Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generate posters from text/images, multi-style and multi-size with layout, supporting reference images and editing text/background/elements of existing posters. Trigger when the user mentions 海报, 宣传图, 广告图, Banner, 推广图, 营销图, 活动海报, 促销海报, or poster.
Comprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.
Interview prediction, simulated follow-up questioning, and practice skill driven by a Chinese-language resume and target role: extract experience claims that need verification, build question and scoring contracts by interview round, and check real mastery through one question at a time, evidence-based feedback, and repeat practice on weak areas; use when the user enters "/interview" or asks for interview prediction, mock interviews, resume follow-up questions, stress interviews, scenario design questions, or checking interview mastery.
Always consult this before writing or outputting anything at the start of any communication with the user. It applies to all situations where text is written or output, such as chat responses, reports, explanations, work updates, and documentation.
Expert Java architect specializing in Java 21, Spring Boot 3, and Jakarta EE ecosystem. This agent excels at designing enterprise-grade applications with modern Java features, microservices architecture, and comprehensive enterprise integration patterns.
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
Use when planning to rank for a specific keyword. The agent Googles it, reads the top 10, classifies intent, reads the top 3 competitor pages, and produces a 90-day ranking plan with intent, SERP analysis, and content recommendations.
Get an INDEPENDENT second opinion from the Kiro CLI run strictly READ-ONLY — a separate reviewer runtime over the real diff, with no write access to the repo. Reads the real diff (branch, a commit, or uncommitted) to build a focused prompt, optionally injects the stack's convention skills (`--skill`, since kiro can't load them itself), then launches kiro via the bundled helper with trust scoped to `fs_read,execute_bash` so it can grep/git to verify findings but never edit. Never uses `--trust-all-tools` (the auto-mode classifier dead-ends read-only tasks on it) or hand-rolls the prompt through the shell; keeps secrets out, treats findings as candidates to verify, and reports an explicit clean result. Use only on explicit user intent or when a user-invoked workflow composes it as the kiro reviewer.
Stand up and run a LinkedIn employee advocacy program for a marketing or sales team. Covers 14-day launch playbook, brand-guideline governance, per-post time budget, cadence benchmarks, and team ROI (reach, engagement, pipeline). Triggers on \"employee advocacy\", \"get the team posting\", \"scale LinkedIn across team\", \"advocacy ROI\". Not for planning one person's own calendar (use linkedin-content-planner).
This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek, OpenRouter) using SwiftOpenAI-CLI. Use this skill when users ask to "use grok", "ask grok", "use groq", "ask deepseek", or any similar request to query a specific LLM provider in agent mode
Read a local source file or synthesize conversation context, then integrate admitted content directly into topic, entity, concept, and analysis pages in existing memory (the wiki substrate). Use this when the user wants to add a source to the wiki, add a document, ingest a local note, transcript, article, report, or PDF, or explicitly preserve the current conversation as a topic note. For session-learning routing across wiki, guidance, checkpoint, task annotation, or discard, use /loam::learning-from-session. Must not ingest a goal wholesale; admit only independently reusable findings.
Helps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively. Use when the user says "managing up," "my manager," "I disagree with a decision," "I need to push back," "my skip level," "communicating with leadership," "my manager committed my team without asking," "how do I tell my boss," or "senior leadership." Do NOT use for influencing peers or cross-functional stakeholders (use influence) or for general EM self-reflection (use managing-yourself).
Install and wire markstream-vue, markstream-react, markstream-vue2, markstream-angular, markstream-svelte, or markstream-solid into an existing repository. Use when Codex needs to choose the right package, install the smallest framework-specific peer-dependency set, fix CSS/reset order, choose Vue 3 renderer mode and built-in, plain, or custom code-block paths, decide between `content`, `nodes`, and Vue 3 virtual-scroll coordination, or add a minimal working renderer example.
Analyze data using MATLAB. Use when the task involves tables, timetables, time-series data, numeric arrays, sensor matrices, or gridded data — including but not limited to exploring, row filtering, sorting, cleaning, transforming, aggregating, smoothing, padding, trimming, and answering questions about data. MATLAB provides extensive, easy-to-use built-in functions for these workflows with no additional products required.
Review and apply annotations left on a Markdown file with mdnote (highlight-and-comment review for .md files). Trigger when the user says "I left notes", "check my annotations", "review my notes on <file>", asks you to look at feedback on a doc, or after you've pointed the user at a Markdown file for review.
