Catalogue de skills·2424 skills
Tous les skills
Des skills prêts à l'emploi — copie le Markdown du skill et colle-le dans ton agent.
Compatible avec
Liste des skills du catalogue Arboris
2424 skills sur 2424
Skill
Description
Agents
Copier le skill
What To Use When (Microsoft)Données & Recherche100Run this FIRST, before ANY thinking, retrieval, task creation, or file generation, for any single-output task a free M365 Copilot can do; if action-bias pushes you to start, STOP and run this first. Fires on: "summarize my email/inbox/unread", "summarize my meetings", "summarize my Teams messages" (any window, e.g. "last 5 weeks"); "catch me up" / "what did I miss"; a single question or lookup: "how do I", "why", "when is", "what is", "who is", "are we", "do we", "is it", any billing/pricing/licensing question, calendar/contact lookups; "draft a doc" or memo; "create a presentation", deck, or spreadsheet; "research competitors"; "analyze this data". GUIDE the user to the matching free 1P agent (Copilot Chat; Word/Excel/PowerPoint; Researcher; Analyst), not Cowork; use it only if they insist. Do NOT fire for DIRECT ACTIONS (send email, schedule a meeting, post to Teams, create an event), long-running or multi-output jobs, or managing skills.
Whiteboard To Infographic (Microsoft)Infra, Ops & Workflow100Convert a hand-drawn whiteboard photo (or sketched process/diagram) from a discovery or working session into a polished, client-ready infographic as an editable PowerPoint slide (.pptx). Use this whenever someone uploads or references a photo of a whiteboard, a hand sketch of a process or system, or session-capture notes and wants it "cleaned up", "made presentable", "turned into a diagram/infographic", "converted for the client", or similar — even if they don't say the word "infographic". Covers two layout archetypes — linear process flows (left-to-right step rails) and network/topology maps (locations, systems, or actors connected by labeled flows). Built for consulting/ERP discovery capture but works for any whiteboard-to-deliverable conversion. Do NOT use for charts/graphs from numeric data, for editing an existing polished design, or for generating diagrams with no source sketch.
Wikipedia Human Style Writing (Microsoft)Docs & Écriture100Use this skill whenever the user asks to write, rewrite, humanise, de-AI, or polish prose so it doesn't read as AI-generated — or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.
Win Loss Overview (Microsoft)Agents & Orchestration100Compare the bundled synthetic Q3 and Q2 win/loss patterns.
Winforms Feature Adoption (Microsoft)Agents & Orchestration100Adopts modern WinForms features in .NET 8+ applications including dark mode (Application.SetColorMode, SystemColors), async APIs (Control.InvokeAsync, Form.ShowDialogAsync, TaskDialog.ShowDialogAsync), and MVVM patterns (ViewModels, INotifyPropertyChanged, Commands, DataContext). Use when user requests "modernize WinForms", "add dark mode to WinForms", "implement WinForms MVVM", "add async to WinForms", "use InvokeAsync", "adopt modern WinForms features", or as a post-upgrade enhancement after dotnet-version-upgrade scenario completes. Also triggers for "Application.SetColorMode", "WinForms dark theme", "WinForms async patterns", "WinForms MVVM architecture", "modernize WinForms UI", and "enhance WinForms application". Prerequisite: projects must already target .NET 8+ (dark mode and async require .NET 9+).
With Tanstack Query (TanStack) — Angular TableFrontend & UI100
Compose Angular Query with signal-owned Table filtering, sorting, and pagination state using reactive query options, manual row-model boundaries, direct query data, server counts, and valid injection context.
With Tanstack Query (TanStack) — Preact TableFrontend & UI100
Compose native Preact Table v9 with @tanstack/preact-query using table state in query keys, manual server filtering/sorting/pagination, server counts, and stable query-result data. Load when React Query examples or manual* expectations are wrong for Preact.
With Tanstack Query (TanStack) — React TableFrontend & UI100
Compose React Table v9 with TanStack Query for server filtering, sorting, pagination, and infinite data. Load for query-key table state, manual* processing boundaries, server rowCount, keepPreviousData, or avoiding duplicated query-result state.
With Tanstack Query (TanStack) — Solid TableFrontend & UI100
Compose Solid Query reactive options with Solid Table manual server processing. Load for tracked query-key signals, query result getters, server row counts, keepPreviousData, and avoiding React Query patterns or duplicated data state.
With Tanstack Query (TanStack) — Svelte TableAgents & Orchestration100
Compose Svelte Query with Svelte Table manual filtering, sorting, and pagination using reactive query inputs, query-result data getters, server counts, and a single source of server-data truth.
With Tanstack Query (TanStack) — Vue TableFrontend & UI100
Compose reactive Vue Query keys and results with Vue Table manual row processing, refs/computed state, server counts, and already-processed pages without duplicating query data into a drifting local ref.
With Tanstack Virtual (TanStack) — Angular TableFrontend & UI100
Virtualize Angular Table final row or column models inside the correct injection and reactive lifecycle with signal counts, scroll elements, keys, measurement, transforms, sticky regions, grid/flex sizing, and infinite data.
With Tanstack Virtual (TanStack) — Lit TableAgents & Orchestration100
Virtualize Lit Table final row or column models with @tanstack/lit-virtual VirtualizerController, host lifecycle-aware counts, scroll refs, stable keys, dynamic measurement, sticky CSS, grid/flex sizing, and infinite data. Load for large rendered tables; Virtual is renderer composition, not tableFeatures.
With Tanstack Virtual (TanStack) — Preact TableFrontend & UI100
Apply TanStack Virtual rendering to the final Preact Table row or column model through React compatibility or virtual-core. Load for adapter selection, reactive counts, scroll targets, stable keys, measurements, spacer geometry, sticky layout, sizing CSS, or overscan.
