Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Writes portable upstream Kubernetes NetworkPolicy YAML - default-deny-all, DNS egress, namespace and pod selector rules - that works on any conformant CNI such as Calico or Cilium. Use when segmentation must stay CNI-portable, introducing a default-deny posture, or restricting east-west traffic between pods and namespaces without depending on a vendor CRD. Keywords: NetworkPolicy, default deny, podSelector, namespaceSelector, ingress, egress, CNI portable. Do not use for Calico-specific resources - use implementing-kubernetes-network-policy-with-calico.
Find high-value ways to deepen a codebase's modules, present them visually, and explore the chosen change. Use when the user asks to improve a codebase's architecture or find where its modules should be deepened or merged. For needless complexity in specific code, use `audit-code-complexity`.
Integrate Arcjet Guard into Cloudflare Think — delegate beforeToolCall to guardHooks so a DENY substitutes or blocks the tool, and read a caller-owned id via cloudflareThinkContext. Use when asked to add Arcjet to @cloudflare/think, Cloudflare Agents Think, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Cloudflare Think, not the Vercel AI SDK and not needsApproval HITL.
Collaborative workflow for handling GitHub issues. Use when a user receives an issue that needs analysis and a reply. Through the four-step method "diagnose → classify → decide → reply", it produces an accurate root-cause analysis and a professional user reply from a single issue, avoiding misjudging the problem type or giving an unprofessional reply.
Generates Tzatziki-based Cucumber tests (Gherkin .feature files) from a functional specification. Use this skill whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin — especially in Java/Spring projects. Use this skill for tests involving HTTP, relational database (SQL), JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions writing integration tests, acceptance tests, or end-to-end tests.
This skill should be used to watch a long-running background job (ffmpeg/media encode, qmd or other embedding/vector-DB run, batch agent/LLM pipeline, or a real-browser/agent-browser daemon) until it finishes or wedges, then deliver a verdict (done, needs-attention, or blocked) plus the exact next command, without burning dozens of manual poll commands. Triggers on "babysit this job", "watch this until it's done", "ping me when the encode/embed/batch finishes", "is this background process stuck", "monitor this ffmpeg/qmd run", or any request to wait on a long-running process and be told when it's complete or hung.
Fine-tune a Kev decision model (open Jev-style System One model) on a user's own workload and serve it with calibrated probabilities. Interviews the user, finds existing Jev/TypeSafe questions or labelled data in their codebase, generates enough synthetic training data to measure a gain, trains and calibrates on Modal, scores against the released checkpoint, deploys a TypeSafe-compatible endpoint, and tears everything down. Use when someone wants noul/choice/score questions answered on their own domain (routing, triage, moderation, classification, scoring), wants calibrated confidence for automation thresholds, mentions Jev, TypeSafe, System One or Kev, or asks to fine-tune, evaluate, deploy or clean up Kev.
Add a new tracked project (or a new category) to the mmontes11/knowledge-base `projects/` section, or update an existing project during a maintenance run. Create the fixed set of standard documents (README, api-reference, releases, features, optional architecture) populated and attributed from upstream, keep frontmatter fresh, register the project in the Tracked projects table, and push to main. Use whenever the user wants to add, track, or refresh a project in the knowledge base — "add <repo> to the knowledge base", "start tracking <project>", "update the <project> entry", "run the maintenance for <project>", "add a new category <x>" — even if they only name the upstream repository.
Answer questions about what the mmontes11/knowledge-base knows — a tracked project (what it is, its API surface, its latest release, its features, its architecture), a book in `books/`, or a foundational topic in `foundation/` — by reading the root README's index tables to locate the right folder and then reading the relevant file. Use whenever the user asks something the knowledge base could hold and wants the answer grounded in it — "what does <project> do", "what's the latest release of <project>", "how does <project>'s API work", "which projects does the knowledge base track", "what does the knowledge base say about <topic>", "summarize chapter N of <book>" — rather than from general knowledge.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies
Senior landing page designer specializing in high-converting pages for SaaS, apps, and services. Use when building landing pages, hero sections, pricing pages, or any conversion-focused marketing page. Always researches current best practices via Perplexity before designing. Includes AI slop detection and cleaning.
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Work with Lapian Notes / 拉片笔记 (github.com/bkingfilm/lapian-notes) — a local-first React/Vite tool that turns a film into an editable shot-by-shot study notebook: local frame extraction, AI-assisted structure analysis (bring your own AI, no API key required), story-line swimlane timeline, structure tree, and audience-emotion curve. Use when the user asks about Lapian Notes, "拉片笔记", "拉片" (shot-by-shot film analysis) tooling, cloning/running this repo (npm run dev, run.bat/run.command), the AI-analysis-package (ZIP) round-trip workflow, or contributing a PR to lapian-notes. Not for generic video editing (use `opencut` for that) or generic film-analysis theory unrelated to this codebase.
