Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Improve existing test suites into minimal, high-signal behavior-focused harnesses with approval-before-mutation, conformance checks, guarded validation, bounded repair, and auditable handoffs. Use when asked to improve, trim, rewrite, delete, review, or harden tests around public contracts, business logic, schemas, security behavior, failures, edge cases, readability, or maintainability.
Assess Splunk indexer-cluster membership, factor and searchability state, bucket fix-up evidence, cluster-bundle distribution, rolling-maintenance readiness, multisite behavior, and SmartStore interactions without changing a deployment. Use for cluster-manager or peer health, unmet replication or search factors, incomplete searchability, persistent fix-up, cluster-bundle state, rolling readiness, and cluster-specific incident routing. Preserve Cloud, Enterprise, evidence-collection, storage-design, upgrade-planning, and active-operations boundaries.
Runs continuous AI iteration loops that repeat build-test-fix cycles until success criteria are met. Use when building features requiring test-driven refinement, implementing tasks with clear pass/fail criteria, or automating iterative improvement workflows.
Manage Keeper Vault, enterprise administration, PAM, and privileged access using Keeper Commander CLI (keeper). Use when the user needs to manage vault records interactively, run enterprise admin tasks (user/team/role management, SSO config, device approvals, compliance reporting), manage KSM Applications and Client Devices, configure password rotation, launch remote sessions (SSH, RDP, database), import/export data, or perform any administrative operation on Keeper. Also use when the user mentions 'keeper commander', 'keeper shell', 'keeper admin', asks about managing users/teams/roles/nodes in Keeper, needs to create KSM applications, or wants to automate Keeper admin tasks. If the user only needs to retrieve or inject secrets for an application, use the keeper-secrets skill instead.
Use for Lanhu (蓝湖) UI design handoffs and lanhuapp.com design project links: list design screens, inspect screenshots and HTML/CSS specs, extract design tokens, download slices/assets, or implement UI. Trigger when the request explicitly mentions 蓝湖, Lanhu, lanhuapp.com, or the bundled Lanhu scripts. Do not use for standalone Figma/Sketch files, generic UI implementation, PRD/Axure docId links, or image editing unrelated to Lanhu.
Chinese thesis defense deck builder for existing XeLaTeX PhD or master thesis repositories. Extracts chapters, figures, equations, tables and publications read-only, plans pages by talk length, renders a Beamer pre-defense or defense deck with speaker notes, and runs a fidelity quality gate plus page previews. Not for .pptx, journal talks, or English defenses.
Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search). Supports MCP tools or the workspace-cli client. Provides tool routing, workflows, and parameter guidance for every tool. Triggers for "check my email", "find a file", "schedule a meeting", "update the spreadsheet", "share a doc", "create a presentation", "add a task", "look up a contact", or any mention of Google Workspace services.
Use when auditing, restructuring, or revising a research manuscript whose scientific question, claim hierarchy, evidence chain, section logic, figures, terminology, or prose may be unclear or out of sync. Apply before sentence-level polishing, especially for whole drafts, major revisions, resubmissions, overclaiming, experiment-by-experiment Results, inaccessible narratives, or manuscripts that need a claim-driven architecture.
Build MATLAB apps from requirements to working code. Asks discovery questions (or skips them when the path is known), recommends UIFigure or UIHTML architecture, identifies layout archetype (Dashboard, Explorer, Tabbed, Wizard, Canvas), produces an implementation plan, and executes the build. For UIFigure apps, optionally serializes as App Designer (.mlapp or plain-text .m + .xml). Use when a user wants to build a MATLAB app, create a GUI, make an interactive tool, build a uifigure app, build a uihtml app, build an App Designer app, build a .mlapp app, build a plain-text App Designer app, or asks which approach to use. Also use when user describes spatial layout needs: dashboard, control panel, sidebar, tabs, wizard, stepper, canvas, workspace.
Create, edit, and run plain-text MATLAB live scripts (.m files) with rich text formatting, LaTeX equations, section breaks, and inline figures. Use when generating tutorials, analysis notebooks, reports, documentation, or educational content, when modifying existing live scripts, or when converting existing binary .mlx files to .m for version control. Requires R2025a+.
General-purpose automated publishing tool for self-media articles. Supports automated publishing workflows for six platforms: Baijiahao, Sohu, Zhihu, WeChat Official Accounts, Xiaohongshu, and Douyin. Uses Playwright automation for platform navigation and publishing, and supports account switching by managing cookies via storageState.
Semantic search over agent memory files. Use when you need to find conceptually related memory blocks, discover forgotten reference files, check what you already know before creating new memory, or search beyond exact keyword matching. Currently supports QMD (local, no API keys).