Plan, prompt, iterate, edit, migrate, and quality-check still-image work made with Midjourney's documented website and Discord interfaces. Use for Midjourney model and parameter selection, image/style/Omni references, Draft or Conversational workflows, typography-aware production, privacy and rights review, or troubleshooting a Midjourney image pipeline; do not use it to invent or automate an unsupported Midjourney API.
Use this skill to author new custom Jetpack Compose modifiers and migrate legacy ones from Modifier.composed { } to Modifier.Node + ModifierNodeElement<T>. Covers the persistent-node lifecycle (onAttach, onDetach, onReset, coroutineScope), the specialized node interfaces (DrawModifierNode, LayoutModifierNode, SemanticsModifierNode, PointerInputModifierNode, CompositionLocalConsumerModifierNode, LayoutAwareModifierNode, GlobalPositionAwareModifierNode, ObserverModifierNode, DelegatingNode, TraversableNode), why ModifierNodeElement MUST be a data class for diffing, and the manual-invalidation knobs (invalidateDraw, invalidateMeasurement, invalidatePlacement, shouldAutoInvalidate). Use when the developer mentions Modifier.composed, custom modifier, ModifierNodeElement, Modifier.Node, "rewriting our drawBehind helper", node lifecycle, or sees Modifier.composed { } in a code review.
Launch and manage the OpenClaw Dashboard web UI for monitoring all your bots, agents, models, and sessions. Automatically detects OS, checks for updates, installs dependencies, and starts the development server. Supports macOS, Windows, and Linux with automatic git detection and fallback download methods. Triggers include "打开机器人大盘", "打开 OpenClaw-bot-review", "打开Openclaw大盘", "打开 bot review", "open openclaw dashboard", "open OpenClaw-bot-review", "open bot dashboard", "open bot review", "launch bot review".
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
Infrastructure as code with OpenTofu (open-source Terraform fork) and Pulumi. Covers OpenTofu HCL syntax, providers, resources, data sources, modules, state management with remote backends, workspaces, importing existing infrastructure, plan/apply workflow, variable management, output values, provisioners, and state encryption (OpenTofu-exclusive). Includes Pulumi TypeScript/Python SDKs, stack management, component resources, config/secrets, state backends, policy as code, and automation API. Common patterns for multi-environment setups, module composition, CI/CD integration, drift detection, and secret management. Use when writing or reviewing HCL configurations, managing cloud infrastructure state, migrating from Terraform to OpenTofu, building Pulumi programs in TypeScript or Python, setting up multi-environment IaC pipelines, or implementing state encryption.
Use this skill to diagnose and fix Jetpack Compose Modifier ordering bugs — wrong paint region for background, wrong click area for clickable, wrong clipping for clip, wrong measurement for padding/size, surprising graphicsLayer scope. Covers the wrap-the-next-modifier mental model, the canonical pitfalls (padding vs background, clickable placement, clip before background, graphicsLayer placement), and why hoisting an entire Modifier chain via remember { Modifier.… } is rarely a real perf win because Compose already interns identical chains. Use when the developer asks "why does the click area extend past the visible button", "why is my background painted in the wrong place", "does Modifier order matter", "should I cache my Modifier chain", or reviews a diff that reorders modifiers.
OpenTelemetry in Go — SDK setup, API surface, breaking changes, contrib instrumentation libraries (otelhttp, otelgrpc, otelmongo), compile-time zero-code instrumentation (otelc), and performance tuning. Use when adding, reviewing, or configuring OpenTelemetry in a Go service. Triggers on "setup otel in go", "go telemetry", "go tracing", "otelconf go", "otelhttp", "otelgrpc", "TracerProvider go", "MeterProvider go", "otelc", "compile-time instrumentation go", "zero-code go instrumentation", "go build instrumentation", or any Go-related OTel question.
Agentic pair programming — drive a change together with a human partner in the loop, narrating intent and pausing at decision points. Use when the user wants to work side-by-side rather than hand off a whole task. Calibrated by three dials (role, detail, autonomy) and an always-on challenge mandate.
Comprehensive Pandas toolkit for construction data analysis. Filter, group, aggregate BIM elements, calculate quantities, merge datasets, and generate reports from structured construction data.
Make a papercut reel, video or explainer end to end. Short vertical (9:16) cut-paper explainers from a link (repo, product page, announcement), idea to mp4. Also routes partial asks to the stage skills and hands out the style prompt for other tools
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
Use this skill when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references.
The sole global workflow control plane for Phaser 4 game repositories; classifies and handles local work according to the current task scope and deterministic risk, and requires precise explicit approval only for side-effecting A4–A6 operations and their impact.
