Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Compare two folders function by function with jscpd --compare, in the same language or across languages, and explain the result. Use when asked how two codebases relate, which functions one implementation has and the other lacks, how far a port has come, whether the iOS and Android versions of an app match, or which function in one folder corresponds to a function in the other.
A skill for creating executive-meeting-quality slides, built around the slide design rules in slide-rules.md. Retrieve only the sections needed for each stage with scripts/rules.py, assemble from components verified against the rules (20 types listed by new_deck.py --list), and finish with zero mechanical-check FAILs from check_deck.py and check_layout.mjs. Only when given an existing PowerPoint and asked for pages to insert into it as PPTX, build directly on that document’s master (slide-rules §8.7). Trigger examples: “Create consulting-quality slides,” “Make a deck that follows the rules,” “Add pages to this pptx in the same format.”
Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instructions, copilot-instructions.md, GitHub Copilot config
Creates product analytics or SQL-backed box plot insights in PostHog. Use when a user asks to create, build, or save a box plot, visualize a numeric distribution, compare quartiles or medians across dates or groups, or turn SQL results into a box plot. Chooses between a standard Trends box plot and a SQL insight, validates the distribution data, saves the insight, and verifies it.
DDD code review and anti-pattern detection — anemia model detection, layered compliance checking, aggregate design review, rich model verification, scoring system (5 dimensions), and ArchUnit automated validation. Use when user asks about code review, 代码审查, DDD review, 架构审查, anti-pattern detection, 反模式检测, or needs to check if code follows DDD.
Event Storming workshop facilitation guide — collaborative domain exploration methodology with 6-step process (chaos exploration/timeline/pivotal events/commands & actors/aggregate discovery/bounded context), standardized sticky note color conventions (orange/blue/yellow/green/pink/purple), workshop preparation and facilitation tips, and digital tool recommendations. Use when user asks about event storming, 事件风暴, workshop, 工作坊, domain exploration, collaborative modeling, or needs to organize a DDD discovery workshop.
Build software with elite design principles focusing on user outcomes, trust, accessibility, and performance. Use when creating UI components, designing user flows, writing production code, reviewing code quality, or when the user mentions UX, accessibility, performance, or trust-focused development.
Use when about to approve a design document — a spec, plan, design doc, RFC, or ADR — and you want an adversarial pre-approval review that surfaces gaps before sign-off. Hunts recurring gap categories (bootstrap & ownership, naming honesty, scale, hidden assumptions, consistency-with-shipped-code, idempotency/failure, security, necessity, completeness) plus, for a plan, a plan lens (task granularity, dependency-DAG, coverage-vs-spec, exit-criteria testability). Verifies claims against the codebase (file:line, never fabricating); returns findings + a ready-for-approval / has-blockers verdict. Review-only: never edits and never approves — the human decides, the author fixes. Gates generic design docs, RFCs, standalone ADRs, specs, and plans — NOT the doc-library technical-design, architecture-doc + its linked ADRs, data-model, or api-spec artifacts (each routes to its dedicated reviewing-* twin). Keywords: design review, spec/plan/RFC/ADR review, gap analysis
Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, listing representor devices, asking which DOCA libraries are available on the current OS, checking per-device per-library capabilities, scoping output to a specific PCIe address, or capturing a side-effect-free capability snapshot for debug or install smoke-test. Trigger even when the user does not explicitly mention “doca_caps” or “capabilities print tool” — typical implicit phrasings include “what does DOCA actually see on this box”, “is my BlueField PF visible to DOCA”, “is Flow available on my RHEL host”, “enumerate VF representors for pf0”, “doca_caps: command not found”, or “empty output for RDMA, is the tool broken”. Refuse and route elsewhere for DOCA installation (doca-setup owns it; never walk the steps), library-internal capability matrices (Flow pipe creation, RDMA verbs features), streaming telemetry / DTS, or modifying the shipped binary
