Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g. adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Add 3D models (.glb/.gltf) to a Decentraland scene using GltfContainer — 8,800+ free assets from the OpenDCL catalog and Creator Hub asset packs (Genesis City, Halloween, Sci-fi, Fantasy, Smart Items; the latest additions are catalogued offline), plus authoring and editing custom models by driving Blender (headless CLI or Blender MCP). Use when the user wants to add models, import GLB files, find free 3D assets, set up model colliders, or create/edit/retexture/optimize a model in Blender — also whenever an `mcp__blender__*` tool is available and the task involves 3D models. Do NOT use for SDK materials/textures (see advanced-rendering), model animations (see animations-tweens), or avatar emotes (see avatar-animations).
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. Trigger when the user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. Do not trigger for Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work unrelated to Agent Script, or when the primary input is a production session or trace ID rather than an agent artifact.
Core consulting thinking frameworks and methodologies for structuring business problems, communicating findings, analyzing strategy, building financial models, and designing operations. Use when any agent or command needs to apply MECE decomposition, pyramid principle, hypothesis-driven analysis, issue trees, SCR communication, Porter's Five Forces, TAM/SAM/SOM market sizing, value chain analysis, NPV/IRR decision criteria, build/buy/partner evaluation, RACI matrices, synergy sizing, valuation triangulation, price-volume-mix decomposition, discount waterfalls, or any standard consulting framework. This skill provides procedural guidance — not just framework names, but how to apply them correctly.
Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke to create REST endpoints, define Pydantic models, implement authentication flows, set up async SQLAlchemy database operations, add JWT authentication, build WebSocket endpoints, or generate OpenAPI documentation. Trigger terms: FastAPI, Pydantic, async Python, Python API, REST API Python, SQLAlchemy async, JWT authentication, OpenAPI, Swagger Python.
Use this skill when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
Use ONLY for auditing executed-task counts or batching/hoisting costs within ONE MSBuild invocation: per-project Exec, duplicate dependency builds, per-item generators, run-once races. NEVER load for evaluation-only global-property variants with once-only target/task execution, idle-node/serial-chain investigations, second/unchanged builds, restores across commands, required-variant bin/obj collisions or unranked slowness. Do not load to check scope or replace an unavailable specialist; answer directly.
A-share financial data toolkit. Provides scripts to retrieve real-time A-share market quotes, financial indicators, share purchases and sales by directors, supervisors, and senior executives, northbound capital flows, and macroeconomic data (LPR, CPI/PPI, PMI, aggregate financing, M2). Use when investment analysis requires real-time A-share market data. All data sources are free; no API key is required.
Temu US product listing (Add Product) API, routed through the LinkFox gateway to the Partner US product interface: V2 listing (temu.local.goods.v2.add), category attributes, specifications, image uploads, product lists/details/edits, category mapping, SKU inventory, supply prices, and more. Trigger when the user mentions Temu US product listing, Temu US Add Product, goods.list, goods.detail, temu.local.goods.v2.add, product category mapping, SKU inventory, supply prices, or Partner US product listing documentation. Use another Temu skill for orders and logistics.
Use when the user asks to recognize invoices, bills, receipts, tickets, or other voucher files with Make Integration services. Also triggered by requests like "发票内容", "识别发票", "票据 OCR", "ocr 这张图片", or "验真发票". Does not manage Make resources (use makecli), design DSL schemas (makedsl), build UI (makeui), implement auth (make-app-auth), Service/API code (make-app-service), runtime packaging (make-app-runtime), or perform non-Make OCR outside makecli integration commands.
Analyzes Move language packages against the official Move Book Code Quality Checklist. Use this skill when reviewing Move code, checking Move 2024 Edition compliance, or analyzing Move packages for best practices. Activates automatically when working with .move files or Move.toml manifests.
Serverless (peer-to-peer) multiplayer in Decentraland with CRDT syncEntity and MessageBus. Use when the user wants synced entities, shared world state, broadcast events, player-to-player communication without a server, or to test a scene with two local players. For server-authoritative state, anti-cheat or persistence see authoritative-server.
Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑". Do NOT use for diagrams (架构图/流程图/时序图) — draw those with Mermaid or code instead.
Analyze private placement and exempt offering compliance under Regulation D, the Investment Company Act fund exclusions, and FINRA private placement rules. Owns the accredited investor definition (Rule 501(a)), the '506(b) vs 506(c)' distinction, 'general solicitation' analysis, 'Form D' filing mechanics, the 'qualified purchaser' standard for 3(c)(7) funds, bad-actor disqualification, integration, and Rule 144 resale restrictions. Use when the user asks 'can my client invest in this private fund', whether an investor is an 'accredited investor' or qualified purchaser, how to verify accredited status in a 'Reg D offering', 506(c) verification steps, FINRA 5122/5123 filing obligations, or the Reg BI/fiduciary overlay when recommending private placements. Also trigger on 'exempt offering', 'private fund exemption', '3(c)(1) vs 3(c)(7)', or 'restricted securities holding period'.
Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.
Implements rate limiting and abuse prevention with per-route policies, IP/user-based limits, sliding windows, safe error responses, and observability. Use when adding "rate limiting", "API protection", "abuse prevention", or "DDoS protection".
RISC-V privileged architecture skill for M/S/U modes and traps. Use when handling CSRs, trap handlers, PLIC/CLINT interrupts, OpenSBI integration, page tables Sv39/Sv48, or QEMU virt testing. Activates on queries about RISC-V privileged, mstatus, mtvec, satp, OpenSBI, PLIC, or Sv39.
Record errors, corrections, capability gaps, and best practices to form a reusable continuous-improvement loop. Use when commands fail, users make corrections, external APIs or tools malfunction, a better approach is discovered, new capability needs arise, or historical experience should be reviewed before a task.
A Chinese-language tool for creating feature specifications, converting natural-language feature descriptions into structured specification documents. Supports automatic branch name generation, Git branch creation, specification file initialization, and quality validation. Trigger phrases include: “speckit规范,” “功能规范,” “创建规范,” “功能描述转换,” and “speckit-specify.” Use this skill when users need to turn feature ideas into structured specifications.
Create organized, visual study notes with folder structures, diagrams, and example-based learning from source materials (PDFs, lecture notes, documentation). Use when creating structured learning materials, exam preparation notes, or educational documentation. Triggers - organize study notes, create visual learning materials, generate notes with diagrams, exam prep notes, example-based learning.
Implement Syncfusion Angular Chart component for professional data visualization. Use this when creating or customizing charts such as line, bar, column, area, pie, financial (candlestick, OHLC), scatter, bubble, or stock charts. Supports axes configuration, series binding, legends, tooltips, zooming, real-time updates, technical indicators, themes, export, and accessibility features.
Mechanics library for running AI coding CLIs as managed tmux workers via agent-tmux <cli> <command> (plus tmux-agent-sessions and the other bundled tools). Entry point is the using-tmux-agent-tools router skill — route through it first; read this skill for wrapper mechanics it defers to. Covers start/send-wait/status/result/stop, structured result.json completion, multi-worker watch, profiles for custom CLIs, and bounded dialogue/fanout. Not for general tmux config, theming, non-tmux headless CLI use, or human team debate.
Generate a design document (design proposal) from a PRD, in the style of Go's official design proposals — Abstract / Background / Design / Rationale / Compatibility / Implementation, with an emphasis on the “why” and tradeoffs. Triggers on: to-design, prd-to-design, prd转设计文档, 生成设计文档, 写设计文档, design doc, design proposal, 设计提案, 技术设计文档.
Triton language skill for Python GPU kernel authoring. Use when writing Triton kernels with @triton.jit, tl.load/store, masking, and atomics; benchmarking with triton.testing; or integrating kernels into PyTorch. Activates on queries about Triton, tl.constexpr, block pointers, Triton benchmarking, or PyTorch custom ops.
Refine: full script drafting and revision. Turn the user's material or reference ideas into a complete word-for-word script ready to read aloud, or revise existing scripts and AI drafts. Borrow ideas based on what the user wants to express without copying someone else's structure. Use when the user needs a complete spoken script, wants a draft revised, or wants to make someone else's viral hit their own.
