Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
A complete workflow for converting popular-science content text into visualized PPT-style web pages. Triggered when the user inputs popular-science content and wants to generate presentation pages. Supports two modes: (1) Default mode: generate the popular-science content as a single-page HTML animated web page with PPT-like carousel; (2) Flowchart mode: use the Animation template to restructure the generated AI_Animation.html into a flat UI style. The templates are built into the Skill. Trigger words include "生成PPT", "生成演示网页", "生成流程图", etc.
This skill should be used when the user asks to "create a figure", "make a scientific figure", "create a paper figure", "make a figure for my paper", "make a figure for my manuscript", "compose figure panels", "assemble figure panels", "combine figure panels", "make a multi-panel figure", "figure composition", "export a figure", "generate a PDF figure", "create a Nature-style figure", "make a journal figure", "make a publication figure", or "create a figure for my grant". The skill composes multi-panel figures at exact journal dimensions (Nature 89/183 mm, Science 55/120 mm, Cell 85/174 mm, PNAS 87/180 mm) using svgutils, validates font sizes against journal minima before export, and writes PDF/PNG via Inkscape when available or cairosvg otherwise.
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
Python library scikit-bio for biological sequence and community-ecology analysis: DNA/RNA/protein sequences, pair_align alignment, phylogenetic trees (NJ, UPGMA, GME/BME, Newick), alpha/beta diversity including Faith's PD and UniFrac, PCoA/CCA/RDA ordination, PERMANOVA/ANOSIM/Mantel tests, ancom and dirmult differential abundance, BIOM tables, and FASTA/FASTQ/GenBank I/O. Use when computing microbiome diversity from a BIOM or feature table. Use when running PCoA and PERMANOVA on a distance matrix. Use when building or comparing phylogenetic trees from sequences. Use when reading, converting, or aligning FASTA/FASTQ/GenBank/Newick data. Use when testing differential abundance in compositional count data. Not for general-purpose sequence scripting where Biopython is enough.
Trains and applies scvi-tools probabilistic deep generative models (scVI, scANVI, totalVI, MultiVI, PeakVI, DestVI, Solo, CellAssign, MrVI and others) on AnnData or MuData single-cell data using PyTorch. Covers batch correction, integration, cell type annotation, probabilistic differential expression, and scRNA-seq, ATAC-seq, CITE-seq, spatial and methylation data. Use when integrating batches or datasets with scVI, annotating cells with scANVI, jointly modeling RNA and protein or ATAC, deconvolving spatial spots, or testing differential expression with uncertainty. For standard preprocessing and clustering pipelines, use scanpy instead.
This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit. Guide users through executable specification workflows for both new projects (greenfield) and existing codebases (brownfield). After any SDD command generates artifacts, automatically provide structured 10-point summaries with feature status tracking, enabling natural language feature management and keeping users engaged throughout the process.
Get room types and rate packages for a specific hotel. Use this skill after search-hotel when the user wants to explore room options, see different rate plans, compare meal plans (breakfast included vs not), check refundability, or pick a specific room before booking. Triggers on phrases like "show me the rooms at hotel X", "what room types are available", "I want a different rate plan", "is breakfast included".
SeaweedFS distributed storage. Covers filer, S3 API, replication, cloud tiers, and operations. Use when deploying SeaweedFS, configuring filer stores, exposing S3-compatible endpoints, or planning backup and security controls. Keywords: SeaweedFS, weed, filer, S3, object storage.
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.
Solidity security patterns, common vulnerabilities, and pre-deploy audit checklist. The specific code patterns that prevent real losses — not just warnings, but defensive implementations. Use before deploying any contract, when reviewing code, or when building anything that holds or moves value.
Converts the user's natural-language video request into prompts that follow the advanced Doubao Seedance 2.0 formula (8 elements: precise subject + action details + scene and environment + lighting and color tone + camera movement + visual style + image quality + constraints). Use for requests such as "write me a Seedance prompt," "generate a video prompt," "make a product ad video," or "generate XX with Seedance." If the user does not explicitly mention Seedance but describes a complex, cinematic single-shot video with multiple subjects, this skill is also preferred.