With Tanstack Virtual (TanStack) — React TableFrontend & UI100
Virtualize final React Table row or column models with TanStack Virtual. Load for useVirtualizer counts, scroll elements, stable keys, data-index measurement, dynamic heights, sticky headers/columns, grid/flex geometry, or infinite fetching; Virtual is renderer composition, not a Table feature.
With Tanstack Virtual (TanStack) — Solid TableAgents & Orchestration100
Virtualize Solid Table row/column models and infinite Query data with createVirtualizer, reactive counts, scroll targets, stable keys, dynamic measurement, transforms, sticky regions, and grid/flex sizing. Load for Solid tracking or layout bugs.
With Tanstack Virtual (TanStack) — Svelte TableAgents & Orchestration100
Virtualize Svelte Table final row or column models with reactive counts and scroll targets, stable keys, dynamic measurement, absolute transforms, sticky regions, grid/flex sizing, and infinite data.
With Tanstack Virtual (TanStack) — Vue TableFrontend & UI100
Virtualize Vue Table final row or column models with reactive counts and scroll targets, stable keys, measurement, spacer geometry, sticky CSS, grid/flex widths, and infinite server data.
Work On Issue (Hugging Face)Tests100Start work on a GitHub issue. Extracts requirements, creates worktree, sets up TDD workflow.
Workflow (Ansible)Agents & Orchestration100
Get workflow guidance for spec-driven development. Use when unsure what to do next, "help me get started", "what should I work on", "I'm stuck", or starting a new session. Do NOT use for directly creating artifacts (this skill guides you to the right skill for that).
Workforce Plan (Microsoft)Agents & Orchestration100Models fictional upskilling and internal-innovation pathways.
Workspace Surface AuditInfra, Ops & Workflow100Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
Write Architecture Docs (Prisma) — ContribDocs & Écriture100
Write or rewrite architecture subsystem docs, ADRs, and reference material for the engineering team. Use when creating, updating, or reviewing docs under docs/architecture docs/, or when the user asks you to write documentation that describes the system's design.
Write Architecture Docs (Prisma) — Contrib 2Frontend & UI100
Write or rewrite architecture subsystem docs, ADRs, and reference material for the engineering team. Use when creating, updating, or reviewing docs under docs/architecture docs/, or when the user asks you to write documentation that describes the system's design.
Write Tests (Hugging Face)Agents & Orchestration100Write failing tests from requirements. Invoke for each todo before /implement.
Write UI Tests (.NET)Infra, Ops & Workflow100
Creates UI tests for a GitHub issue and verifies they reproduce the bug. Iterates until tests actually fail (proving they catch the issue). Use when PR lacks tests or tests need to be created for an issue.
Write Xaml Tests (.NET)Infra, Ops & Workflow100
Creates XAML unit tests for GitHub issues in the Controls.Xaml.UnitTests project. Tests XAML parsing, compilation (XamlC), and source generation. Use when testing XAML-specific behavior, not UI interactions.
Writing Migration Guides (Supabase)Docs & Écriture100
Use when a change is a breaking change — a `fix!:`/`feat!:` commit, a `BREAKING CHANGE:` footer, or any edit that changes a public API's shape or behavior — and needs an entry in the root `V<N>_MIGRATION.md` file. Also use when reviewing a PR that has one, to check it against this format.
Writing Mstest Tests (.NET)Tests100
ALWAYS USE when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for "review" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected/actual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext/lifecycle; timeout/cancellation; OS/CI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest/non-.NET code.
Ws Ckpt (Alibaba)Agents & Orchestration100
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint，仅限 Linux; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"对比快照"、"快照改了什么"时 diff; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。
Xquic PR Formatting (Alibaba)Agents & Orchestration100
Format, create, and update concise XQUIC pull request bodies and review-state transitions. Use when asked to prepare or edit an alibaba/xquic PR body, create a draft PR from an already-pushed branch, update a PR after code changes pushed a new head, or move a validated draft toward review.
Xquic PR Pre Review (Alibaba)Agents & Orchestration100
Fail closed on published draft XQUIC code pull requests before ready-for-review state. Use when asked to pre-review a code PR or move it out of draft; verify current base-to-head code, protocol conformance, validation coverage, adversarial bad cases, hot-path performance, and memory safety in a five-part local report.
Xquic Safe Push (Alibaba)Agents & Orchestration100
Safely stage, commit, and push XQUIC changes after scoped Git checks. Use when asked to stage, commit, push, publish a branch to a fork, or verify that only intended files will be sent to a remote.
Yunt Docker ComposeInfra, Ops & Workflow100Docker Compose (Yunt Academy) : compose.yaml, services, depends_on/healthcheck, volumes/réseaux de projet, variables d’environnement, commandes up/down/logs et debug multi-conteneurs. À utiliser pour orchestrer une app locale multi-services.
Remix (TanStack)Agents & Orchestration98
Build and review Remix 3 applications using the `remix` npm package and subpath imports. Use when working on Remix app structure, routes, controllers, middleware, validation, data access, auth, sessions, file uploads, server setup, UI components, hydration, HMR, navigation, or tests.
Algorithmic ArtAgents & Orchestration97
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Brand GuidelinesFrontend & UI97
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Browserbase BrowserTests97
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.
Chart Builder (Microsoft)Docs & Écriture97Use this skill whenever the user asks to visualize, chart, plot, or graph data (bar, line, scatter, histogram, pie) from a CSV, table, or DataFrame. It gives the agent prebuilt, parameterized matplotlib functions so charts are produced faster and more reliably — with consistent styling and sane defaults — instead of hand-writing matplotlib each time.