Select material: find benchmarks and analyze viral hits. The alchemy furnace's raw-material stage: find benchmarks based on the user's criteria, break down a viral hit to see why it succeeded, then test whether it fits the user through the repetition, customer, and substitution gates. Decide which mechanism to borrow, what to replace, and which of the user's experiences can carry it. Also helps decide which AI tool to use. Use when the user sees a viral hit and wants to adapt it, is looking for benchmarks, or doesn't know whom to learn from.
Integrate Vercel Blob for file uploads and CDN-delivered assets in Next.js. Supports client-side uploads with presigned URLs and multipart transfers for large files. Use when implementing file uploads (images, PDFs, videos) or troubleshooting missing tokens, size limits, client upload failures, token expiration errors, or browser compatibility issues. Prevents 16 documented errors.
Design and build the visual layer of a long-form talking-head video as one persistent world the camera moves through, instead of a sequence of separate graphics. Use when asked to edit a video, add motion graphics, design the visuals for a script, plan an edit, or fix an edit judged confusing, text-heavy, hard to follow, or "clearly made by an AI". Covers the persistent world, camera grammar, the spotlight rule, spatial open loops, ornament and token discipline, transcript timing, and the verification gates.
Writing release note articles for tldraw SDK releases. Use when creating new release documentation, drafting release notes from scratch, or reviewing release note quality. Provides guidance on structure, voice, and content for release files in `apps/docs/content/releases/`.
Routes Maven version questions to the right workflow by choosing project-local update report interpretation for a user’s own pom.xml, or Maven artifact discovery from maintainer-approved structured evidence. Use when interpreting dependency, plugin, or property update reports; finding Maven coordinates; verifying groupId artifactId version; browsing versions from approved evidence; or constructing artifact URLs without fetching remote content. Part of Plinth Toolkit
Use when you need to write fast unit tests for Quarkus applications — including pure tests with @ExtendWith(MockitoExtension.class), @QuarkusTest with @InjectMock for full CDI mock replacement, @InjectSpy for partial CDI bean mocking, REST Assured for resource-focused tests, @ParameterizedTest with @CsvSource / @MethodSource, QuarkusTestProfile for test-specific configuration overrides, and naming conventions (*Test → Surefire, *IT → Failsafe). For framework-agnostic Java use @131-java-testing-unit-testing. This should trigger for requests such as Add or improve unit tests in a Quarkus project; Reduce slow @QuarkusTest usage with Mockito-first tests; Add @InjectSpy partial mocking or QuarkusTestProfile configuration in Quarkus tests; Convert repeated test methods to @ParameterizedTest with @CsvSource or @MethodSource; Write fast pure unit tests for Quarkus services. Part of Plinth Toolkit
Route ambiguous product, document, or Agentic work to the right design or implementation skill. Use for unresolved owner/project shape, mixed specialties or explicit low-frequency TaskDAG or DynamicTask requests. Clear tasks use their specialist directly; conversation expression, progress and handoffs use agently-collaboration alongside any task.
Generate optimized Apple App Store metadata recommendations with ASO best practices. Use this skill when analyzing app listings, optimizing metadata (title, subtitle, description, keywords), performing competitive analysis, or validating App Store listing requirements. Triggers on queries about App Store optimization, metadata review, or screenshot strategy.
Read real-time amplitude and 8-band frequency data from any AudioSource, AudioStream, or VideoPlayer entity in a Decentraland SDK7 scene with the AudioAnalysis component. Use when the user asks for music visualizers, beat reactivity, equalizers, or audio-reactive scenes. To play sound see audio-video.
Expert knowledge for Azure Key Vault development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when using Key Vault/Managed HSM with Private Link, Entra ID RBAC, BYOK/HSM keys, Event Grid, or Terraform, and for other Azure Key Vault development tasks. Not for Azure Cloud Hsm (use azure-cloud-hsm), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Attestation (use azure-attestation), or Azure Information Protection (use azure-information-protection).
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.