Write modern, version-aware C# for .NET repositories while staying compatible with the repo's target framework and language-version policy. USE FOR: modern idiomatic C# code; language-version compatibility decisions; upgrading or reviewing C# feature usage across versions. DO NOT USE FOR: non-C# .NET languages such as F# or VB; analyzer-only or formatter-only setup with no language feature choice. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Creative direction and design intelligence for Remotion motion graphic videos. Use when an agent needs to (1) convert a script or SRT into a shot-by-shot visual design document, (2) ideate motion graphics with editorial intent for each scene, (3) produce a design brief for user approval before writing Remotion code. Always use before generating any Remotion video code from a script.
Image generation skill. Use when the user needs to generate images, visual infographics, create images, or edit/modify/adjust existing images. An image generation service based on the NanoBananaPro model on China's API易 proxy site (https://api.apiyi.com/), with no need to access the external internet. Supports 10 image aspect ratios (`1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`, etc.) and 3 resolutions (1K, 2K, 4K), and supports text-to-image and image-to-image editing. Based on Google's NanoBananaPro model (fast model), accessed via API易's domestic proxy service.
Offensive testing of perimeter network appliances and VPN crypto — IKE/IPsec (aggressive-mode, transform/DH enum, NAT-T), Check Point SIC/OPSEC, safe firmware/patch-level inference for FortiGate/PAN-OS/Cisco ASA/Citrix feeding CVE applicability, NTLM Type-2 target-info decode, handshake-completion TLS-version probing, and an RST-TTL forgery discriminator. The active/offensive counterpart to the static firewall-review skill. Use when a perimeter firewall/VPN/appliance is in scope and you must test it (not just audit a config), without reinventing raw-socket protocol tooling each engagement.
Build OpenTelemetry collector configs, instrument services, transform telemetry with OTTL, and debug missing traces, metrics, or logs. Use for OTel/otelcol collector config, OTLP export, SDK instrumentation, sampling, cardinality, TLS/PII controls, Kubernetes/Helm values.yaml deployments, collector health and alerts, and AI coding-agent telemetry (Claude Code, Codex, Gemini CLI, Antigravity, GitHub Copilot, Cursor).
Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for “instrument my code”, “add opik tracing”, “add observability”, “trace my agent”. Not for building a new app from scratch, or a review-only pass with no code changes.
Use whenever the user wants to obtain, download, or fetch a paper's PDF — given a DOI, an arXiv id, a paper title, a citation, or a list of DOIs. Trigger on phrases like "download this paper", "find the PDF for [DOI]", "grab me the [Nature/bioRxiv/arXiv] paper on X", "get the open-access version", "I need this article", or any bulk/batch paper download request, even when the user doesn't explicitly say "PDF" or "DOI". Resolves via Unpaywall → Semantic Scholar → arXiv → PubMed Central → bioRxiv/medRxiv → publisher direct (institutional opt-in) → Sci-Hub mirrors as last-resort fallback.
Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden assumptions, and connections to the user's other work. Use when the user shares an arXiv link, PDF, or paper title and asks to read / summarize / digest / TL;DR / analyze / review / critique / explain / break down a paper, asks about a paper's contributions / methods / results / equations / figures, wants to compare two papers side by side, or needs a reading note for their records.
Use when the user asks about Pionex Dual Investment (earn dual): listing supported pairs or products, checking yield rates or index prices, querying balances or investment history, placing or revoking an investment, or collecting settled earnings. Do NOT use for spot trading (pionex-trade), futures grid bots (pionex-bot), or market price/depth data only (pionex-market).
Write and review content for plain language accessibility. Use when writing interface copy, error messages, instructions, onboarding text, help content, legal or medical information, forms, or any user-facing text. Triggers on: plain language, reading level, simplify text, jargon, hard to understand, nobody reads this, unclear copy, rewrite, too complicated, ESL, literacy, readability.
Access to Plain customer support platform. Read customers, threads, timeline, help center content, and broadcasts. Add notes to threads. Create, update, and publish help center articles. Draft broadcasts, manage broadcast audiences, and manage broadcast unsubscribes.
Orchestrate one-click generation of major and detailed plot points: preprocessing, extraction, refinement, and formatting. Use when a complete plot outline with point-by-point development is needed, or when a plot workflow or plot-point pipeline is mentioned.
Build or critique an audience-understanding artifact—research-based user personas, a Jobs-to-Be-Done framing, or the choice between them. Grounds the work in real research (never invented demographic fiction), keeps only detail that changes a decision, and picks the lens by research objective, stage, and resources. Applies the always-true core and gates context-dependent decisions (personas vs. JTBD vs. both, research-based vs. proto, how many personas, which details, segmentation depth, AI's role). Trigger when asked to create user personas, define a target audience/segment, apply Jobs-to-Be-Done, decide who the product is for, or review existing personas.
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' or 'should I offer a free plan.' Use this whenever someone is figuring out what to charge or how to structure their plans.
