Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal questions — data subject requests, vendor inquiries, NDA requests, discovery holds — or when managing response templates.
Internal vs external career growth paths, goal setting, career maintenance, and long-term planning for software engineers. Use when deciding between internal promotion vs external job search, setting career goals, or planning long-term career trajectory.
Reason about CDISC SDTM and ADaM implementation for regulatory submissions. Use when the user asks about SDTM domain mapping, ADaM dataset design, controlled terminology versioning, define.xml completeness, FDA or PMDA submission requirements, query prioritization by clinical impact, SUPPQUAL usage, or CDISC compliance review. Triggers include "SDTM mapping", "ADaM dataset", "CDISC compliance", "controlled terminology", "define.xml", "FDA submission data", "PMDA submission", "SDTM domain", "ADSL", "ADAE", "ADLB", "BDS structure", "SUPPQUAL", "RELREC", "value-level metadata", "CDISC CT", "regulatory submission data standards", "eCTD datasets", "SDTM 3.3", "ADaM 1.1", "query prioritization", "clinical data review".
Chains together clear specifications, proactive risk analysis (premortem/register), and measurable success metrics into a comprehensive planning artifact for high-stakes initiatives. Use when planning migrations, launches, or strategic changes that need implementation roadmaps, risk mitigation, and instrumentation. Invoke when user mentions "plan this migration", "launch strategy", "implementation roadmap", "what could go wrong", "how do we measure success", or when high-impact decisions need comprehensive planning.
Given a topic or workflow from the user, automatically generates a complete short-video piece (script, storyboard, digital-human voice-over, and mixed AI footage); calls the Chanjing Open API and sub-skill scripts in the same repository.
Institutional-quality equity research initiation reports for A-share companies. Covers company analysis, financial modeling, valuation, chart preparation, and final report assembly. Adapted from the original initiating-coverage skill for Chinese market conventions, CAS accounting, and AkShare data sources. Triggers on "A股首次覆盖", "首次评级", "initiate coverage China", "initiate on [company]", "A股研究报告", or "start research on [company]".
Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands, architecture, and conventions, then asking at most 3 targeted questions for what cannot be inferred. Use whenever the user says 'create a CLAUDE.md', 'my CLAUDE.md is blank', 'generate project context', 'initialize CLAUDE.md', 'set up Claude context for this repo', 'fill in my CLAUDE.md', or any variation where someone needs their project context documented for Claude. If a CLAUDE.md already exists with content, runs a diff-and-merge flow before writing.
Use when writing, editing, reviewing, testing, planning, or refactoring code in any language or framework; creating files or deciding where code and folders belong; designing or changing module boundaries, layers, and dependencies; starting a new project; auditing or cleaning up an existing one; or compressing agent instruction files. Covers SOLID, design patterns, and the dependency rule.
Compress a prompt while preserving semantic content. Use when user says "compress this prompt", "make this shorter", "reduce token count", or "shorten these instructions". Supports lossy (default, 30-50% reduction) and lossless (--lossless, 100% retention) modes.
Guidance for responding to and recovering from a significant identity/tenant compromise - regaining administrative control, evicting the adversary in a single coordinated action, and hardening to prevent reentry. Covers trusted foundation (PAW), containment, eviction, identity recovery (krbtgt, federation), and post-eviction hardening. WHEN: compromise recovery, incident response, regain control after breach, evict attacker, tenant compromise, rebuild trust, ransomware recovery, post-breach hardening, kick out adversary, emergency response, attacker is in our tenant right now, ransomware hit our organisation, regain admin access after a breach, adversary has domain admin or Global Admin. DO NOT USE for routine SOC investigation (use defender-xdr / sentinel) or for preventive hardening with no active compromise (use security-architecture / entra-id).
Configure nginx for static sites, reverse proxying, load balancing, SSL/TLS termination, caching, and performance tuning. When setting up web servers, application proxies, or load balancers, this skill provides production-ready patterns with modern security best practices for TLS 1.3, rate limiting, and security headers.
Craft CMS 5 front-end Twig development — atomic design, template architecture, components, Vite buildchain. Covers atoms/molecules/organisms, props/extends/block patterns, layout chains, view routing, content builders, image presets, Tailwind named-key collections, multi-brand CSS tokens, JavaScript boundaries (Alpine/DataStar/Vue, tabs, accordions), Vite asset loading, and front-end auth (login, registration, password reset, profiles).
Push the current branch and create a pull request on GitHub. Derives the title and description from any JIRA ticket referenced by the branch, and references every issue (JIRA, GitHub, etc.) the PR actually fixes — never related items. Draft by default, use --no-draft for a ready PR.
