Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build Next.js 16 + React 19 + TinaCMS sites with visual editing, blocks-based page builder, and complete SEO. Use this skill whenever the user mentions TinaCMS, Tina CMS, Next.js with a CMS, visual editing with Next.js, click-to-edit, content-managed Next.js site, blocks pattern page builder, or migrating to Next.js + TinaCMS. Also trigger for TinaCMS schema design, self-hosted TinaCMS, TinaCMS media configuration, or any TinaCMS troubleshooting. Covers Day 0-2 setup from scaffolding through production deployment on Vercel.
Create, modify, validate, and export NixieFX particle-effect projects for the public editor and runtimes. Use when an agent needs to locate or initialize vfx-editor.prj, create an effect with the nixie-fx CLI, edit effect JSON, organize textures materials or meshes, diagnose validation and backend-support reports, export out/vfx, or prepare an effect for visual review in the NixieFX editor.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Add a pass-through path in the graphic_2d repository of an Openharmony project. Call this capability when the user wants to add an RSInterface interface in the graphic_2d repository and indicates that the interface is ToSerivce.
Build Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. Integration-only layer — describes when and how to compose OKX tools with Helius tools for swaps, token discovery, smart money signals, meme token analysis, and portfolio intelligence.
'Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.
Build on Bitcoin Layer 1 with OP_NET - Bitcoin L1 consensus layer for trustless smart contracts. Use when building AssemblyScript smart contracts, TypeScript libraries, React frontends, or Node plugins for OPNet. Triggers on Bitcoin smart contract development, OP20 tokens, OP721 NFTs, WebAssembly contracts, verify-dont-custody patterns, epoch mining, and OPNet architecture questions.
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
Shared optimization guidance plus CuTe Python DSL overlays. Use when: (1) selecting optimizations for a CuTe Python DSL kernel, (2) deciding whether a finding is shared or cute-dsl-specific, (3) recording CuTe Python DSL implementation notes, (4) reviewing the knowledge layout for cute-dsl work, (5) mapping shared patterns to a CuTe Python DSL implementation surface.
Shared optimization guidance plus cuTile Python DSL-specific overlays. Use when: (1) selecting optimizations for a cuTile Python DSL kernel, (2) checking cuTile-specific implementation traps, (3) deciding whether a profiling finding belongs in shared knowledge or a cuTile overlay, (4) updating cuTile Python DSL optimization docs, (5) reviewing how a shared pattern maps to cuTile.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Full optimization workflow, sub-agent launch templates, agent communication contracts, default configurations, tuning strategy, and knowledge base update protocol. Use when: (1) starting an optimization cycle, (2) launching a Profiler or Designer sub-agent, (3) interpreting or formatting agent communication, (4) updating the knowledge base after a profiling or implementation iteration, (5) deciding default configurations or tuning strategy for a kernel.
Generates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas, Pydantic models, regex, choice lists, and integer/float types, on Transformers, llama.cpp, vLLM, and limited OpenAI backends. Use when you need output that always parses as valid JSON or matches a regex. Use when extracting typed data into Pydantic models from a local model. Use when classifying text into a fixed set of categories. Use when running batch structured generation on vLLM or Transformers. Use when controlling token sampling at the grammar level. Not for API models needing automatic retries (use Instructor).
Oxylabs proxy networks: Residential, Mobile, shared Datacenter/ISP, and Dedicated Datacenter/ISP proxies with geo-targeting, IP rotation, session persistence, and port-based sticky IPs. Use when routing traffic through proxies, building scrapers with proxy auth, rotating or sticky sessions, whitelisting IPs, or accessing geo-restricted content.
Conduct reviewer-style, evidence-safe reviews of academic manuscripts across disciplines using progressive method, domain, review-round, and optional reviewer overlays. Use when the user asks for a critique, scientific review, priority comments, top-to-bottom review, revision-round assessment, prior-comment regression check, or review memo rather than ordinary drafting. Infer the smallest applicable module set from the conversation and manuscript; ask only when unresolved domain or review-profile ambiguity would materially change the review. Includes optional psychometrics and SEM, computational and LLM, water and CNHS, flood and hydrodynamics, and explicit Ethan-style modules.
Generate professional slide deck images from academic papers and content. Creates comprehensive outlines with style instructions, auto-detects figures from PDFs, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", or "slide deck" for papers.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use when the user wants Claude Code, Codex, or other AI coding/business agents to work together as peers. This skill should be used whenever the user mentions coordinating Claude Code and Codex, agent handoffs, multi-agent workflows, parity, respect, pushback between agents, deciding which agent should lead, or turning a business/code workflow into a two-agent operating model.
Performs a security-focused code review by launching multiple specialized agents and a verification agent to ensure comprehensive coverage and accurate findings. Use this skill when the user asks for a "perform-security-review", "bitwarden-security-review", "execute a security review", "run a comprehensive security audit", "perform an end-to-end security assessment", or needs to coordinate multiple security checks across code, dependencies, secrets, and configurations. The skill manages the workflow, delegates tasks to specialized agents, and presents final findings to the user.