Translate privacy principles and legal requirements into data-flow, lifecycle, acceptance, and verification artifacts. Map data classification, purpose, processing, access, retention, deletion, residency, and consent; define verifiable privacy acceptance criteria; and produce data-lifecycle records, retention/deletion verification plans, and privacy change reviews. Use when engineering privacy into a system, feature, or data flow — not for legal advice, jurisdiction-specific regulatory interpretation, or replacing security engineering or incident response.
Product naming collaboration workflow. Use when the user wants to name a product, project, or module. Through the structured process of "soul mining → constraint extraction → option divergence → direction selection → competitor validation → final confirmation", it produces names with brand vitality from vague ideas and avoids off-the-cuff naming.
Promotes a handover test to the regression or smoke test suite. Renames the file to remove the ticket prefix, moves it to the target directory, and updates the test.describe block. Use when asked to promote, graduate, or move a handover test to regression or smoke.
Tests LLM applications for prompt injection vulnerabilities per OWASP LLM01:2025. Covers direct injection (user input manipulating model behavior) and indirect injection (external content containing hidden instructions). Auto-invoked when reviewing LLM applications that process external content, build RAG pipelines, or accept user input that reaches a language model. Produces a test report with categorized findings and defense recommendations.
Provide concise, goal-aligned suggestions before generating or optimizing image, video, audio, GPT Image, or storyboard prompts. Use when the user asks for advice, direction, risks, alternatives, or "how should this prompt be improved" before producing the final prompt. This skill gives suggestions only and should not replace the main prompt-building skill.
Code quality gatekeeper and auditor. Enforces strict quality gates, resolves the AI verification gap, and evaluates codebases across 12 critical dimensions with evidence-based scoring. Use when auditing code quality, reviewing AI-generated code, scoring codebases against industry standards, or enforcing pre-commit quality gates. Use for quality audit, code review, codebase evaluation, security assessment, technical debt analysis.
Implements retrieval-augmented generation pipelines. Use when building document retrieval systems, choosing chunking strategies, selecting embedding models, configuring vector stores, implementing hybrid search, or evaluating RAG quality. Use for embedding strategy, vector stores, retrieval pipelines, chunking, hybrid search, re-ranking, multi-query retrieval, parent document retrieval, contextual compression, MMR diversity selection, reciprocal rank fusion, and evaluation. For KB architecture selection and governance, use the knowledge-base-manager skill. For knowledge graphs, use the knowledge-graph-builder skill.
Use when rendering a Markdown document (English or Korean) such as a proposal, IRB cover letter, handout or reference table to PDF via pandoc and xelatex, with auto-fitted table widths and CJK fonts. Not for manuscripts with a bibliography (/manage-refs) or Word forms.
Maintain repository integrity and documentation. Use for auditing structure, checking config validity, and reviewing inventory. Use proactively to validate the repository or sync documentation. Examples: - user: "Validate the repo" → run audit_repo.py - user: "Check agents" → run audit_repo.py, review errors - user: "Update documentation" → run sync_docs.py - user: "Check for issues" → run full audit
Produces a standardized requirements brief from any source: DevOps work items, mockups, natural language descriptions, existing reports, or documents. This is a utility skill — it gathers and structures requirements but does not build anything. If the goal is to create a report, datasource, or other artifact, use the appropriate creation skill as the entry point; it will invoke this skill when it needs requirements.
Build risk-adjusted return-optimized A-share portfolios for Chinese investors, with asset allocation based on capital size, risk appetite, and investment horizon. Use this skill when users ask about building portfolios, asset allocation, A-share portfolio optimization, position management, or rebalancing strategies, or request portfolio construction advice based on a specific amount and risk appetite.
Security hardening and best practices for robotic systems, covering SROS2 DDS security, network segmentation, secrets management, secure boot, and the physical-cyber safety intersection. Use this skill when securing ROS2 communications, configuring DDS encryption and access control, hardening robot onboard computers, managing certificates and credentials, setting up network segmentation for robot fleets, or addressing the unique security challenges where cyber vulnerabilities become physical safety risks. Trigger whenever the user mentions SROS2, DDS security, robot security, robot hardening, ROS2 encryption, ROS2 access control, robot network security, secure robot deployment, robot certificates, keystore generation, robot firewall, e-stop security, safety controller isolation, or IEC 62443 for robotics.
Plan, execute, audit, and verify behavior-preserving migrations from Java Maven or Gradle projects to project-shaped Rust Cargo workspaces, including derived crate boundaries, scale-appropriate topology, 100% lossless source-test/case migration, byte-identical test assets, and complete per-case differential parity. Use when comparing repositories at module, package, object, file, method, parameter, documentation, example, test, fixture/data, dependency-reuse, JavaBean/script-property, concurrency, runtime-behavior, oversized Rust-file, or test-organization level; producing migration documents; continuing an incomplete port; or repairing workspace drift. Enforces source-authoritative inventories, Rust-native APIs, a 500-line cohesion-review threshold and 800-line authored-file blocker, idiomatic unit/integration test placement, strict non-completion states, frozen baselines, and unified verification.
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.
