Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert knowledge for Azure Container Storage development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring DACS pools, Elastic SAN CMK encryption, AKS deployment, BlobFuse2, or Run:ai + vLLM, and other Azure Container Storage related development tasks. Not for Azure Blob Storage (use azure-blob-storage), Azure Files (use azure-files), Azure Elastic SAN (use azure-elastic-san), Azure Managed Lustre (use azure-managed-lustre).
Expert knowledge for Azure Network Watcher development including troubleshooting, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when configuring flow logs/Traffic Analytics, packet captures, Connection Monitor migrations, VPN checks, or KQL/Terraform automations, and other Azure Network Watcher related development tasks. Not for Azure Monitor (use azure-monitor), Azure Networking (use azure-networking), Azure Virtual Network (use azure-virtual-network), Azure Virtual Network Manager (use azure-virtual-network-manager).
Expert knowledge for Azure Reliability development including best practices, decision making, architecture & design patterns, and limits & quotas. Use when choosing regions/AZs, geo-pairs, AKS HA, DB/network resilience, or Queue/Web PubSub limits, and other Azure Reliability related development tasks. Not for Azure Resiliency (use azure-resiliency), Azure Monitor (use azure-monitor), Azure Service Health (use azure-service-health), Azure Site Recovery (use azure-site-recovery).
Expert knowledge for Azure Synapse Analytics development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Synapse workspaces, Spark/SQL pools, Synapse Link, Delta Lake tables, or ELT with PolyBase, and other Azure Synapse Analytics related development tasks. Not for Azure Data Factory (use azure-data-factory), Azure Data Explorer (use azure-data-explorer), Azure HDInsight (use azure-hdinsight), Azure Databricks (use azure-databricks).
Expert knowledge for Azure Web Application Firewall development including best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Front Door/App Gateway WAF rules, rate limits, geo/IP filters, CAPTCHA/bot defense, or OpenAI/APIM protection, and other Azure Web Application Firewall related development tasks. Not for Azure Application Gateway (use azure-application-gateway), Azure Front Door (use azure-front-door), Azure Firewall (use azure-firewall), Azure DDoS Protection (use azure-ddos-protection).
Chanjing platform integration for FrameVideo: OAuth-aware digital-human video synthesis, public/custom digital-human and voice selection, Chanjing AI Creation image/video assets, platform BGM/SFX downloads, polling/downloading generated assets, and wiring Chanjing assets into FrameVideo compositions. Use when listing Chanjing people or voices, checking Chanjing auth in a platform workflow, submitting/polling digital-human videos, planning/submitting/downloading AI Creation image/video tasks, downloading Chanjing music or sound effects, or integrating Chanjing-generated assets into FrameVideo. For local Kokoro TTS/transcribe/remove-background use framevideo-media; for composition HTML conventions use framevideo
Design autonomous coding loop prompts for Clay's Ralph Loop. Use this skill when the user says /clay-ralph, mentions "ralph loop", wants to set up an autonomous coding loop, or wants Clay to run tasks while they're AFK. Guides the user through creating .claude/PROMPT.md and .claude/JUDGE.md for hands-off iterative development. Even if the user just says "I want to automate this task" or "run this overnight", this skill applies.
Use cmux Cloud machines through the CLI. Use when the user says cmux cloud, cloud VM, cloud machine, cmux vm, Base workspace, machines panel, run/exec on a cloud machine, cloud agent, vm snapshot/fork/restore, push/pull files to a VM, open a port or desktop on a machine, or notify from inside a VM.
Reduce a change's complexity WITHOUT altering behavior—lower cognitive load, not line count: read the target plus its callers and tests, take a baseline check, then apply the smallest clarifying edits in the safest order (dead code and boolean cleanup → flatten nesting with guard clauses → consolidate duplication → local renames and helper extraction), respecting Chesterton's Fence. Re-run the baseline after each edit and revert any change that alters observable behavior or regresses, keeping only safe improvements—a simplification that changes semantics is a bug, not a cleanup. Use only when the user explicitly asks to simplify or clean up existing code.
