Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Runs integration tests against the Azure SQL Database container (Private Preview, local engine) in CI. Use when setting up GitHub Actions, Azure Pipelines, or GitLab CI to test against Azure SQL DB; when adding a database service container to a CI workflow; when tests need a real Azure SQL engine in the pipeline; or when you see "service container", "health-cmd", "ACR_USERNAME/ACR_PASSWORD", "MSSQL_SA_PASSWORD secret", or "integration test database". Also use when a workflow was about to pull the SQL Server image mcr.microsoft.com/mssql/server, in which case stop and use the Azure SQL Database engine image instead. Covers pulling from the private ACR with credentials, the service health check that runs sqlcmd inside the container so the runner needs no client tools, provisioning appdb before tests, and pointing the test connection string at the user database not master.
Implement server-side logging with dw.system.Logger, custom log categories, and named log files. Use this skill whenever the user needs to add debug or error logging to Commerce scripts, write to a dedicated log file, configure log categories and levels, or use nested diagnostic context for tracing. Also use when setting up logging in controllers, hooks, or job scripts -- even if they just say 'add logging to my script' or 'write to a custom log file'.
Use when turning voxel edits into production Bevy 0.20 remesh work with `AsyncComputeTaskPool`, `poll_once`, `Mesh3d`, and Rapier `Collider`: dirty/halo fan-out, revision tokens, stale-result rejection, coalescing, priority, bounded uploads, or atomic swaps.
Biopython sequence analysis: parse FASTA/FASTQ/GenBank/GFF (SeqIO), NCBI Entrez (esearch/efetch/elink), remote/local BLAST, pairwise/MSA alignment (PairwiseAligner, MUSCLE/ClustalW), phylogenetic trees (Phylo). Use for gene family studies, phylogenomics, comparative genomics, NCBI pipelines. For PCR/restriction/cloning use biopython-molecular-biology; for SAM/BAM use pysam.
Turn a one-line motion / animation / design brief into the full prompt: a committed look grounded in five reference images, three motion references, numbered beats with a turn, and the refs and assets attached. Also tightens edit notes. Use for \"/blank-page\", \"expand this prompt\", \"make this prompt more specific\", \"what is missing from this prompt\", \"help me write the prompt for X\", or whenever a one-line animation / composition / design brief is about to be handed to an agent.
Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.
This skill MUST be used when designing, evaluating, or refining a business model (商業模式設計／商模重構／九要素), and SHOULD be used for new products, pivots, monetization, and go-to-market decisions that require coordinated choices about customer value, delivery, revenue, and costs.
Create and check long-running video material evaluation tasks. Use this skill when the user wants to submit videos for evaluation, check an existing video evaluation task list, or fetch the result of a previously created video evaluation task. This skill is not a general-purpose video upload skill because upload is allowed only as an internal step of task creation. Authentication uses an API key passed as an Authorization bearer token.
Translate all text in a Canva design to another language, creating a translated copy. Faster than manually copying and editing each text box in Canva's editor. Use when users say "translate my design to [language]", "make a Spanish/French/etc version", or "localize my Canva design".
Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use whenever the user says “capture this,” “brain dump,” “let me dump some ideas,” “I've got a bunch of thoughts,” “here's everything on my mind,” “idea dump,” “let me get this out of my head,” “I need to organize my thoughts,” “here's what I'm thinking,” or similar phrases about unloading a messy stream of ideas, tasks, thoughts, and plans to make them coherent. Also trigger when the user pastes or dictates a long, unstructured block of mixed ideas, even without an exact phrase. Designed for fast action, with no upfront intake. Output has four sections (Projects/Ideas, Tasks, Connections, How I Can Help) and ends with a directive question. Asks at most one clarifying question during organization when an item is genuinely ambiguous between a task and a project.
Use this skill to identify and score acquisition channels by audience fit, speed, cost, effort, and learning value, then recommend the top three. Trigger it when choosing where to reach a defined audience, planning go-to-market, or replacing an underperforming channel.
