Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Runs database schema migrations against the local Azure SQL Database container so the same migrations apply identically on the local engine and in the Azure cloud. Use when asked to "run my migrations against the local SQL", "apply schema to the container", "apply EF Core / dotnet ef database update", "Prisma migrate dev / deploy", "Alembic upgrade head", or deploy a DACPAC / SqlPackage to the container. Covers provisioning appdb on master first, then applying schema to the user database, plus per-tool commands and connection-string hygiene. This is the Azure SQL Database engine (EngineEdition 5), not the SQL Server image; reach for this skill whenever schema migration tooling targets the local container.
Deploy and manage Managed Runtime (MRT) storefronts using the b2c CLI. Use this skill whenever the user needs to deploy a PWA Kit bundle, manage MRT environments and projects, set environment variables, configure URL redirects, or manage organization connections — even if they just say "deploy my PWA" or "set up a staging environment".
Backlink / off-page SEO audit. Works WITHOUT a paid tool by default — it uses the Google Search Console Links report (your top linking sites, most-linked pages, and anchor text) plus any backlink export the user provides (Ahrefs / Semrush / Majestic / DataForSEO CSV). Analyzes referring-domain profile, anchor-text distribution (over-optimized / spammy patterns), most-linked pages vs. money pages (internal-linking opportunity), toxic/spam link signals, and link-building priorities. Use this skill when the user asks about backlinks, link building, off-page SEO, referring domains, anchor text, toxic/spam links, disavow, or their link profile. Trigger on: "backlinks", "backlink audit", "link building", "off- page SEO", "referring domains", "anchor text", "toxic links", "spam links", "disavow file", "who links to me", "link profile", "domain authority". NOTE: rich third-party metrics (DR/DA, full link index) require a paid data source; this skill is explicit about what it can and can't see without one.
From logic to speech: chains the three independent skills barry-logic-training → barry-speech-training → barry-translation-training to produce a complete English speech in one go. The orchestrator only handles the hand-offs and mode selection; the specific logic of each stage is defined by the corresponding independent skill. Two tracks: standard track (step-by-step confirmation) and fast track (produce the finished piece in one go). Triggers: 逻辑到演讲, 从逻辑到演讲, logic to speech, 帮我梳理逻辑然后准备演讲, 梳理加演讲, 整理成演讲.
Standalone logical thinking training for working professionals. Two modes: exploration mode (not yet clear, need to start from finding the real problem and build up to a pyramid) and structuring mode (content already exists, just needs reorganising into a pyramid structure). The AI acts as a Socratic coach, using follow-up questions to guide students to complete their own thinking. Triggers: 逻辑思维训练, 逻辑训练, 练逻辑, 搭金字塔, logic training, 帮我梳理一下.
The **unified entry point** of the Barry workplace English toolbox. Called when a new learner first encounters the toolbox — it shows a welcome message and guides them through the full 3-step onboarding (profile → assessment → solution); also called when returning learners need to re-run onboarding (because their situation changed). **This is the skill a learner should call on first launch** — it ties together how the whole toolbox is used, so learners don't need to know the name of each atomic skill. Trigger words: 开始、启动、开始学英语、英语训练、barry、barry-onboarding、english onboarding、how do I start、I want to learn english、欢迎、welcome.
Collection and updating of Section 1 (basic personal details) of the Barry student profile. A 10-20 minute guided in-depth interview that digs into the student's work context, pain points, goals, time commitment, and learning history, written to `~/.barry-english/profile.md`. First runs for new students are triggered by barry-onboarding; returning students invoke it directly to update the profile (when changing jobs/changing roles/adjusting goals). Triggers: 基本情况, 更新档案, 更新基本情况, 我换工作了, profile update.
Design a Barry learner's training plan + automatically generate a dedicated daily training skill. Reads learner profile Section 1+2+3 + the Four-Strands training method toolbox, designs the Section 4 training plan, and after learner authorization automatically installs it to <current AI agent skills directory>/barry-daily-<nickname>/, copying the Quiz web code to ~/.barry-english/quiz-web/. **Prerequisite: barry-profile + barry-assessment must already be completed**. 10-15 minutes. Trigger words: 定制方案、出方案、训练方案、生成训练 Skill、barry solution.
