Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guidance for Microsoft Entra External ID — the unified customer identity and access management (CIAM) and external collaboration platform that replaces Azure AD B2C (for new tenants) and consolidates B2B guest scenarios. Covers external tenant creation, user flows (sign-up/sign-in, password reset), custom branding, identity providers (Google, Facebook, Apple, SAML/OIDC), email OTP and passkey support, custom attributes, custom authentication extensions (replaces B2C custom policies), API connectors, Conditional Access for external users, self-service sign-up in workforce tenants, B2B collaboration vs B2B direct connect, cross-tenant access settings, and migration considerations from Azure AD B2C. WHEN: Entra External ID, CIAM Microsoft, customer identity, replace Azure AD B2C, B2B guest user, B2B direct connect, cross-tenant access settings, external tenant, self-service sign-up, custom authentication extension, social identity provider, partner collaboration Entra, external user lifecycle, guest user expiration. DO NOT USE for workforce identity (use entra-id), workforce governance (use entra-id-governance), or workforce CA (use conditional-access-mfa).
Guidance for Microsoft Entra Verified ID — verifiable credentials issuance and verification platform based on open standards (W3C Verifiable Credentials, DIDs, OpenID4VC). Covers issuer setup (tenant configuration, DID registration, signing key in Key Vault), credential schema design, rules and display files, issuance flows (QR / deep link), verification flows, Face Check biometric matching, integration with Entra ID for workforce onboarding and access, integration with verification partners, and use cases (employee verification, remote onboarding, low-friction account recovery, vendor/contractor identity proofing). WHEN: Entra Verified ID, verifiable credentials, decentralized identity, DID issuance, issue credential Entra, verify credential, Face Check, remote onboarding identity proofing, account recovery with VC, contractor identity verification, vendor verification, workforce onboarding VC. DO NOT USE for B2C/CIAM (use entra-external-id), workforce identity admin (use entra-id), or PKI/certificate design (use pki-design).
Analyze a stack trace, crash report, panic, or error log; find the failing frame and the root cause; then propose a fix and a way to verify it. Covers Kotlin/JVM/Android (coroutines, ANRs, R8-obfuscated traces), KMP/Compose Multiplatform, Flutter/Dart (FlutterError, RenderFlex overflow), Swift on iOS/macOS (.ips reports, EXC_BAD_ACCESS), Rust panics, C++ segfaults and sanitizer output, plus Python, JS/TS, Go and Java. Use when someone pastes a stack trace, crash log or panic—even with no question attached—or says “why does this crash”, “what does this error mean”, “debug this exception”, “root-cause this trace”, “symbolicate this crash”, “deobfuscate this trace”, or the Hungarian “miért crashel”, “mit jelent ez a hiba”, “elemezd ezt a stack trace-t”, “nézd meg ezt a crash logot”. Not for auditing a whole project for latent bugs (that is code-analyzer), nor for a red CI run whose log has not been fetched yet (that is github-fix-ci-error).
Escreve PRDs (Product Requirements Documents) — cria novos ou edita existentes que ainda não foram concluídos. Funciona no modo draft-first: gera o documento completo imediatamente a partir do que o usuário fornecer, marcando premissas inferidas inline para revisão pontual — sem entrevistas longas. Quando o input cobre múltiplas features, detecta automaticamente e propõe divisão em PRDs separados, criando-os em sequência na mesma sessão. Cada PRD é autocontido e foca em comportamento e regras de negócio; detalhes técnicos ficam em TRD/ADR. Use quando o usuário quiser criar ou editar um PRD, documento de requisitos, especificação de feature, planejar uma funcionalidade, definir escopo de uma entrega, documentar requisitos, ou avaliar a quebra/granularidade de um PRD — mesmo que não use o termo "PRD" explicitamente. Também quando mencionar "requisitos do produto", "spec de feature", "escopo da feature", "documento de requisitos", "refinar PRD", "ajustar PRD", "quebra de PRD", "granularidade de PRD", ou fornecer uma descrição longa de funcionalidades para especificar.
Evaluates and improves gameplay balance from telemetry in any engine. Use when comparing monotonous vs exploratory play, diagnosing death/spawn/scoring/input issues, setting difficulty, timer, or pacing targets with human-limited simulated players, calibrating those players against a person's replays or run summaries across play sessions, or proposing structural balance fixes instead of numeric tuning
Propose a new UI pattern or modify an existing Design System component per Bitwarden's published governance process — design-team alignment, Core vs. Recipe/Snowflake decision with UI Foundation, Figma branching and property conventions, review gates, merge timing.