Author a new FrameVideo registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the framevideo repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `framevideo` skill, for installing existing registry items use the `framevideo-registry` skill
Expert in designing and structuring online courses—curriculum architecture, learning outcomes, module design, and assessment strategies. Covers backward design methodology, scaffolding content, and creating courses that actually deliver transformation. Use when “create a course, course curriculum, course outline, learning outcomes, course structure, design a course, online course, ” is mentioned.
Enforces Effective-Dart documentation on the public surface — a `///` doc on every public class/method/getter/field/typedef, a one-sentence standalone summary that says WHY plus units/ranges/nullability/throws/side-effects (never a restatement of the name), verb-phrase method docs, "Whether…" boolean getters, `[bracket]` cross-links, one `library;` doc per exported barrel, in-body `//` that explains why not what, and the enforced invariant restated at its enforcement point — backed by `public_member_api_docs` and `dangling_library_doc_comments` as analyzer errors. Use when adding or reviewing a public API, a Notifier/provider, a Service interface, a sealed Failure, a value type, or preparing a package's dartdoc.
Agent workspace migration. Turn any project into a maintainable workspace consistent across Claude Code, Codex, and Grok by auditing rule files, identifying the source of truth, normalizing names, and generating bridges. Triggers: /dbs-agent-migration, /agent迁移, “migrate to Codex,” “migrate to Claude Code,” “migrate to Grok,” “unify AGENTS.md,” “organize skill bridges,” “my Agent workspace is a mess,” “help me unify Claude, Codex, and Grok.” Agent workspace migration. Turn any project into a maintainable Claude Code / Codex / Grok three-host workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration, /agent-migration, “migrate to Codex”, “migrate to Claude Code”, “migrate to Grok”, “fix AGENTS.md”, “organize skill bridges”
dontbesilent interactive learning. Breaks a topic into a series of learning articles, adjusting the depth, angle, and pace of each subsequent article based on the user's feedback on the previous one. Triggers: /dbs-learning, /dbs-learn, /交互式学习, “Teach me a topic”, “Continue with the next lesson”, “Write the next lesson based on my feedback”
Keep a repository's docs the product authority, with one dated owner-decision register, lasting docs in `docs/` grouped by kind, and scratch in an ignored `.scratch/`. Use when you record or rely on an owner decision, add, move, or remove a doc, write a temporary note, plan, or spec, edit agent instructions, or set this method up in a new repository.
An execution-focused skill for developing, maintaining, distributing, and validating DeepSeek Harness (DSH) plugins. Covers host/client form assessment, bundle/profile contracts, Service and function plugins, tools, HTTP, persistence, slots, Conversation Node, client builds, HMR, GitHub installation, and real-world integration testing.
Create deterministic editorial-style cover images with a warm paper-gray background, oversized black slab-serif/Chinese display typography, generous whitespace, and a dotted vector analysis icon. Use when the user asks for a “点阵编辑风封面”, “暖灰杂志风封面”, “Codex + Hyperframes 同款封面”, or wants to reproduce/adapt the specific minimal left-text/right-icon banner style. Produce editable SVG and a rendered PNG; do not use this skill for generic covers without this visual direction.
A home Montessori practice coach within the eeailab / 伊伊 AI 成长实验室 system. Answers parents’ questions about Montessori education at home or guides users through systematic Montessori learning. Triggers: $eeailab-montessori, $eelab-montessori, Montessori, Montessori education, Montessori at home, I want to learn Montessori, or how Montessori interprets this child’s behavior.
Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and streaming content. Use when building user interfaces that need professional polish and developer-focused features.
Build and deploy machine learning models with PyTorch, HuggingFace Transformers, and scikit-learn. Use when you need model training, fine-tuning with LoRA/QLoRA, text classification, NER, embeddings, RAG pipelines, dataset preparation, model evaluation, hyperparameter tuning, ONNX export, quantization, inference optimization, or classical ML with XGBoost and scikit-learn.