Create a short-form vertical video (TikTok, Instagram Reels, YouTube Shorts). Optimized 9:16 pipeline with a live Studio preview, auto-captions, hook-first structure, and background music mood selection; renders to MP4 only when you ask
Use this skill to drive cross-app and system-UI flows from instrumentation tests using UiAutomator 2.3.0 — `UiDevice`, `BySelector` / `UiObject2` (modern), `UiSelector` / `UiObject` (legacy), `Until` conditions, and `Configurator` global timeouts. Covers the singleton acquisition (`UiDevice.getInstance(InstrumentationRegistry.getInstrumentation())`), `pressBack/pressHome/pressRecentApps`, `device.findObject(By...)` cached-node refresh and `StaleObjectException` recovery, the `executeShellCommand` `@Discouraged` path vs `Context.startActivity` plus `<queries>`, and the full `By` factory catalog. Use when the user reports `StaleObjectException`, `Espresso InjectEventSecurityException`, `findObject returns null`, asks "how do I open Settings from a test", "toggle Wi-Fi", "dismiss notification shade", or "test that spans my app and another".
CuTe Python DSL API reference and implementation patterns for NVIDIA GPU kernel programming. Provides execution model, core API table, key constraints, common patterns, and documentation index. Use when: (1) writing or modifying CuTe DSL kernel code, (2) looking up CuTe DSL API syntax, (3) implementing attention/GEMM/MLA patterns in CuTe DSL, (4) understanding CuTe DSL execution model and compilation pipeline, (5) checking what CuTe DSL can and cannot do.
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
Design effective data dashboards with proper KPI hierarchy, chart type selection, and interactive features. Use this skill when the user needs to create a dashboard, choose the right visualizations, organize metrics for different audiences, or evaluate dashboard tools — even if they say 'build a dashboard', 'our reports are confusing', 'which chart should I use', or 'executives can't find the metrics they need'.
Doubaoya (doubaoya / 本鸭) skill reconciliation updater: reconciles the locally installed set of doubaoya skills to the current full set in the official repository — archiving ones removed upstream, installing newly added ones, refreshing outdated ones, then self-checking. Packages are identified by content hash, so other people's and user-modified ones are left untouched down to a single character; removed ones are moved to an archive directory rather than deleted. Reconciles the installed doubaoya skills to the upstream set, then self-checks. Triggered by: /dby-update, 更新本鸭, 更新都爆鸭, 升级 doubaoya skill, 检查本鸭更新, 把本鸭更新到最新版.
Set up the Datadog Google Cloud integration with Terraform: creates a service account in the host project, lets Datadog's delegate principal impersonate it via roles/iam.serviceAccountTokenCreator (no service-account keys), enables the required APIs, grants the monitoring roles across the chosen projects and folders, and registers the account through datadog_integration_gcp_sts. Use when the user wants to monitor GCP resources such as Compute Engine, Cloud SQL, GKE, Cloud Run, or Pub/Sub, wants to connect a GCP project or folder or organization to Datadog, or asks to set up or repair the GCP integration. Does not set up log forwarding.
Set up the Datadog Oracle Cloud Infrastructure (OCI) integration with Terraform: verifies ~/.oci/config, then applies Datadog's official oracle-cloud-integration module to create the Datadog service user, group, IAM policies, and API key in the tenancy and register it with Datadog, optionally including log collection. Use when the user has Oracle Cloud resources, wants to monitor an OCI tenancy, wants to connect OCI to Datadog, or asks to set up or repair the OCI integration.
Use when running or designing an EventStorming workshop — phrases like "EventStorming", "event storming", "domain discovery workshop", "sticky notes on a wall", "big-picture EventStorming", "process modeling EventStorming", "software design EventStorming", "pivotal event", "hotspot", "should we do an EventStorming session". Defines EventStorming as Alberto Brandolini's lightweight collaborative workshop format for exploring a domain by mapping it as a sequence of past-tense events.
Guidelines for de-jargoning Chinese output. Activates automatically when the model replies in Chinese, keeping output concise, direct and natural, and avoiding AI-flavored expressions such as consulting jargon, internet slang, fake urgency and emotional manipulation. Trigger phrases: 「讲人话」「去油」「去黑话」「去 AI 味」「别那么 GPT」「正常说话」. Even without a trigger phrase, the rules of this skill should apply whenever the model is generating a Chinese reply. Also applies when the user says 「这段话太 GPT 了」「帮我改成人话」「输出太油了」「说话别绕」.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, WHY HOW WHAT papers, 3W literature scan, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 三段式文獻掃描, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題, 심층 연구, 문헌 조사, 체계적 문헌고찰, 메타분석, 사실 확인, 연구 방향을 잡아줘, 연구 주제 정하는 것을 도와줘, revisión de literatura, metaanálisis
Enhances milestones.yaml with detailed acceptance criteria for each milestone. Derives functional acceptance criteria, non-functional gates, testing requirements, documentation requirements, and exit checklists from business and technical requirements. Updates milestones.yaml in place with optional acceptance_criteria and exit_checklist fields.
Extract a brand's design from any reference the user provides (site URL, screenshot, or existing assets) and generate a full design system reference page AND a 1-page A4 brand book PDF. Triggers on "design system", "brand book", "make design assets", "extract design", "brand page", "one page brand".
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.
Expert in documentation structure, cohesion, flow, audience targeting, and information architecture. Use PROACTIVELY for documentation quality issues, content organization, duplication, navigation problems, or readability concerns. Detects documentation anti-patterns and optimizes for user experience.
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.