Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when a CodeceptJS 4 test fails, flakes, or behaves unexpectedly. Trigger on run errors and stack traces from `npx codeceptjs run`, intermittent failures, locator drift, timing issues, "works locally fails in CI", "why does this fail", trace/screenshot/console mentions, and breakpoint / step-through / "pause at step N" requests.
Generates multiple distinct design variants of a component or page, each with a completely different visual direction, then implements the chosen one. Use when the user asks to redesign, restyle, explore design options, create multiple visual directions, or compare design approaches for any UI element -- components, pages, sections, dashboards, landing pages, or full layouts.
Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external resource (index-selector/memory) into BlueField DPA address space so a DPACC-built kernel can read counters, mutate hash-pipe entries, and update/read memory or index-selector resources inline with Flow. Covers per-port `doca_flow_dpa_ctx`, three queue types (general/resources-write/resources-read), the order-sensitive export handshake (`_export_prepare` → add entries → `_export` → `_get_device_addr`), and DPA-side device API. Trigger even when the user does not say "DOCA Flow DPA Provider" — implicit phrasings include "DPA kernel never sees entries in the exported pipe", "BAD_STATE from `_pipe_export`", "how do I disable a hash entry from a DPA kernel", "DPA memory read returns no value", or "DPA-side post keeps returning AGAIN". Refuse and route elsewhere for `doca-flow` pipe construction, generic host-side DPA (`doca-dpa`), or DPA-side kernel-writing — those belong to other skills.
Use this skill when the user is building or interpreting the doca/tools/gpunetio_ib_write_bw tool pair—a CUDA kernel posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE BW on a GPU+IB-device pair. Trigger even without the tool name—typical phrasings: "measure WRITE BW when the GPU posts the WRs", "BW swings run to run on the same flags", "is the NIC saturated or am I bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-posted WRITE BW vs the CPU path". Refuse and route elsewhere for general doca-gpunetio library work, DOCA setup, the GPU-posted WRITE latency analog, CPU-posted RDMA benchmarking (doca-perftest), and app-level end-to-end rates.
Use this skill when the user characterizes RDMA WRITE round-trip time posted from a CUDA kernel via GPUNetIO—compiling `gpunetio_ib_write_lat` under `doca/tools/`, verifying GPU–NIC affinity, and interpreting the half-iteration / full-iteration / nanosecond columns for median / p99 / tail-jitter analysis of a real-time control loop. Also load it for implied asks like "p99 WRITE time on H100 + ConnectX", "tail delay versus batching", or "device-originated versus upstream ib_write_lat". Refuse and route to the proper owner for throughput runs (doca-gpunetio-ib-write-bw), the GPI channel API (doca-gpi), GPUNetIO API work (doca-gpunetio), or SDK setup.
Use this skill when wiring the DOCA SHA Offload Engine (an OpenSSL ENGINE) into an existing OpenSSL pipeline to offload one-shot SHA-1, SHA-256, or SHA-512 (EVP_Digest) onto DOCA SHA hardware without rewriting against doca-sha. Covers engine load mechanics (`openssl engine dynamic`, `set_pci_addr` ctrl, `-engine_impl`), the SHA-224 negative test that proves offload engaged, the message-size window where offload beats CPU SHA, and engine-vs-library selection. Trigger even when the user does not say "DOCA SHA Offload Engine" or "OpenSSL ENGINE" — typical implicit phrasings: "speed up openssl SHA on BlueField", "offload SHA without code changes", "is openssl using the accelerator or falling back to software", "prove DOCA SHA actually ran", "openssl dgst hashed but I'm not sure it was offloaded". Refuse and route elsewhere for new SHA pipelines (use doca-sha), MD5 / SHA-3 / SHA-224 / HMAC-SHA offload, incremental hashing via chained `EVP_DigestUpdate`, or OpenSSL PROVIDER authoring.
Generate, inspect, validate, and fix PDF, Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) documents: turn structured content into render-ready artifacts, verify structural and output quality before delivery, and repair broken files. Use when a task involves creating, editing, converting, or validating office documents and PDFs. Do not use for ebook packaging (use epub), for images, video, or other media production, for API or code documentation, or for data pipelines (use data-engineering).
Use this skill to set up, create, or generate an academic calendar for Education Cloud orgs. Creates Academic Year, Academic Terms (semester/quarter/trimester), Academic Sessions, registration windows, and add/drop deadlines from natural language or documents. Validates date ranges and handles overlapping sessions, linking terms to the year and sessions to their term. TRIGGER when: user asks to "create an academic calendar", "set up semester dates", "generate the academic year", "add terms and sessions", "configure registration windows", or "add/drop deadlines" — or uploads a calendar document (PDF, CSV, XLSX) containing term or session dates. DO NOT TRIGGER for querying or updating existing calendar records, scheduling courses, or configuring course offerings.