Track upcoming catalysts for A-share coverage universe — earnings dates, regulatory announcements, sector conferences, product launches, and policy events relevant to Chinese equities. Adapted from the original catalyst-calendar skill for A-share market conventions. Triggers on "A股催化剂日历", "事件日历", "财报日历", "earnings calendar A-share", "upcoming catalysts China", or "what's coming up for [company]".
Configure, maintain, or troubleshoot Claude Code local network protection: Claude/Anthropic HTTP(S) traffic goes through a dedicated inbound and fixed outbound; single node by default, or explicitly configure one primary and one backup node for fail-closed automatic failover; shells, scripts, and remote databases are not intercepted. Verify the wrapper, Clash/Mihomo dedicated inbound, proxy chaining, dynamic residential IPs, network hooks, the macOS sandbox, and Camoufox. Also used for explicitly authorized account residue scanning or cleanup. Use when the user mentions claude-code-guard, Claude account-ban prevention, blocked remote databases, Seatbelt EPERM, proxy disconnection blocking, node drift, or primary/backup failover; it cannot guarantee no account bans, no leakage whatsoever, or that different accounts cannot be linked.
Use when ANY command fails with 'command not found', when installing CLI tools (ripgrep, fd, jq, yq, bat, etc.), auditing project environments, or batch-updating tools. Triggers on: command not found, install tool, missing binary, environment audit, update tools, which, apt install, brew install.
This skill should be used when the user asks to "design a CLI", "improve command structure", "format terminal output", "review CLI usability", "design help text", or "add flags and arguments". Automatically activates when designing new CLI tools, improving command interfaces, formatting terminal output, or reviewing CLI usability. Not for GUI/web design, backend APIs, or shell scripting.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Design interfaces where colour is never the only way information is communicated. Use when designing status indicators, data visualisations, form validation, alerts, maps, or any content that uses colour to convey meaning. Triggers on: colour blind, color blind, colour alone, color alone, colour vision, color vision, red green, deuteranopia, protanopia, tritanopia, colour coding, status colour, chart colours, accessible colours.
This skill MUST be used when drafting or reviewing internal proposals, fundraising decks, partnership proposals, proposal rewrites, and decision-oriented business plans that must persuade a specific audience to approve resources, invest money, or commit to collaboration. MUST trigger on requests such as 商業企劃, 內部提案, 募資提案, 合作提案, 提案優化, 提案審稿, 董事會版本, 投資人版本, ask 撰寫, 資料不足處理.
Use this skill when starting a new course / workshop / training program and you need to design its outline before any lecture content is written. Triggers on phrases like "規劃課程", "課程大綱", "幾天怎麼排", "學習目標", "workshop outline", "syllabus design", "course outline", "learning objectives", "課程總覽", or when the user has a topic and audience but no structure yet. This skill produces the skeleton (.md files) that all downstream stages — content authoring, SPA conversion, visual assets — depend on. Always invoke this BEFORE jumping into writing lecture notes or building a site.
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers (=========), class organization, naming conventions (services, queue jobs, records, events, enums), defineRules() and validation, beforePrepare() and addSelect(), MemoizableArray, DateTimeHelper vs Carbon, strict_types/declare(strict_types=1), short nullable notation (?string), typed properties, void returns, control flow (early returns, match over switch), CP Twig template conventions, form macros, translations (Craft::t), ECS/PHPStan config, scaffolding commands, and the verification checklist.
Establishes a brand's visual direction and compresses it into a Creative Direction Brief with a paste-ready 'style block' that every downstream image prompt reuses, so all generated assets look like they came from one brand. Use when the user says 'define my brand style', 'I want a consistent look', 'what should my visuals look like', 'help me pick an aesthetic / mood / color palette', 'my generated images all look different', or before any multi-asset creative work where no style guide exists yet. Produces the Creative Direction Brief: aesthetic profile, palette with hex codes, style block for prompts, and prohibitions.
Audit connection management — serverless functions opening direct Postgres connections, transaction-mode pooler misuse (PgBouncer / Supabase / prepared statements), and pool sizing against backend max_connections. Module M15. Feeds the Performance & Scale score.
This skill MUST be used when evaluating high-stakes decisions with bias-aware quality control, including proposal review, decision meeting facilitation, personal coaching, and autonomous agent review. MUST trigger on requests such as 重大決策、偏誤檢查、提案審查、決策會議引導、決策教練、 go/no-go 決策、AI 自行審查決策.