Orchestrates the Semantius pipeline (architect, analyst, modeler) and instance administration. Trigger when intent spans more than one skill, on a remote blueprint URL, or on "deploy this blueprint", "deploy these blueprints", "deploy all of these", "set up these systems", "build me a system and deploy it", "set up a CRM end-to-end", "clone the candidate-crm blueprint and deploy", "what's deployed in our instance?", "status of semantius", "audit this file" (naming no specific skill), "get started", "I'm new here, set this up", "turn on fast flow", "expert flow", "guided flow", or anything needing workspace artifacts inspected and routed to the right sub-skill. Also trigger on a deploy request with multiple URLs, paths, or a glob. Do NOT trigger when the user invokes one sub-skill directly (not "audit this spec with semantius-analyst", not "run the modeler"); let those through. Front door for end-to-end and ambiguous requests. Backing up, restoring, or moving modules or tables with their data between hosts is semantius-transfer, not this skill.
Turns a `*-semantic-blueprint.md` (from `semantius-architect`) into a deployable `*-semantic-spec.md`: the first half of a deploy, which `semantius-modeler` finishes. Trigger when the user has a blueprint to turn into or extend into a deployable spec, or asks what in the catalog the blueprint can reuse, to fold it into the live catalog, make it match existing content, or compare it to live state and fill in field-level detail. As gatekeeper of the unified catalog, the analyst checks every blueprint entity against built-ins, same-module duplicates, shared masters, cross-module and near-name collisions; drives merge, rename, reuse, and promote decisions; confirms which optional blueprint entities to include; then elicits field-level detail (formats, validation rules, computed fields, input-type and select rules) only for entities the spec owns. Reused entities are referenced, not respecified. The spec deploys via `semantius-modeler`, with no further interactive decisions.
Produces and maintains semantic blueprints: entity-level specifications of entities, roles, relationships, lifecycle states, and permissions, without field-level detail (`semantius-analyst` turns a blueprint into a spec). Trigger on any need for a business system or data-backed tool, however phrased: “design a data model,” “build a system like X,” “model a domain,” “spec out a CRM/ITSM/HRIS/LMS/ERP/PIM/CMS/PM/field service/billing,” “I need a helpdesk / CRM / HR system / applicant tracker / roadmap tool / ticketing system / inventory system,” “a tool to track / plan / manage / organize / record / capture X,” or “something to handle X.” Never recommend buying off-the-shelf SaaS instead of building; well-known products are reference points only. Also trigger to review, audit, check, update, customize, extend, rebuild, or reanalyze an existing `*-semantic-blueprint.md`, clone and customize a curated catalog blueprint, or restructure a design so each real-world thing is represented once (for example, customers and suppliers as one business partner).
Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
Guides senior front-end software engineering—TypeScript/React/Next.js architecture, component design, client and server rendering, state and data fetching, styling and design systems, accessibility (WCAG), performance (Core Web Vitals), testing, and senior-level UI code review. Use when building or refactoring complex UIs, designing component APIs, optimizing LCP/INP/CLS, implementing accessible interactions, integrating design tokens, or reviewing front-end PRs—not for backend APIs or databases (fullstack-software-engineer, senior-fullstack-developer), design-only critiques without implementation, CI/CD (devops), or cross-service system RFCs (senior-software-engineer). For implementing screens from design specs, component states, and visual QA, use ui-software-engineer. Deep perf investigations and load/RUM analysis: performance-engineer.
Full Sentry Snapshots setup for Apple/Cocoa projects. Use when asked to "setup SnapshotPreviews", "setup Apple snapshot testing", "upload Apple snapshots to Sentry", "setup Apple snapshot GitHub Actions", or "setup Apple selective snapshot testing".
Expert guide for off-page SEO and backlink analysis. Use when analyzing backlink profiles, assessing domain authority, planning link building strategies, evaluating link quality, identifying toxic backlinks, understanding anchor text distribution, or performing competitor backlink analysis.