Build functional prototypes and MVPs at maximum speed to validate ideas through working software. Use for proof-of-concept development, rapid iteration on user feedback, no-code or low-code solutions, backend-as-a-service integration, A/B testing scaffolding, quick feature validation, or modular architectures designed for fast experimentation and learning.
Go-style error handling for TypeScript: return errors as a plain `Error | T` union instead of throwing. `instanceof Error` narrows the type — no Result wrapper. The gist: ```ts class NotFoundError extends errore.createTaggedError({ name: 'NotFoundError', message: 'User $id not found', }) {} async function getUser(id: string) { const user = await db.findUser(id).catch((e) => new DbError({ cause: e })) if (user instanceof Error) return user // early return, like Go's err != nil if (!user) return new NotFoundError({ id }) return user // caller narrows the same way } ``` ALWAYS read this skill when a repo uses the errore convention (errore.org). ALWAYS use errore for new TypeScript projects.
Conduct comprehensive code reviews of GitLab merge requests, analyzing code quality, security, performance, and best practices. Use when the user says “review” or “code review,” or asks to review merge requests or analyze branch changes before merging
Query Google Search Console via the Search Console API v1 — search analytics (clicks / impressions / CTR / position), sites, sitemaps and URL inspection. Use when the user mentions Search Console, organic search performance, top queries / pages, indexing status, or sitemaps.
GEO (Generative Engine Optimization) citation tracking + optimization (2026-06-24 standard). Run fixed queries weekly across 4 major AIs (Claude/GPT/Perplexity/Gemini) to check whether answers cite the target domain. Add Citable Statistics and AI-friendly formats (one-sentence answer + table + FAQ) to pages that aren't cited. Use Bing IndexNow submissions to ensure LLMs discover/index content quickly. Monitor GA4 AI-source traffic. Use when the user says “Am I cited by AI?”, “GEO optimization,” “update llms.txt,” or “AI citation tracking.” Defaults to B2B/open source; query topics and Citable Stats sources differ for 2C products (education/apps); see gingiris-seo-geo/references/2c-adaptation.md
A framework for user interviews and requirements validation, covering primary evidence, solutions, prioritization and follow-up handoffs. Validate requirements through behavior and retesting; do not use the number of interviews as proof of PMF. Covers interview recruitment, question design, interview execution, data synthesis and decision-making. From gingiris-user-interview
Parse and explain HL7 v2.5 IHE PAM (Patient Administration Management) messages. Identify the message type, extract segments (MSH, EVN, PID, PV1, PV2), validate the structure, and provide detailed explanations of ADT messages for patient administration workflows. Use when the user provides or asks to analyze an HL7 v2.5 IHE PAM / ADT message, identify a message type, or extract or explain MSH/EVN/PID/PV1/PV2 segments. For the proprietary HPK format, use hpk-parser instead
GitHub dark-purple gradient deck — GitHub-dark #0d1117 + purple-blue radial ambient light + 60px grid mask, centered layout, purple pill labels, tricolor gradient title (#a855f7→#60a5fa→#34d399), GitHub-style code palette, purple left-border highlight blocks. Suited to developer workflow / MCP / Agent / dev tool tutorials, similar to GitHub Blog / Linear Changelog.
Deploy NewAPI LLM Gateway on Huawei Cloud via Terraform. Use when deploying a unified LLM API gateway for multi-model management, load balancing, and key rotation. Trigger: deploy NewAPI, NewAPI gateway, LLM gateway, 部署NewAPI, NewAPI网关, LLM网关
Huawei Cloud SWR (Software Repository for Container) image automation and operations skill using hcloud CLI. Use when the user wants to: (1) configure cross-region image sync (auto or manual), (2) manage SWR triggers for auto-deploy to CCE/CCI, (3) query available sync target regions, (4) check sync job status, or (5) create/update/delete trigger configurations. Trigger: user mentions “SWR automation”, “SWR 自动化”, “镜像同步”, “SWR sync”, “跨区域同步”, “cross-region sync”, “触发器”, “SWR trigger”, “自动部署”, “auto deploy”, “镜像复制”, “image replication”, or “SWR 触发器”
Imports a Dataverse solution zip into a target environment, with optional staged import to check dependencies before committing. Use when asked to “import solution,” “install solution,” “deploy solution zip,” “push solution to environment,” “deploy to staging,” “deploy to production,” or “install site in new environment.”