Skill for creating new PPTX, PDF, and PNG files with Presenton. Use this skill whenever a user asks for a PowerPoint, presentation, slide deck, pitch deck, report deck, PDF, presentation PDF, PNG slide, slide image, or exported deck, even when Presenton is not mentioned. Use a concrete design brief from the user when provided; otherwise search Presenton designs, upload user-provided images, search Presenton icons, generate 1280x720 HTML with HTTPS asset URLs, export requested formats—or all three formats when none is specified—and return download URLs plus a shareable presentation-preview link.
Debugs PyTorch 2 compiler stack failures, including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches. Use for torch.compile errors, BackendCompilerFailed exceptions, recompilation issues, Triton kernel failures, FX graph problems, or debugging PT2, Dynamo, Inductor, or compiled model issues.
Call the Pudu cloud OpenAPI to dispatch robot tasks, query status, handle delivery, patrol, calls, and analyze statistical data. First check the credentials and cluster environment variables; if any are missing, ask the user to provide them. Then call the appropriate interface based on the user's intent and display the results. Use this skill when the user mentions keywords such as “Pudu robots,” “pudu,” “dispatch robot task,” “query robot status,” “delivery task,” “patrol task,” “call robot,” “lifting task,” “errand,” “Lightning Box,” “ad playback,” “ad configuration,” “cabinet task,” “cabinet SKU,” “product SKU,” “cabin photo,” “traffic control zone,” “map list,” “statistics,” “risk avoidance,” “dashboard overview,” or “OpenAPI.”
Двусторонняя сверка кода и графа — уборочный такт: всюду ли код соответствует графу, а граф — коду; конец каждой сущностной задачи. Триггеры: reconcile, «сверь код с графом», «приведи граф в порядок», «протки свою область», «отдай долги графа», does the graph match the code, tidy the graph. Также: задача, записанная крией; феномен-ярлык состояния; комментарий-портянка, пересказывающая граф. Distinct from weaving (ремонт графа изнутри), integrity (claim-аудит), reality-audit (поведенческие заявки). Композирует entry, writing, weaving. Нужны тулы iskron_*.
Diagnose and fix 3+ genuinely independent failures concurrently on Claude Code’s real parallel agent runtime, without splitting one root cause into conflicting investigations. Proves failures do not share a root cause (same dependency/config/migration/deploy across traces) before launching, matches each lane to the best specialized agent, briefs it with real evidence (failing output, stack traces, test names), launches all lanes in one message with background execution and worktree isolation, then reruns each original failure and checks for conflicts. Refuses to parallelize fewer than 3 lanes or symptoms that may share a cause, consolidates lanes that converge on one root cause instead of claiming independent wins, and reports partial success honestly. Use when the user gives 3+ clearly independent failures to fix in parallel.
Same behaviour in fewer, clearer lines — covers the judgment gaps that linters cannot catch (reinvention, wrong frame, hidden duplication, derived state, procedural rebuilds, speculative generality, defensive excess, type-system underuse). Trigger when reviewing, refactoring, or simplifying code — and even when the user doesn't explicitly ask for "simplification" but is reviewing code, refactoring, or asking "is there a shorter way to write this?". Complements knip/eslint/ruff/tsc by focusing on the conceptual modelling layer those tools cannot see.
Conventions for adding or editing the SceneMenuBar above a scene's <SceneTitleSection>. Use when adding new menu items, moving items between menus, gating behind feature flags, building a new scene's menubar, or wiring rich inputs (tags, combobox) into the bar.
Manage local service credentials without ever exposing their values. The `secrets` CLI adds, rotates, lists, enables, disables, and inspects encrypted integrations (including MCP/agent tooling) through interactive entry, reporting only service names and enablement status. Hard invariant: secret material never enters arguments, logs, or output, and `--reveal` is never used; reports show the service, not the value. Use only on explicit request to wire or inspect credentials.
Review FastAPI security audit patterns for dependencies and middleware. Use for auditing auth dependencies, CORS configuration, and TrustedHost middleware. Use proactively when reviewing FastAPI apps. Examples: - user: "Audit FastAPI route security" → check for Depends() and Security() usage - user: "Check FastAPI CORS setup" → verify origins when allow_credentials=True - user: "Review FastAPI middleware" → check TrustedHost and HTTPSRedirect config - user: "Secure FastAPI API keys" → move from query params to header schemes - user: "Scan for FastAPI footguns" → check starlette integration and dependency order
Information security expertise for cybersecurity frameworks (NIST, ISO 27001), security architecture, incident response, vulnerability management, identity management, and cloud security. Use when designing security programs, responding to incidents, or assessing vulnerabilities.
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.