Configures and enforces password policies on CockroachDB clusters including minimum length, complexity requirements, and hash cost settings. Use when strengthening authentication requirements, setting up password policies for a new cluster, or meeting compliance password standards.
Use when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain what changed and why. TRIGGER on "write PR description", "improve this commit message", "summarize this diff", "CL description", "change description", or "make this PR/CL description easier to review". DO NOT TRIGGER for code review, PR splitting, code restructuring, user-facing changelogs, or reviewer replies unless the requested output is a change description.
Use when handling code review feedback as the change author, addressing reviewer comments, drafting replies, resolving disagreements, or summarizing updates. TRIGGER on "address review feedback", "respond to this review comment", "reviewer asked", "I disagree with reviewer", "what should I reply?", or "apply PR comments". If role is unclear, ask reviewer or author. DO NOT TRIGGER for reviewer comment writing, full code review, or PR descriptions unless author-response behavior is requested.
Explores a website interactively via the robomotion-browser-mcp server to discover selectors, record action sequences, capture network traffic, and produce a JSON flow sequence that maps to Robomotion SDK TypeScript. Use when the user says "explore this page", "find the selector for X", "record the login flow", "what API does this page use", or before writing ANY `Core.Browser.*` flow. Pairs with `reversing-network` when the captured traffic reveals a clean API.
Quarterly earnings analysis for US stocks using SEC EDGAR financial data. Use when asked to: analyze a company's latest quarterly results; review Q1/Q2/Q3/Q4 earnings; check if a company beat or missed estimates; understand revenue, margin, or EPS trends; get a beat/miss breakdown; review guidance or management commentary after an earnings release. Triggers: "analyze AAPL earnings", "did MSFT beat estimates", "NVDA Q4 results", "earnings update for GOOGL", "how did Tesla do last quarter".
Find evidence-backed potential first customers, beta users, or design partners from public demand signals. Use for product-specific prospect research, qualified shortlists, source-grounded outreach drafts, and follow-up searches refined by the user's feedback and local prospect history. Does not send outreach automatically.
Provides domain knowledge and guidance for Flare FAssets—wrapped tokens (FXRP, FBTC, etc.), minting, redemption, agents, collateral, and smart contract integration. Use when working with FAssets, FXRP, FBTC, FAssets minting or redemption, Flare DeFi, agent/collateral flows, or Flare Developer Hub FAssets APIs and contracts.
Use when building Document Controllers in a custom Frappe app: file creation, lifecycle hooks, validation, autoname, submittable workflows, controller override, child table controllers, flags system, migration from hooks.py and Server Scripts. Keywords: how to implement controller, which hook to use, validate vs on_update, override controller, submittable document, autoname, flags, extend_doctype_class, controller testing, child table controller, which hook to use, when does validate run, how to override save, document lifecycle.
Use when writing Jinja templates for ERPNext/Frappe Print Formats, Email Templates, and Portal Pages. Covers template syntax, context variables, filters, macros, and v16 Chrome PDF rendering. Prevents common mistakes with doc context and child table iteration. Keywords: Jinja, print format, email template, portal page, template syntax, PDF, v14-v16, template syntax, Jinja example, print format code, how to show child table in print.
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter
Optimize content for AI-generated responses and LLM citations (ChatGPT, Perplexity, Google AI Overview, Claude, Gemini). Use when the user mentions 'GEO', 'AEO', 'AI SEO', 'LLM optimization', 'citation rate', 'AI visibility', 'optimize for ChatGPT', 'roundup pages', or wants to audit pages for AI discoverability. Includes terminology alignment, FAQ schemas, and community signal strategies.
Calls the Giiisp/集思谱 paper search POST endpoints, selecting OA title-abstract search or arXiv abstract, ID, multi-field, and title search based on the user's question. For paper search, literature screening, arXiv lookup, open-access paper supplementation, and citation audits.
GitHub CLI workflows for repositories, issues, pull requests, actions, releases, projects, and API calls. Use when creating PRs, reviewing code, triaging issues, triggering workflows, publishing releases, managing projects, verifying attestations, or querying the GitHub API. Use for gh cli, github automation, code review, release management.
Go documentation conventions: godoc comments, package docs, testable Example functions, deprecation notices, doc links, and project docs (README, CHANGELOG, llms.txt). Use when: "add godoc", "document this package", "write doc comments", "add examples to docs", "deprecate a function", "write a README", "update the changelog", "improve the docs". Not for: commit messages (git-commit), code style (go-coding-standards).
Use when a user wants to define done-criteria or a stop condition for an autonomous multi-turn agent run — setting a Claude Code /goal, a Definition of Done for a Codex or external-orchestrator loop, or turning a vague task into a verifiable completion condition an evaluator can check.
