts, spreads, iron condors, earnings plays, or options risk management. Includes volatility analysis, position sizing, and earnings-based strategy recommendations. Educational focus with practical trade simulation.
Guides Oracle database development including SQL, PL/SQL stored procedures, triggers, EXPLAIN PLAN optimization, AWR analysis, RMAN backup, RAC clustering, and Data Guard. Use when the user needs to write Oracle SQL, create PL/SQL procedures, tune query performance, or manage Oracle database administration.
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the top of "我的设计". Each connector module picks its own UI form (list, avatar stack, status ring, heatmap, file grid, alert card, …) based on the data shape it returns, so the layout scales as Orbit's connector ecosystem grows. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against the user's live connector data.
Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection and renders the digest as the Orbit Daily Digest email opened inside Gmail's reading view. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Gmail data.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Version-pinned inventory of the telemetry (spans, metrics, logs, attributes) emitted by OpenTelemetry collector components and SDK instrumentation packages. Use when working with a covered component — what it emits at a given version, or how emission changed across versions — and when upgrading a component or SDK version, to see the telemetry after the change.
Converts research papers into executable skill packages via document conversion, critical analysis, and co-evolutionary refinement. Triggers on: "convert this paper to a skill", "paper-to-skill", "extract methodology from paper", "make a skill from this paper". NOT for literature review, use research-critique.
Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.
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.