Standalone public speaking training for working professionals. Core differentiator: in-depth audience analysis drives the structure design. Two modes: coaching mode (build from scratch) and fast mode (produce a framework directly from existing material, then fine-tune). Triggers: 演讲训练, 公众演讲训练, 练演讲, speech training.
Converts markdown plans into beads (tasks with dependencies) and polishes them until implementation-ready. The bridge between planning and agent swarm execution. Use when converting a plan to beads, polishing bead descriptions, adding test coverage beads, reviewing bead dependencies, or preparing tasks for agent swarm execution.
Use when designing Bevy 0.20 persistence with `DynamicWorldBuilder`, `DynamicWorld::serialize`, `WorldAssetRoot`, `IoTaskPool`, or `SettingsPlugin`: stable IDs, versioned save DTOs/migrations, checksums and atomic writes, snapshots plus sparse deltas, native/browser storage, and safe ECS serialization boundaries.
bmzskill professional tool navigation entry point. Routes users who are unsure which music project evaluation tool to use into specialized sub-flows such as creative inspiration, lyrics quality checks, genre and vocal design, pre-release health checks, release package generation, and data review.
Use this skill to analyze market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and US Stock Market Uptrend Stock Ratio charts. Use it when the user provides breadth chart images for analysis, requests a market breadth assessment or positioning strategy recommendations, or wants to understand the medium-term strategic and short-term tactical market outlook based on breadth indicators. It also works without chart images by fetching CSV data directly from public sources. All analysis and output are conducted in English.
This skill should be used to create or update a C4 architecture diagram alongside an ADR, especially in LikeC4. PROACTIVELY activate on "add a C4 diagram", "create a context diagram", "container view", "LikeC4 model", "draw the architecture", "diagram this decision", "architecture diagram for the ADR", "visualize the components", "C4 view", or "Simon Brown C4." Provides: canonical-C4 Context and Container views from confirmed elements, relationship descriptions, and strict refusal of non-canonical diagram types.
Caffeine JVM local caching skill. Covers the decision tree for choosing local cache vs remote cache (Redis), comparison of the three expiration strategies expireAfterWrite vs expireAfterAccess vs refreshAfterWrite and their combination rule (refresh < expire), CacheLoader loading and reload async refresh patterns, Spring Cache @Cacheable integration, maximumSize eviction policy, and recordStats cache statistics. Corrects LLM mistakes: using ConcurrentHashMap + manual expiration, routing all caches through Redis, refreshAfterWrite > expireAfterWrite causing caches to never refresh, and CacheLoader returning null causing cache penetration.
Chains estimation, decision analysis, and storytelling to transform uncertain choices into clear, stakeholder-ready recommendations. Quantifies uncertain variables, applies expected value analysis to identify the best option, then packages the analysis into a persuasive narrative. Use when evaluating strategic options (build vs buy, market entry, resource allocation), quantifying tradeoffs, justifying investments, pitching to decision-makers, or when user mentions ROI analysis, expected value, business case, cost-benefit, or needs to combine estimation with persuasive communication.
Systematic stock screening and investment idea sourcing for A-share markets. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Adapted from the original idea-generation skill for Chinese market conventions and data sources. Triggers on "A股选股", "股票筛选", "寻找机会", "stock screen China", "A-share ideas", "find ideas for Chinese stocks", or "screen for A-share opportunities".
Daily morning research note for A-share markets. Summarizes overnight developments, pre-market sentiment, trade ideas, and key events for the trading day. Adapted from the original morning-note skill for Chinese market conventions. Triggers on "早报", "晨会纪要", "今日策略", "morning note", "morning meeting", or "daily A-share preview".