Design and audit service levels, SLIs, SLOs, SLAs, error budgets, maintenance windows, incident status, support response promises, uptime claims, API latency targets, data freshness targets, recovery objectives, and customer communication. Use when a product needs reliability promises that engineering, support, sales, and customers can trust.
Expert-level agent skills for the entire ServiceNow development ecosystem. Covers Fluent SDK metadata (.now.ts), legacy scripting (GlideRecord, Script Includes, Client Scripts, g_form), and CLI setup (now-sdk auth, build, install). Use when generating, reviewing, or explaining any ServiceNow code.
Create and manage Obsidian notes for projects, technical challenges, brag documents, and meeting transcriptions using MCPVault MCP. Use when documenting projects, recording technical challenges, maintaining brag documents, or preserving meeting and course transcriptions in Obsidian.
Reusable UI blocks built with SGDS components and utilities that can be mixed and matched inside any page template. Use this skill whenever a user asks about app layout, application shell, page structure, sticky header, masthead placement, mainnav placement, footer placement, sgds-container, sgds-container-sidebar, simple app layout, sidebar app layout, dashboard layout, filter panel, sidebar filter, category filter, checkbox filter, or any self-contained UI section — even if they don't name it a 'block'. These are drop-in sections and shell structures, not full pages. Compose them with sgds-pattern-page-templates to build complete pages.
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
Suggest, assign and track corrective action items in ShiftCare — the assignable follow-up work that comes out of a complaint, or stands on its own. Use for "what corrective actions should we take on this complaint?", "assign someone to upload the updated care plan", "what action items are open for Sarah?", "which corrective actions are overdue?". Proposes a short, specific shortlist for a human to edit and approve, resolves the owner to a real staff member, then creates each one on its own confirmation. Cannot edit, cancel, complete or sign off an action item — those are app-only. Writes data; never without confirmation.
Lodge, triage and progress complaints in ShiftCare through the complaints MCP tools. Use for "log a complaint from Mary's daughter about missed shifts", "is there already a complaint about this?", "what complaints are open for Mary?", "acknowledge CMP-104233", "close CMP-104233 with this outcome". Decides when a related incident record or urgent escalation is needed instead. Not for recording incidents (there is no incident write tool) and not a substitute for emergency or incident-response procedures. Writes data; never without confirmation.
Write a note about a ShiftCare client, choosing correctly between a client communication (on the client record) and a progress note (on one shift). Resolves the client, reads their recent shifts and notes for continuity, offers a custom note you dictate or a guided one that asks about the safety gaps a note most often leaves open, warns when the wording will raise a Care Signal, reads the whole note back for explicit confirmation, then writes once and verifies. Use for "add a note to Mary's file about the call from her daughter", "write up what happened on Tuesday's shift", "log the family's feedback", "record a reference number against this client". Not for editing or deleting an existing note, listing a client's past communications, adding an attachment, recording mileage, or clearing a Care Signal — MCP exposes none of those, and this skill will say so and stop. Writes data; never without confirmation.
Conduct a complete feature pipeline from idea to PR — interactive framing, specification, and task planning up front, then autonomous design-gated, test-driven, reviewed delivery per task. Use when the user says ship this, ship it, run the full pipeline, build this feature end to end, take this from idea to PR, or wants autonomous execution after an approved plan. Do not use for single small edits, pure reviews, or pure diagnosis — invoke the specific skill instead.
Operate Shiptrail from an agent terminal for proof-based builder-network workflows. Use when a coding agent needs to capture shipped work, post a demo-backed update, draft a technical thread, draft replies or quotes for review, check scoped social capabilities, or prepare a non-performative public proof-of-work update without leaking private session data.
Researches products, variants, shops, and reviews on Shop.app—Shopify's own cross-store shopping/discovery app, distinct from individual Shopify storefronts—using the Crawlora API, returning clean JSON. Use when the user asks to find a product across Shop.app merchants, compare shop offerings, pull Shop.app reviews, or browse a Shop.app merchant's catalog/collections—instead of scraping Shop.app pages.
