Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Structured design dialogue before CloudCannon work that has more than one sensible answer—such as a migration’s editability tradeoffs, modeling a collection or page builder, restructuring content or config, or an ambiguous “make this work with CloudCannon.” Explores intent and constraints, then presents a design for approval before implementation. Not for single well-defined tasks, clear bug fixes, or a detailed spec.
This skill should be used when working with Convex actions, HTTP endpoints, validators, schemas, environment variables, scheduling, file storage, and TypeScript patterns. It provides comprehensive guidelines for function definitions, API design, database limits, and advanced Convex features.
Edit the scene currently open in Creator Hub through its MCP server: entities, components, Smart Items, scene settings, and preview. Use when `creator-hub` MCP tools are in the session, a scene is or may be open in Creator Hub (including before editing its main.composite, main.crdt, or scene.json), when connecting an external agent to the Hub, or when the user mentions the Creator Hub AI assistant or its MCP server.
Audits codebases and product copy for deceptive dark patterns inferable from local source code and text—no runtime inspection or screenshots needed. Produces a structured narrative report with confidence grading, source locations, concise reasoning, and official pattern reference links for each detected pattern. Covers pricing, subscriptions, consent, modals, preselected controls, misleading CTAs, and more.
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, strips defensive code, and in skill-file mode lints SKILL.md files for quality. Use when cleaning up code, simplifying, removing boilerplate, before committing, or when reviewing a skill before promoting it.
Precise DingTalk contact lookup. Use when a userId is already known to look up details, department, title or email, to reverse-lookup a user by full phone number, or to query yourself, department members and roles. Fuzzy name search, employee ID, responsibilities and reporting lines go to dingtalk-aisearch; once you have the userId, use this skill to fill in details. Command prefix: dws contact.
Doctor Strange — causal sand-table simulation via parallel universe subagents. Models actors, incentives, constraints, feedback loops, state changes, and failure modes before rendering how a future event may unfold step by step, like a human mentally rehearsing multiple futures. Stores simulations as persistent memory for later recall. TRIGGER when: user explicitly asks to simulate / rehearse / play out a scenario; user says "推演", "模拟", "预演", "imagine", "what if", "run through", "play this out", "what could go wrong"; user faces a high-stakes upcoming decision and is uncertain how it will unfold. DO NOT TRIGGER when: user wants factual lookup or research; user wants analysis of a past event (use regular memory); user wants a simple recommendation without simulation; user is debugging code or doing technical work unrelated to decision-making. Three modes: SIMULATE (run a new forward simulation), RECALL (surface past simulations as soft priors), MANAGE (list/void/re-run stored simulations).
Plan, build, and run lifecycle email programs through the Hyper MCP — welcome/onboarding, nurture, re-engagement, win-back, and abandoned-cart sequences across whichever provider fits (Klaviyo for ecommerce, Resend for SaaS/dev tools, Beehiiv for newsletters, Gmail for low-volume ops). Use when the user wants to build an email sequence, set up a welcome flow, recover lapsed users, send a broadcast, manage a list/audience/segment, or asks about lifecycle/drip/nurture campaigns.
Emergency triage and symptom screening assistant. Trigger this skill when users describe physical discomfort, pain, sudden symptoms, or ask health-related urgent or semi-urgent questions such as "Where does it hurt?", "I don't feel well", "Which department should I visit?", "Do I need to go to the hospital?", or "Help me assess this". Also applies when users are doing an initial symptom screening for family or friends. Core capabilities: quickly narrow down possible causes through hypothesis-and-elimination interactive questioning, provide a ranked list of possible causes, recommend a department to register with, and suggest tests to undergo after arriving at the hospital. Helps users prepare information before seeking care and reduces communication overhead at the hospital.
Comprehensive financial audit tool for balance sheets and income statements. Use when Claude needs to verify balance sheet equilibrium, validate income statement items against detail records, track account changes with opening/closing balance reconciliation, verify cross-statement relationships, or generate audit reports with account analysis and transaction tracing.
Use when the user wants to write an email to an investor—cold outreach, a warm intro request, a follow-up after a meeting, a monthly investor update, or a thank-you note. Also activates for “intro email”, “investor email”, “follow up with VC”, or “investor update”
High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.