Methodology for attacking Microsoft Exchange mail servers. Use when an OWA (Outlook Web App) login page or Exchange admin panel is found, when Exchange is running on port 443, or when an Exchange server is discovered in the internal network. Use when a port scan finds 25/443/587/993/995 with an Exchange fingerprint. Covers OWA password spraying, ProxyLogon (CVE-2021-26855), ProxyShell (CVE-2021-34473), ProxyNotShell (CVE-2022-41040), mailbox search and export, GAL global address list extraction, and NTLM relay to Exchange. Exchange is one of the highest-value targets in domain penetration — you can obtain domain admin mailboxes, extract the address book of all staff, and gain SYSTEM privileges. Use this skill whenever /owa /ecp /autodiscover /mapi paths are found
(NS) Orchestrate partitioned version implementation slice-by-slice — dispatch one synchronous subagent per slice with small context, commit after each slice, and advance automatically without confirmation until all slices are done or a stop condition is hit. Use whenever a version has a version-roadmap.md with pending slices and the user asks to "run the orchestrated implementation", "execute all slices", "orchestrate the partitioned version", or drive a subversion roadmap to completion. Do NOT use for non-partitioned versions (execute tasks directly), ad-hoc coding (code-coder), or planning/partitioning (pm-version-partitioner).
Build a reporting or executive presentation where every slide title states a conclusion and the deck follows a pyramid, answer-first structure. Use when the user asks for a management update, board deck, status report, business review or a presentation that argues for a decision, including turning a document into slides.
Build FastAPI applications using Clean Architecture principles with proper layer separation (Domain, Infrastructure, API), dependency injection, repository pattern, and comprehensive testing. Use this skill when designing or implementing Python backend services that require maintainability, testability, and scalability.
Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool implementations.
This skill should be used when taking a single software feature from intent to shipped as a solo developer — goal-first, TDD, deterministic verification, evidence only where it earns its keep, and human judgment at the two moments that matter (goal approval, merge). Trigger when the user says "let's build feature X", "ship this feature", "run this through the factory", "write a goal contract", "feature-factory", or wants a disciplined intent→merge loop that resists process bloat. NOT for whole-product planning, multi-feature roadmaps, or autonomous multi-agent swarms.
Design and audit feature flags, staged rollouts, kill switches, targeting rules, exposure plans, holdouts, rollout gates, rollback paths, flag cleanup, and operational ownership for SaaS, apps, games, AI features, marketplaces, and desktop software. Use when releasing risky changes gradually or when a product needs safe experimentation, canaries, or emergency disablement.
Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.
Evaluate model predictions against ground truth using COCO, Open Images, or custom protocols. Use when computing mAP, precision, recall, confusion matrices, or analyzing TP/FP/FN examples for detection, classification, segmentation, or regression tasks.
This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies
AI script supervisor for continuity, dialogue tracking, script notes, scene analysis. Use when: tracking continuity, script supervision, dialogue notes, scene analysis, production reports. Keywords: film, script, continuity, dialogue, continuity.
Financial analysis and research workflows for market research, equity research, comparable companies, precedent transactions, and DCF valuation. Use when asked to build or critique DCF models, comps/precedents tables, competitor or strategy analysis, market sizing, or to deliver analyst-ready outputs in Excel, PowerPoint, or Markdown from CSV/Excel/SQL/API/web data.
Help developers use FineUI forms: Form / SimpleForm containers, form fields (TextBox / TextArea / NumberBox / DatePicker / DropDownList / CheckBox / RadioButtonList and more), the Calendar inline calendar, field-level and whole-form validation, and reading field values. Covers F.js (JavaScript), Pro (WebForms), FineUI.Core MVC (Fluent API) / RazorForms / RazorPages (TagHelper), plus FineUI.Java (Spring Boot + Thymeleaf dialect tags, kebab-case). Trigger phrases: "FineUI 表单", "F.Form", "SimpleForm", "FormRow", "表单校验", "ValidateForms", "Required", "TextBox", "NumberBox", "DatePicker", "DropDownList", "RadioButtonList", "CheckBox", "CheckBoxList", "TimePicker", "Label", "Hidden", "FileUpload", "TriggerBox", "DropDownBox", "HtmlEditor", "MarkInvalid", "字段标签", "LabelWidth", "读取表单值", "下拉树", "文件上传", "富文本编辑器", "Calendar", "内嵌日历", "日期范围", "月份选择", "年份选择", "时间选择", "OnDateSelect", "FineUI.Java", "Spring Boot", "Thymeleaf", "@FineUIPage", "text-box", "simple-form", "form-row".
Help developers use FineUI's Grid component, covering F.js (JavaScript), Pro (WebForms), FineUI.Core's MVC/RazorForms/RazorPages, and FineUI.Java (Spring Boot + Thymeleaf dialect tags). Use for table configuration, column definition and rendering, data loading and binding, cell editing, row selection (checkbox multi-select/single-select), paging, sorting, summary rows, header filtering, multiple headers, row grouping, tree tables, column locking, cell merging, row expansion/row command/row events, drag-and-drop sorting, big-data tables, and toolbars. Trigger phrases: "FineUI 表格", "F.Grid", "Grid 列", "grid columns", "FineUI.Java", "Spring Boot", "Thymeleaf", "@FineUIPage", "f:grid", "render-field", "data-field", "RenderField", "RenderCheckField", "复选框多选", "EnableCheckBoxSelect", "选中行", "SelectedRowIndexArray", "GetSelectedDataKeys", "getSelectedDataKeys", "RendererFunction", "RendererArgument", "列渲染", "服务端分页", "loadData", "DataKeyNames", "表格排序", "AllowSorting", "合计行", "EnableSummary", "SummaryType", "表头过滤", "AllowFilters", "EnableFilter", "多表头", "GroupField", "行分组", "EnableRowGroup", "树表格", "EnableTree", "TreeColumn", "列锁定", "AllowColumnLocking", "单元格合并", "mergeColumns", "行扩展列", "RowExpander", "行命令", "RowCommand", "行单击事件", "OnRowClick", "拖拽排序", "EnableColumnMove", "大数据表格", "EnableBigData".