Read, study, and answer questions about long books and papers without loading the whole text into one context window, keeping page-anchored notes as a reusable workspace. Use whenever the user asks to read, study, summarize, analyze, review, or answer questions about a long book, textbook, PDF, EPUB, thesis, dissertation, survey paper, or any document of roughly 50+ pages, in any language (Vietnamese "đọc sách", "tóm tắt sách", "phân tích luận án"). Also use when a `{slug}-notes/` workspace from a previous session sits next to a source file and the user asks a follow-up question about that book. Not for short documents (under ~30 pages) that fit in context; read those directly.
Guidance for Microsoft Defender for Identity (MDI) — identity threat detection (ITDR) across on-premises Active Directory, AD CS, AD FS, and Entra Connect using sensors. Covers sensor placement, prerequisites, posture assessments, and lateral-movement detection. WHEN: Defender for Identity, MDI, MDI sensors, detect lateral movement, on-prem AD threat detection, identity security posture, AD CS monitoring, ADCS abuse, domain controller sensor, detect Kerberoasting, DCSync, Golden Ticket, identity ITDR, honeytoken, gMSA Directory Service Account, suspicious LDAP, ESC1 ESC8. DO NOT USE when the goal is cloud identity protection in Entra ID (use entra-id-protection) or correlating cross-workload incidents (use defender-xdr).
Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary runtime defenses that inspect and constrain LLM prompts and responses. Use when adding a production runtime safety layer to an LLM, RAG, or agent application to block jailbreaks, prompt injection (OWASP LLM01), toxic content, or sensitive-data leakage before it reaches or leaves the model.
Use when setting up CI/CD pipelines, creating deployment configurations, generating deploy checklists, or configuring infrastructure. Triggers: new project needs deployment, migrating CI/CD provider, adding staging/production environments, automating release process, setting up monitoring for deploys.
CuTe Python DSL kernel workflow, CuteKernel runtime wrapper, suitability gate, tiling guidance, and CuTe-specific pitfalls. Use when: (1) planning or implementing a kernel in the CuTe Python DSL, (2) the optimization needs more explicit control than cuTile exposes but should remain in a Python-driven workflow, (3) defining package naming for cute-dsl kernels, (4) documenting CuTe Python DSL design choices, (5) recording language-specific knowledge for CuTe Python DSL.
Create or extract a design-token foundation — colors, typography, spacing, radii, shadows — as a real tokens file (CSS variables and/or Tailwind theme) plus a migration map from current hardcoded values. Use when the user says 'set up a design system', 'our styles are inconsistent', 'we have 50 shades of the same blue', 'add design tokens', 'formalize our design', 'make new features match', or when starting a new frontend that needs a foundation before building screens. Also the first step whenever other design work keeps fighting ad-hoc values. Produces the tokens file, a global→semantic token structure wired for dark mode, and a short list of the worst drift to migrate first.
Build a complete, AI-consumable design system from any design reference — a style description ("dark mode fintech with glassmorphism"), a screenshot/image of an existing app, or a Figma link. Outputs structured design tokens (JSON), CSS variables, a Markdown specification, and an HTML preview page — all designed to be fed directly into AI coding agents (like frontend-design) so they produce visually consistent interfaces without guessing. Use this skill whenever someone asks to: create a design system, extract design tokens, build a component library, generate a style guide, define a color palette or typography scale, standardize their UI, or prepare design context for AI-assisted development. Also trigger when someone says things like "make my app look consistent", "I need a theme", "set up design variables", "create a style foundation", or "extract the style from this design".
Runs automated, non-interactive jobs on remote Android devices with Developer Device Platform (DDP) Device Run using `gcloud beta device-run sessions`: native Android executables or shell scripts (for example CLI tools, custom runners, test harnesses or benchmarks) and Android instrumentation tests, on one or many devices, then waits for completion and collects per-device outputs and logs. Use when running a binary or test suite on remote devices without an interactive connection. Don't use it for interactive device reservations, adb tunnels or screen streaming (use developer-device-platform-basics), or for local devices.
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.