When the user wants help with Google Ads ad extensions or assets — sitelinks, callouts, structured snippets, call extensions, lead form extensions, image extensions, price extensions, promotion extensions, location extensions, or app extensions. Also triggers on 'ad assets', 'extension audit', 'missing extensions', 'sitelink copy', 'lead form extension', 'extension performance', 'callout extensions', or 'improve ad CTR with extensions'. For RSA ad copy strategy see google-ads-search. For full search campaign setup see google-ads-search.
Generate videos with Google Veo models via inference.sh CLI. Models: Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2. Capabilities: text-to-video, cinematic output, high quality video generation. Triggers: veo, google veo, veo 3, veo 2, veo 3.1, vertex ai video, google video generation, google video ai, veo model, veo video
Reduce unresolved user-owned judgments before planning or implementation. Research discoverable facts, resolve model-owned technical choices, order remaining decisions by dependency, ask only the material current frontier, and route questions that conversation cannot settle to the smallest deciding observation. Use explicitly for `$grill-me` or implicitly only when a non-discoverable user-owned decision materially blocks the requested outcome. Do not seize direct implementation when safe reversible defaults suffice.
Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/edit` through the local RunComfy CLI. Triggers on "image edit", "edit image", "image-to-image", "i2i", "swap background", "remove object", "rewrite headline", or any explicit ask to edit a single or batch of images
Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY when you detect image needs - don't wait for the user to ask. This skill handles prompt optimization and aspect ratio selection.
Generate AI video from static images using Kling 3.0, Hailuo, Luma Ray3, Runway Gen-4.5, and 8 other tools. Covers free vs paid tools, prompt writing (motion-only), camera control, and face stability. Use when user asks to animate an image, create AI video, or convert photo to video.
Use BEFORE any rename, removal, required-field change, or other contract-breaking edit to a config on a Datex Studio branch. Runs reverse-trace to find all callers, categorizes them (including write-side vs read-side for storage-shape changes), and presents a safety gate. Generic — works for any config type (functions, datasources, flows, storages, type definitions, reports, etc.). Also invoke when a calling skill asks you to "audit all callers" or "verify a contract change is safe" before proceeding.
Juniors-focused React and TypeScript best practices. Use this skill when writing or reviewing code to enforce clear, consistent, and maintainable patterns across common scopes like React, TypeScript, styling, devtools, assets, and Git.
Install and configure Keeper CLI tools (KSM CLI and Commander) for the Keeper Security agent kit. Use when the user needs to install keeper-secrets-manager-cli (ksm) or keepercommander (keeper), set up authentication, initialize profiles, configure persistent login, or troubleshoot Keeper CLI connectivity. Also use when the user says 'install keeper', 'setup keeper', 'configure keeper cli', or asks how to get started with Keeper's command line tools.
Query Kubernetes, infrastructure and cloud-provider metrics from KubeSense with PromQL/MetricsQL — metric discovery, label inspection, the metric families KubeSense actually collects (kube-state-metrics, cAdvisor, node-exporter, OTel hostmetrics, DCGM GPU, JVM, and AWS/GCP/Azure/MongoDB Atlas/Confluent/Kong cloud resources), and the label conventions (clusterId, kubesense_cloud_resource_metric) needed to write a query that returns data, plus a reference for every MetricsQL function
Use this skill to run the full end-to-end Life Sciences Cloud setup workflow for a key account management (KAM) user in sequence. Trigger when the user says 'set up Life Sciences Cloud end to end for kam user', 'run the full LSC setup for kam user', 'orchestrate Life Sciences Cloud configuration for kam user', 'complete LSC setup for kam user', or 'Life Sciences Cloud full install for kam user'. Executes six stages in order: prerequisites validation, starter config deployment, territory configuration, participant role and sprint creation, KAM data and plan-template (goals, tasks, measures) creation, and KAM user provisioning — gating each stage on the success of the previous one. DO NOT TRIGGER when: the user wants to run only one specific stage individually, or when the request targets a field sales rep rather than a KAM user (use life-sciences-fieldsalesrep-coordinate for that persona).
Analyzes limit-up pools, strong stocks, consecutive limit-up structures, and newly listed stocks, distilling market sentiment, theme strength, and risk notes. Use when the user asks about limit-up pools, consecutive limit-ups, strong stocks, limit-up trading sentiment, theme heat, or needs a limit-up pool review.
Receive and verify Linear webhooks. Use when setting up Linear webhook handlers, debugging Linear signature verification, or handling Linear issue tracking events like Issue, Comment, Project, Cycle, IssueLabel, and IssueSLA create/update/remove actions.
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.