Manage Heihu Zhizao materials: query, view, create, import, or update material master data. Use when users handle material codes, names, specifications, business scopes, inventory attributes, or custom fields. Does not handle BOMs, physical inventory, or the full production launch process.
Shared execution rules for hhzz-cli: handles configuration, authentication, command discovery, permissions, write confirmation, result verification, unified business results, and error handling. Must be read before using any Heihu Zhizao business Skill. Does not replace specific business Skills or the CLI contract.
Manage Heihu Zhizao work orders: query work orders and their sources, outputs, materials, process plans, and dispatch information; import or dispatch work orders. Use when handling an individual production work order. Does not handle full new-product production launch, material readiness checks, or on-site production execution.
Expert guidance for Rails I18n (internationalization and localization). Use when working with translations, locale files, t() / l() helpers, lazy lookups, pluralization, interpolation, date/time/number formatting, model translations, error message translations, setting locale from URL/header/session, or organizing YAML translation files. Triggers on "i18n", "internationalization", "translation", "locale", "localize", "t()", "translate", "multilingual", "pluralization", "locale file", "YAML translation".
Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Guides framework and design system detection, builds the sendFeedback utility and feedback widget matching existing project patterns. Use when the user wants to add a Give Feedback widget, collect user sentiment tied to feature flags, set up feedback collection, or wire up the $ld:feedback tracking event
Query patent claim information from the Eureka patent database. This skill triggers when users mention patent claims, claims, patent Claims, independent claims, dependent claims, claim count, patent protection scope, patent claims, claim data, independent claims, dependent claims, claim count, patent claim text, patent protection scope, or Eureka patent claims. Trigger it even if the user does not explicitly mention “Eureka” or “claims,” as long as they need the full text or number of a patent's claims.
Expert guidance for using Lucide icons in Rails applications via the lucide-rails gem. Use when adding icons, choosing icon names, styling SVG icons, making icons accessible, or building icon-based UI patterns (buttons, nav, badges, empty states). Triggers on "lucide", "icon", "lucide-rails", "SVG icon", "icon library", "lucide_icon", "feather icon", "inline SVG", "add an icon", "icon button", "icon name".
Conducts comprehensive Magento 2 security assessments and implements security measures. Use when auditing security, identifying vulnerabilities, implementing security controls, or ensuring compliance. Masters security auditing, vulnerability management, and compliance frameworks
Security review of MCP (Model Context Protocol) server implementations and configurations. Use when auditing MCP server source code, evaluating third-party MCP servers before installation, or reviewing Claude Code MCP integrations for overpermissioning, injection risks, and data exposure.
Use when you want to expose an n8n workflow as a tool the coding agent can call. Two cases. (1) Wrap n8n API capabilities the MCP doesn''t natively expose: folder CRUD, tag rename/delete, instance metadata, credential creation. (2) Expose a general-purpose workflow as an agent tool: a workflow that calls a third-party API, runs business logic, or does any task you want the agent to invoke. Triggers on "expose as MCP tool", "build a tool for my agent", "I need to know X" where X isn''t an MCP tool, "create folder", "rename tag", or any capability gap.
Use before any bulk edit, migration, standardization, or redesign—including splitting a large file or module and refactoring for agents or readability—before adding a guard, linter, hook, or constraint against a class of bugs, and before retrying a fix for the same symptom. It checks the hypothesis, mechanism, scope, and applicable facts before implementation; the result is one recommended approach, its boundary, and a verifiable sign of success. Also use when a decision relies on an unverified cause, external fact, or metric. Do not use for choosing a product task, finding edge cases, or making a small agreed-upon change.
Use Obscura for lightweight headless browsing, web scraping, and CDP automation. Trigger when users mention Obscura, want a lighter Chrome replacement for AI agents, need `obscura fetch` or `obscura scrape` commands, want to run `obscura serve`, need Playwright or Puppeteer to connect to Obscura over Chrome DevTools Protocol, or need a safe local development workflow such as Vite plus hostc plus Obscura because localhost is blocked by Obscura's SSRF protections
Design value propositions for candidate customer segments and help the user choose the strongest one. Use when Codex needs to explain jobs, pains, and gains when needed, check niche-positioning prerequisites, ask one question at a time, present multiple value-proposition options, and write user-confirmed outputs into `opc-doc/`.
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.