[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs ranked promotion candidates. This is the outer loop's inspect step — it turns raw learning data into actionable gap reports. Use on a regular cadence (weekly, before major tasks, or at session start for critical projects). Can be invoked manually or scheduled.
Apply this opinionated workflow when modernizing legacy systems: strangler fig pattern, branch by abstraction, characterization tests, incremental monolith decomposition, framework upgrades, feature-flagged migration with rollback.
Place a real product into a believable lifestyle or in-use scene (kitchen, bathroom, desk, outdoor, gym, bedroom, festive) for listing images, ads and social posts while keeping the product identical. Use for lifestyle scenes, lifestyle images, in-use photos, context shots.
Integrates Apache ECharts into UniApp and UniAppX projects for cross-platform data visualization (H5, mini-programs, native App). Supports line, bar, pie, scatter, radar, gauge, funnel, heatmap, and more chart types. Use when the user needs to create ECharts charts in UniApp/UniAppX or configure interactive data visualizations for mobile and web.
Scrapes Google Search AI Overviews (AI Overview / AI Mode) and returns the main search AI Overview highlights for a keyword. Suitable for in-depth research using up-to-date web information, technical Q&A, long-tail product research, and analysis of overseas consumer preferences. Supports single-turn conversations only; for follow-up questions, the agent must summarize the context and submit a new request. Trigger this skill when users mention Google AI, AI Overview, AI Mode, Google AI overviews, Google AI search, in-depth overseas research, long-tail product research, consumer preference analysis, web page highlights, Google AI search, AI Overview, AI Mode, deep research, or consumer preference analysis. Trigger it even if the user does not explicitly mention “Google AI”, as long as their request is to “search Google and summarize web page highlights with AI”.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Classifies LLM prompts and responses as safe or unsafe using Meta's LlamaGuard (7B v1, 8B v2 and v3) across six categories: violence and hate, sexual content, guns and illegal weapons, regulated substances, suicide and self-harm, and criminal planning. Covers HuggingFace Transformers and vLLM inference, a FastAPI moderation endpoint, Sagemaker deployment, and NeMo Guardrails integration. Use when filtering user prompts before an LLM call, moderating model outputs before display, serving a self-hosted moderation API, or reducing latency and GPU memory of a moderation model with vLLM or quantization. Use when tuning thresholds to cut false positives. For a simpler hosted option, use the OpenAI Moderation API instead.
Make websites, docs, blogs, or landing pages agent-friendly: visible and readable to LLMs and AI agents like ChatGPT, Perplexity, Claude Code, and Cursor. Use for requests involving llms.txt, llms-full.txt, serving .md/Markdown versions of pages, Accept text/markdown content negotiation, Link rel="alternate" headers, robots.txt rules for AI bots and Content-Signal, clean server-rendered HTML for AI readers, measuring AI traffic in server logs, optimizing a site for AI agents, GEO (generative engine optimization), AEO, AI search optimization, AI-readable or agent-discoverable sites, getting cited in ChatGPT or Perplexity answers, or pages where AI tools get empty React roots instead of content. Also use to push back on debunked patterns: ai.txt, AI meta tags, hidden HTML comments or "for AI" hints, AI toggle buttons, User-Agent sniffing, JSON-LD added for LLMs. Do NOT use for traditional Google SEO, sitemap.xml, schema.org rich snippets for search engines, WCAG/accessibility audits, or CSP/security headers.
Design or evaluate a logo against the SAD bar — Simple, Appropriate, Distinct — always judged in context. Use when designing a new mark, refining one, or assessing whether an existing logo is any good. Triggers on “logo,” “wordmark,” “brandmark,” “mark,” “monogram,” “favicon/app icon,” “is our logo good,” “redesign our logo,” “logo critique,” or “logo concepts.” Reads the brand's emotional target and competitor set first — a logo is never judged in a vacuum
The step-by-step procedure for running this repo's Promptfoo evals with a generator and a judge over provider APIs. Use when starting a new skill and needing a baseline before writing content, when a run stalls or returns no data, when a provider rate-limits, or when deciding whether an edit needs a retest.
Marketing skills for AI agents. CRO, copywriting, SEO, analytics, pricing, and growth engineering. From Corey Haines' Marketing Skills collection. Use when working with marketing, cro, conversion, copywriting, seo, landing page, pricing, growth.