Use when running autonomous loops, repeated operations, or when detecting stagnation patterns - enforces rate limits, protects configuration files, manages recovery with cooldown periods, and prevents infinite loops during autonomous development
Verify citations and references in scientific documents to detect hallucinated or invalid sources. Extracts DOIs, URLs, arXiv IDs, PubMed IDs, and ISBNs from Markdown, LaTeX, org-mode, and plain text, then validates them using API lookups and web fetches. Use this skill when: - Reviewing AI-generated content for citation accuracy - Validating references in papers, reports, or documentation - Checking if DOIs/URLs resolve to actual papers - Auditing a document for broken or fake citations
When the user needs to create a client-facing document such as an SEO audit, proposal, scope of work, competitive analysis report, onboarding document, or market intelligence report. Also use when the user mentions "audit report," "proposal," "scope of work," "SOW," "pitch deck," "client presentation," "pricing document," "onboarding checklist," "competitive report," "market analysis," "prospect audit," "free audit," "AI visibility audit," or "deliverable." For ongoing performance reports, see local-reporting. For the research behind audits, see local-seo-audit.
Generates structured scaffolds (frameworks, checklists, templates) for technical work — TDD test suites, exploratory data analysis plans, statistical analysis designs, causal vs predictive modeling objectives, and validation checklists. Use when starting technical work that needs systematic planning before execution. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", "design an A/B test", or when technical work needs scaffolding before execution.
Review changes since a fixed point (commit, branch, tag, PR reference, or merge-base), checking separately whether they follow the repository's recorded coding standards and whether they implement the original issue's requirements. Use when the user asks to review a branch, PR, WIP changes, or changes since a particular point.
Use when completing a task, implementing a feature, or before committing to verify work meets requirements and coding standards. Triggers: task completion, pre-commit check, pre-merge validation, plan alignment verification, post-refactor quality gate.
Guide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal evidence. Use when the user wants an agent-led code tour, code-along, live source explanation, or recorded terminal walkthrough.
Use when Codex Desktop sessions, threads, sidebar history, project conversations, or local session lists are missing after an update or restart, only one conversation is visible, sessions need to be restored for a workspace, or the user asks to repair Codex session_index/state/global-state/cwd metadata. This skill audits and restores local Codex session metadata safely.
Access cryptocurrency market data from CoinPaprika: prices, tickers, OHLCV, exchanges, contract lookups for 12,000+ coins and 350+ exchanges. Free tier, no API key needed. Install MCP: add https://mcp.coinpaprika.com/sse as SSE server, or install plugin: /plugin marketplace add coinpaprika/claude-marketplace
Scaffold a new Adobe Commerce app using the aio-commerce-sdk. Creates the base project structure and app.commerce.config file with metadata. Use when the user wants to create a new Commerce app from scratch or initialize a bare Commerce app project. After scaffolding, chains to appbuilder-project-init for Developer Console setup (project, workspace, API subscriptions) when the user wants to deploy. Does not configure extensibility domains — use commerce-app-eventing, commerce-app-webhooks, commerce-app-business-config, commerce-app-admin-ui, or commerce-app-storage for that
Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans. Use for neighborhood preparedness, mutual support, shared projects, and community learning programs. Do not use for travel guides, promotional brochures, standalone policies, simple document formatting, or live incident response.
Reviews the legality of draft contracts and business conduct, comparing against regulations such as civil law, labor standards law, personal data protection law and company law, flagging high-, medium- and low-risk clauses and offering amendment suggestions.
Owns repositories, data sources and mapping for Compose and Compose Multiplatform apps: DTO to domain to UiModel boundaries, Ktor clients and bearer auth, WebSocket and SSE, Room, DataStore, Paging 3, offline-first and data-layer tests. Use when writing or reviewing a repository, data source, DTO, mapper, HttpClient, bearer token, WebSocket, SSE, Room DAO, migration, DataStore, PagingSource, RemoteMediator, offline cache or MockEngine test. Do NOT use for ViewModel or UI wiring (compose-feature), composables (compose-ui), the MVI contract or error tiers (compose-architecture), Gradle modules (compose-project), or commonMain vs platform splits (compose-platform).