SSRF audit tool for PHP web source code. Identifies user-controllable URLs/addresses reaching network request sinks, traces intranet/protocol/port restrictions and echo, and outputs exploitability ratings, PoCs, and remediation advice (omission not allowed).
Adds or modifies a camera backend under physicalai.capture. Use when implementing a new Camera type, extending create_camera in src/physicalai/capture/factory.py, discovery helpers, optional pip extras for vendor SDKs, SharedCamera transport, or tests under tests/unit/capture with fake devices.
Configures preprocessors, postprocessors, and runners around InferenceModel via manifest specs and ComponentRegistry. Use when editing physicalai.inference.preprocessors or postprocessors, manifest preprocessor/postprocessor lists, instantiate_component, registered type names, or class_path init_args for inference pipeline components.
Loads and validates policies exported from Physical AI Studio for Runtime deployment. Use when working on InferenceModel, InferenceModel.from_pretrained, manifest.json, adapter auto-detection (onnx, openvino), backend/device kwargs, Hugging Face Hub policy packages, or the Runtime side of the export/load contract that Studio produces with physicalai export.
Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics. Use when running physicalai benchmark, editing configs under library/configs/benchmark, adding or changing a Benchmark class in physicalai.benchmark, tuning rollout/episode/env settings, recording rollout videos, or interpreting results.json / results.csv.
Exports and validates Physical AI Studio policies for Runtime deployment. Use when working on policy.export(...), the physicalai export CLI, the ONNX/OpenVINO/Torch/ExecuTorch backends, export metadata, numerical parity checks, or the Studio side of the export/load contract that Runtime consumes with InferenceModel(...).
Works with Physical AI Studio datasets and Lightning datamodules built on the LeRobot format. Use when wiring physicalai.data.lerobot.LeRobotDataModule into a training config, choosing a repo_id, converting between the physicalai and lerobot data layouts, defining observation Features/FeatureType, setting normalization, or debugging batch shapes and dataloading.
Use this skill to pick the right test double — fake, mock, stub, spy, dummy, or Robolectric shadow — for an Android test. Encodes Google's verbatim preference order ("fakes ... are preferred", "Fakes are preferred over stubs for simplicity", "Fakes or mocks are therefore preferred over spies"), gives Android examples (in-memory `FakeUserRepository`, `mockk<UserRepository>()`, `ShadowSystemClock`), and a decision matrix mapping intent to the correct double. Use when the user asks "fake or mock", "should I use Mockito here", "how do I replace this dependency in tests", "what's the difference between a stub and a mock", "spy vs mock", or mentions `mockk`, `every { } returns`, `verify { }`, `org.mockito`, `argumentCaptor`, `Robolectric` shadows, `ShadowSystemClock`, or `FakeRepository`.
Use when: a requirement change occurs during a project, the change's impact scope and risks need assessing, or change history needs recording. Do NOT use when: the change is trivial and needs no formal assessment, or a clear decision on the change already exists and no analysis is needed
Use when: a technical plan is finalized and involves multi-department collaboration, collaboration processes and role assignments need clarifying, or cross-team communication is difficult. Do NOT use when: a single team completes the work independently, or the collaboration relationships are already clear and need no mapping
Use when: you need to design product data metrics, plan data tracking, build a data monitoring system, or perform data analysis and trend forecasting. Do NOT use when: the data metrics are already clear, or only simple statistics are needed without a metric system.
Use when: managing multiple product lines and needing portfolio decisions, BCG matrix analysis, product lifecycle assessment, or resource allocation. Do NOT use when: there is a single product with no portfolio management needs, or the product lines are fixed and need no adjustment
Use when: preparing for launch after risk control is complete, needing a launch checklist and rollback plan, or running the formal release process. Do NOT use when: the launch process is already standardized and automated by operations, or a simple release needs no checklist
Use when: allocating R&D resources across multiple products, performing ROI assessments, resolving resource conflicts, or planning teams. Do NOT use when: resources are sufficient and no prioritization is needed, or there is a single product with no multi-project coordination
Simulates a multi-role PRD/prototype review board, giving review conclusions from six perspectives: product, engineering, QA, design, operations, and legal. Triggered when the user says "帮我评审一下这个 PRD", "看看这个需求有没有问题", "模拟评审会", "review 一下这个文档", "这个需求能不能过评审", "帮我查漏补缺". Also applies when: the user uploads a PRD, requirements doc, prototype screenshot, or feature spec and asks for a check; the user mentions "评审", "review", "过会", "需求评审", "方案评审" or similar keywords; the user asks whether a requirement is feasible from an engineering or QA perspective. Not for: writing PRDs (use pm-prd-writer), pure code review (use code-review), or pure design walkthroughs (use design-critique).
High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
Generate interactive prototypes from a PRD document. **Use this skill when the user needs to generate an interactive UI prototype from a PRD, a multi-page navigation demo, or quickly validate a product design.** Trigger scenarios: the user says "生成原型", "做个 demo 看看", "生成可跳转的原型", "把 PRD 变成可点击的页面".
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.