Help developers use FineUI's layout system — how a container's `Layout` property arranges child controls: Fit (fill) / Region (top, bottom, left, right, center regions) / HBox·VBox (flexbox) / Block (responsive grid) / Column / Anchor, plus viewport adaptation (IsViewPort / AutoSizePanelID). Covers F.js, Pro, FineUI.Core (MVC/RazorForms/RazorPages), and FineUI.Java (Spring Boot + Thymeleaf dialect tags, kebab-case, including the region-panel convenience control). Trigger phrases: "FineUI 布局", "Layout", "Region 布局", "区域布局", "RegionPosition", "HBox", "VBox", "BoxFlex", "弹性布局", "Fit 布局", "Block 响应式", "BlockMD", "栅格布局", "IsViewPort", "视口自适应", "Column 布局", "Anchor 布局", "FineUI.Java", "Spring Boot", "Thymeleaf", "region-panel", "region-position", "box-flex", "is-view-port".
Set or switch FineUI's existing built-in and custom themes, handling global configuration, PageManager overrides, and Cookie preferences. Covers the F.js, Pro, and Core modes and Java. For adding new themes, brand colors, and theme.config generation tasks, use fineui-custom-theme.
Help developers use FineUI's Tree component: tree container and nodes (TreeNode), static/backend node building, data binding, node icons, checkbox tree (cascade, reading checked nodes), node events (click/expand), asynchronous lazy loading. Covers F.js (JavaScript), Pro (WebForms), FineUI.Core's MVC (Fluent API)/RazorForms/RazorPages (TagHelper), and FineUI.Java (Spring Boot + Thymeleaf dialect tags). Trigger phrases: "FineUI 树", "F.Tree", "TreeNode", "树节点", "树控件", "EnableCheckBox", "enable-check-box", "复选框树", "CascadeCheck", "cascade-check", "级联选中", "GetCheckedNodes", "getCheckedNodes", "懒加载", "OnNodeLazyLoad", "on-node-lazy-load", "异步加载子节点", "节点点击", "nodeclick", "OnNodeExpand", "on-node-expand", "FineUI.Java", "Spring Boot", "Thymeleaf", "@FineUIPage", "f:tree", "f:tree-node".
Upgrade existing FineUI projects to a higher major version (**v10 and above only**), identify breaking changes, generate a migration checklist, and apply it item by item. Applies to F.js (JavaScript), Pro (WebForms), and FineUI.Core's MVC/RazorForms/RazorPages. (FineUI.Java starts at v16.0 with no historical upgrade path; only its shared F.js client breaking changes apply, see below.) Trigger phrases: "FineUI 升级", "升级 FineUI", "FineUI upgrade", "升级到 v1x", "破坏性变更", "不兼容", "迁移 FineUI", "EncodeText", "raw 标签", "DateParseString". Use this skill when the user wants to upgrade FineUI from an older version to a newer one, or asks "will the upgrade have any incompatibilities?".
Help developers use FineUI windows and message boxes: Window (inline content / iframe popup), opening/closing windows, iframe child page passing data back to the parent page (closeArgument), and MessageBox (Alert dialog / Confirm dialog / Notify box). Covers F.js (JavaScript), Pro (WebForms), FineUI.Core's MVC (Fluent API)/RazorForms/RazorPages (TagHelper), and FineUI.Java (Spring Boot + Thymeleaf dialect tags, kebab-case). Trigger phrases: "FineUI 窗口", "F.Window", "弹窗", "对话框", "MessageBox", "Alert.Show", "F.alert", "F.confirm", "确认框", "通知框", "Notify", "ShowNotify", "iframe 窗口", "关闭窗口", "回传数据", "closeArgument", "GetShowReference", "OnClose", "FineUI.Java", "Spring Boot", "Thymeleaf", "@FineUIPage", "f:window", "showAlert", "showNotify", "showConfirm", "ActiveWindow", "setHidden".
Control the user's Firefox from a terminal. Use when your task needs the user's browser or authenticated session, page navigation, tab/window control, screenshots, DOM reads, waits, or page interactions in Firefox. Do not use it as a web search replacement.
Builds NUI interfaces for FiveM using React 18 + TypeScript + Vite + Tailwind CSS v3 + Zustand. Use when the user mentions NUI, interface, UI, menu, HUD, panel, overlay, React, Vite, Tailwind, or any in-game interface for FiveM — regardless of the backend framework (vRP, QBCore, Qbox, ESX). Covers project structure, FiveM CEF restrictions, observe/Post hooks, VisibilityProvider, animations, dynamic config/theme, and performance rules.
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.