Investigates a specific CI failure to a verdict: whose fault, which commit, who wrote it, and whether it's fixed. Use for "who broke master", "why did this test fail in CI", "is this failure my PR's fault or everyone's", "is this test flaky or actually broken", "when did this failure start". Works from the engineering_analytics warehouse views (engineering_analytics_ci_failures, engineering_analytics_ci_job_history) plus the CI failure logs. Not for aggregate CI health, cost, or merge bottlenecks (use diagnosing-ci-and-merge-bottlenecks) and not for building saved insights (use turning-engineering-analytics-into-insights).
Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying. Use when the user asks to "check the logs", asks whether a service, deploy, release, or change is working or broke anything, asks why errors are up or what changed, or wants the root cause of failures visible in logs. Routes the logs MCP tools (services overview, pattern mining, before/after pattern diffing, bucketed counts, facets, raw rows) so investigations start from summaries instead of raw rows or hand-written SQL over the logs table.
Move an existing Remotion project onto Kinetograph so it renders without a browser. Use when the user has a Remotion project (remotion or @remotion/* imports, `remotion render` scripts, @remotion/three, @remotion/player) and wants it to run, preview or render with Kinetograph, or asks what in a Remotion project will not work there.
Generate legal service documents such as litigation plans, non-litigation plans, proposals, consulting reports, and case-closing reports from case materials or communication records. For external proposals, generate editable Word documents with designed layouts (four cover options: C/D/E/F, with optional team and law firm appendices). Use when the user needs legal service documents or a designed Word proposal.
Persist, schedule, resume, and hand off monitoring or ownership campaigns that outlive one agent session or disposable workspace. Use when work must be checked repeatedly over days, when creating a new long-term campaign, when transferring ongoing work to a future agent, or when producing a delayed evidence-based report
Lottie and dotLottie adapter patterns for FrameVideo. Use when embedding lottie-web JSON animations, .lottie files, @lottiefiles/dotlottie-web players, registering instances on window.__fvLottie, or making After Effects exports deterministic in FrameVideo
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run list_mcps.py, show catalog with auth types and install commands
Expert micro-interaction architect for mobile apps, web applications, and responsive websites. Use this skill when the user asks to add, build, fix, audit, or consult on micro-interactions, animations, transitions, motion design, gesture feedback, haptics, loading states, skeleton screens, pull-to-refresh, swipe actions, scroll animations, button states, form validation feedback, toast notifications, modals, dropdowns, toggles, progress indicators, shared element transitions, spring physics, easing curves, motion tokens, or any interaction that provides visual/haptic/auditory feedback to user actions. Triggers on: "micro-interaction", "animation", "transition", "motion", "easing", "spring", "gesture", "haptic", "feedback", "loading state", "skeleton", "shimmer", "pull to refresh", "swipe", "drag", "hover effect", "press state", "focus ring", "scroll animation", "parallax", "stagger", "orchestration", "reduced motion", "View Transitions", "layout animation", "shared element", "hero animation", "morphing", "Framer Motion", "GSAP", "Lottie", "Rive", "React Spring", "anime.js", or any request to make an interface "feel better", "feel alive", "feel snappy", "feel responsive", or "feel polished".
Step-by-step migration from React Router v7 to TanStack Router: route definition conversion, Link/useNavigate API differences, useSearchParams to validateSearch + useSearch, useParams with from, Outlet replacement, loader conversion, code splitting differences.
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.