Build custom PCB structures with pcbComponent, shapes, Boolean ops, feeds, and multi-layer stackups for non-catalog geometries. TRIGGER: user asks to build, modify, or customize a pcbComponent — add/remove shapes, edit polygons, place feeds, add metal layers, cut slots, or create non-catalog RF structures. Also when modifying geometry of an existing catalog-designed component (e.g., adding pads, removing elements, editing vertices). Invoke BEFORE writing pcbComponent code — layer/shape/feed API is non-obvious. SKIP: designing catalog components like filters/couplers/txlines (use the specific matlab-design-pcb-* skill), material/stackup definition only (use matlab-manage-pcb-material), EM analysis (use matlab-analyze-em), importing PCB files (use matlab-read-pcb-layout).
Analyzes sensor configurations and creates inertial fusion filters in MATLAB Navigation Toolbox. Manages filter selection (imufilter, ahrsfilter, complementaryFilter, insfilterMARG, insfilterAsync, insfilterNonholonomic, insfilterErrorState, insEKF, insCF), construction, tuning, and fusion loops. Use when fusing IMU/AHRS/INS/GPS+IMU data, estimating orientation or pose, or choosing a filter. Do NOT use for vision-only SLAM, Simulink fusion, or IMU simulation.
MATLAB/GNU Octave numerical computing: matrices, linear algebra, ODEs, signal processing, optimization, statistics, scientific visualization. MATLAB-syntax examples run on both. For Python use numpy/scipy; for statistical modeling use statsmodels.
Analyze MD trajectories from GROMACS, AMBER, NAMD, CHARMM, LAMMPS. Reads topology/trajectory into Universe objects; supports RMSD, RMSF, radius of gyration, contact maps, H-bonds, PCA, and custom distance/angle calculations. Use for post-simulation structural analysis; use OpenMM/GROMACS for running simulations.
This skill should be used when user asks to "Menu宽度为0", "Menu宽度问题", "Menu显示异常", "Menu子窗口问题", "Menu layout异常", "recreate subwindow", "快速打开Menu问题", "Menu闪退", "Menu位置错误", "子窗口recreate", "Menu崩溃", "Menu打印recreate", "点击无响应", "点击菜单关闭", "菜单位置左上角", "菜单方向不对", "菜单避让坑", "宽度高度为0", or mentions any Menu component issues like Menu width being 0, Menu display problems, Menu subwindow issues, Menu layout exceptions, positioning errors, crashes, click response issues, menu closing immediately, incorrect positioning, direction issues, safe area issues, or zero width/height problems. Provides systematic debugging guidance for Menu component issues including width problems, subwindow recreation, layout exceptions, positioning errors, crash analysis, click issues, menu positioning, and dimension problems with automatic log enhancement patch generation.
Use Mergify config commands to validate configuration files, simulate Mergify actions, and write Mergify configuration. ALWAYS use this skill when validating, writing, editing, or simulating Mergify config. Triggers on config validate, config simulate, mergify configuration, mergify.yml, .mergify.yml, Mergify merge queue config, pull_request_rules, queue_rules, Mergify conditions.
Guidance for Microsoft Priva — privacy risk management and subject rights requests. Covers Priva Privacy Risk Management and Priva Subject Rights Requests to find privacy risks and fulfill data subject requests (GDPR/CCPA). WHEN: Microsoft Priva, privacy risk management, subject rights request, DSAR, data subject request, GDPR fulfillment, privacy risk policies, data minimization, overexposed personal data.
Use this skill to wire Mockito (the dominant Android mocking framework, exclusively used by androidx itself) into a JVM unit-test suite. Covers `org.mockito:mockito-core:5.x` plus the `org.mockito.kotlin:mockito-kotlin:5.x` Kotlin DSL — `mock<T>()`, `whenever`, `argumentCaptor<T>()`, `any()` / `anyOrNull()` / `eq()`, `MockitoJUnit.rule()` vs `MockitoAnnotations.openMocks(this)` lifecycle, the inline mock-maker for Kotlin final classes (`mock-maker-inline` plugin file), `@SdkSuppress(minSdkVersion = 28)` for instrumented final-class mocks, and the suspend-stubbing escape hatch via `runBlocking`. Use when the user mentions `whenever`, `Cannot mock final class`, `InvalidUseOfMatchersException`, `@Mock null`, `MockitoJUnitRunner`, `argumentCaptor`, `mock-maker-inline`, or asks how to mock with mockito-kotlin.
Verifies that implemented neural network models correctly respect their intended symmetries through systematic equivariance testing, layer-wise isolation, and gradient analysis. Use when testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if a model is actually equivariant, or diagnosing why an equivariant model isn't working.
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications
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.