Use this skill first for any Jetpack Compose or Compose Multiplatform task: a new feature or screen, a change to existing code, a bug fix, a review, making code follow the kit, project or build setup, or a question. It picks the task path and the exact kit files to read. Not for Kotlin work outside a Compose or CMP app.
Owns platform splits for Compose Multiplatform apps: places declarations in commonMain, chooses expect/actual vs interface plus DI, wires host adapters and ports, and validates iOS/Swift interop, desktop and web targets, and platform lifecycle. Use when touching commonMain, expect, actual, iosMain, Swift, SKIE, Flow to Swift, desktop, wasm, web target, or platform-specific code. Do NOT use for routing or architecture (compose-architecture), feature slices (compose-feature), composables or resources (compose-ui), repositories or persistence (compose-data), or Gradle target setup (compose-project).
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__syncwarp, or cuda::barrier / wgmma issues. Do NOT use for host/CPU-side bugs (use valgrind or AddressSanitizer) or global-memory data races (out of scope). Trigger keywords - compute-sanitizer, memcheck, racecheck, initcheck, synccheck, CUDA memory error, OOB, race condition, uninitialized memory, __syncthreads, barrier, deadlock
Write and debug Flink SQL that runs on Confluent Cloud, enforcing the CC-vs-Apache-Flink (OSS) dialect boundary. Use when the working directory is a Confluent Cloud Flink workspace, when a Flink SQL statement needs checking before it runs on a CC compute pool, or when the user mentions CC Flink, Confluent Cloud Flink SQL, the `confluent flink` CLI, a CFU compute pool, `CREATE CONNECTION`, or asks to check or debug Flink SQL whose runtime is Confluent Cloud. Also trigger when a Flink SQL question is posed and nothing establishes an Apache Flink OSS runtime. Do NOT trigger for: building or deploying Flink UDFs in Java (UDF/UDTF/PTF — use flink-udf); a full CDC pipeline from a database through Flink into Tableflow/Iceberg/Delta Lake (use confluent-cloud-cdc-tableflow); Kafka Streams topology work (use kafka-streams-programming); or Flink SQL confirmed to run on Apache Flink OSS, not Confluent Cloud.
Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.
Extract explicit and implicit constraints (compliance, security, hosting, tooling, stakeholder, scope, and external-dependency boundaries) from a project's documentation, then build or update a canonical CONSTRAINTS.md. Spawns one subagent per source document to flag externally-imposed boundaries with evidence citations and confidence ratings, then correlates, deduplicates, and organizes the results by category before writing them into CONSTRAINTS.md. Use this skill whenever a user mentions \"CONSTRAINTS.md\", \"extract constraints\", \"find our constraints\", \"document constraints\", \"compliance constraints\", \"what limits this project\", \"synthesize constraints\", or wants to capture externally-imposed boundaries (legal, security, compliance, stakeholder, vendor) that shape what a project can build and how. Always prefer this skill over ad-hoc constraint documentation.
Fetch up-to-date documentation for any open-source library or framework. Use when the user asks to look up docs, check an API, find code examples, or verify how a feature works — especially with a specific library name, version migration, or phrases like 'what's the current way to...' or 'the API might have changed'. Also covers setup and configuration docs. Do NOT use for general programming concepts, internal project code, or version lookups (use deps-dev).
Apply these opinionated C# conventions whenever writing or reviewing C# 12 / .NET 8+ code: nullable enabled with warnings as errors, records and primary constructors, pattern matching over cast chains, the Result pattern for expected failures, async all the way with CancellationToken, IOptions config, IHttpClientFactory, and never returning EF entities from an API.
This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app. Trigger on "show me these images", "review this batch", "open these in Cull", "rate / shortlist / collect these", "find similar images", "make a smart collection", "run a quality pass", "export the keepers", "publish this collection". Works via the `cull` CLI by default (no MCP required); the `mcp__cull__*` tools are optional for richer interactive control.
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.