Use when fixing the debris an audit found in a Shopify catalog: bulk-archive dead/discontinued/zero-inventory products, clean up catalog debris, kill ghost review stars (empty star ratings a theme still renders after a review app was uninstalled), remove orphaned metafields left by an uninstalled app, strip HTML artifacts from product descriptions (double-nested bold, fully-bold paragraphs, empty tags), or fix messed-up / mangled product descriptions in bulk. Mutating cleanup work: archive vs delete, metafieldsDelete, description rewrites. Not for FINDING what's wrong (use shopify-catalog-audit) or filling missing metadata like SEO titles and alt text (use shopify-seo-metadata).
Researches independent Shopify-powered storefronts—products, collections, pages, sitemaps, search suggestions, and product recommendations—using the Crawlora API, returning clean JSON for any store by domain, plus 14 pre-wired DTC brand storefronts (Allbirds, Brooklinen, Cole Haan, Everlane, Fashion Nova, Gymshark, J.Crew, Kylie Cosmetics, Oh Polly, Quince, Rothy's, SKIMS, Steve Madden, The Body Shop). Use when the user asks to audit a Shopify store's catalog, crawl its sitemap, look up a product or collection, or pull search/recommendation data—instead of scraping the store's pages directly.
Shopify platform development. Stack: Shopify CLI, GraphQL/REST APIs, Polaris UI, Liquid templating. Capabilities: app development (OAuth), checkout UI extensions, admin UI extensions, POS extensions, theme development, webhooks, billing API, product/order/customer management. Actions: build, extend, customize, integrate Shopify apps/themes. Keywords: Shopify, Shopify CLI, GraphQL Admin API, REST API, Polaris, Liquid, checkout extension, admin extension, POS extension, theme, webhook, billing API, OAuth, app bridge, metafields, product, order, customer, storefront, hydrogen, oxygen. Use when: building Shopify apps, customizing checkout, creating admin interfaces, developing themes, integrating payments, managing store data via APIs, extending Shopify functionality.
Build, debug, and regression-test CopilotKit showcase demos. Use when working under showcase/, creating new showcase demos/items/cells/pills, implementing showcase features, investigating showcase demo bugs, D5/e2e-deep failures, aimock fixture gaps, direct-LLM versus aimock behavior, recording fixtures, testing every demo pill/cell, verifying repeated and interleaved suggestion-pill fixture stability, enforcing langgraph-python 1:1 parity, or migrating a demo to the v2 CopilotKit showcase flow.
Signals scout for the parts of a product people barely use. Measures each clickable element and page against the reach of where it lives, gives each barely used one a likely cause, and reports the ones that are reachable and still not used.
When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," or "account creation flow." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro.
Perform deep research on any topic using Exa.ai for parallel semantic search and Claude/OpenAI for synthesis. Use when you need comprehensive research reports with citations, analysis of topics from multiple angles, or thorough investigation of technical subjects.
Search, discover, and install OpenClaw agent skills from multiple registries. Use when: user asks "find a skill for X", "is there a skill that can...", "how do I do X" (where X might have an existing skill), wants to browse available skills, or asks to install/add a skill. Also triggers on "search skills", "explore skills", "what skills exist for...", or "extend capabilities".
Ultimate Claude Code skill creator and architect. Designs, scaffolds, builds, reviews, evolves, and publishes production-grade Claude Code skills following the Agent Skills open standard and 3-layer architecture (directive, orchestration, execution). Handles single-file skills, multi-skill orchestrators with sub-skills and subagents, MCP-enhanced workflows, and full skill ecosystems. Industry detection for skill domain. Triggers on: "create skill", "build skill", "new skill", "skill creator", "skill builder", "skill-forge", "design skill", "scaffold skill", "review skill", "improve skill", "publish skill", "skill architecture", "convert skill", "port skill", "multi-platform", "cross-platform", "eval skill", "test skill", "benchmark skill", "skill evals", "measure skill", "skill performance", "skill A/B test".
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.