Use this skill to locate authoritative NVIDIA DOCA information without the source tree: the docs.nvidia.com page for a library/service/tool, which DOCA libraries are installed and at what version, a sample on disk or GitHub, a path under /opt/mellanox/doca, or a 404'd or renamed documentation URL. Activate on implicit phrasing only when the conversation already names DOCA, BlueField, ConnectX, or /opt/mellanox. Do not activate for generic “which version is installed” or “where is the sample” questions without that context. Refuse and route elsewhere for hands-on programming, environment preparation, API tutorials, or hardware/firmware changes—those belong to doca-programming-guide, doca-setup, the per-library skills, and doca-hardware-safety
Build a starting-point taxonomy for an MCP tool — what users were trying to accomplish before they reached the tool — and publish it as a PostHog notebook. Reconstructs each session's goal from its opening tool calls, then clusters those goals into named categories with size, share, and facet mix. Use when the user asks "why do people use this tool?", "what are users actually trying to do?", "what problem brings people here?", "where do these sessions start?", "segment usage of <tool> by goal", or wants a Clio-style taxonomy of MCP usage. Complements exploring-mcp-intent-clusters, which groups what agents did per call rather than why the session began. The agent running this skill writes the goal labels itself, reading the corpus query output session by session — the bundled scripts cover the mechanical facets but measurably lose the goal's altitude, so do not delegate that field to them.
Migrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, migrate Terraform to AWS, migrate Cloud SQL to RDS, migrate GKE to EKS, migrate Cloud Run to Fargate, migrate App Engine to Elastic Beanstalk, Google Cloud migration, migrate from OpenAI to Bedrock, move off OpenAI, switch from ChatGPT API to AWS, migrate from Gemini to Bedrock, migrate LangChain to Bedrock, migrate LangGraph to AWS, migrate agentic workloads to AWS, move AI workloads to AWS, migrate my AI app to AWS. Runs a 6-phase process: discover GCP resources from Terraform files, app code, or billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Includes AI provider migration guidance (for example, OpenAI to Amazon Bedrock) by selecting closest-fit Bedrock model families for required modality, latency/quality targets, context windows, and cost constraints. Model mapping is compatibility-guided, not 1:1 parity; validate prompts, tool-calling behavior, and eval metrics before cutover. Do not use for: Azure migrations to AWS (see azure-to-aws), on-premises migrations to AWS, AWS-to-GCP reverse migration, general AWS architecture advice without migration intent, GCP-to-GCP refactoring, or multi-cloud deployments that do not involve migrating off GCP.
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.
Lightweight GPT Image 2 image generation and editing workflow. Use when Codex needs to configure OpenAI-compatible image API channels, generate or edit images from the command line without Python, print equivalent curl calls, or help users quickly try curated GPT-Image-2 prompt templates.
CLI tool for AI-powered web scraping, data extraction, search, and crawling via ScrapeGraph AI. Use when the user needs to scrape websites, extract structured data from URLs, convert pages to markdown, crawl multi-page sites, search the web for information, automate browser interactions (login, click, fill forms), get raw HTML, discover sitemaps, or generate JSON schemas. Triggers on tasks involving: (1) extracting data from websites, (2) web scraping or crawling, (3) converting webpages to markdown, (4) AI-powered web search with extraction, (5) browser automation, (6) generating output schemas for scraping. The CLI is just-scrape (npm package just-scrape).
An in-depth web-based fact checker for verifying external claims in technical documents or verifiable factual claims in spoken scripts. Use when the user says “deep review,” “Lao Han review,” “web review,” “technical document review,” or “verify spoken-script facts,” or asks to verify factual claims in technical plans, deployment scripts, configuration files, or spoken scripts. By default, review only; modify files only when the user explicitly requests fixes or the workflow contract authorizes them. Does not perform style-only reviews.
For a phenomenon provided by the user, generate mechanistic hypotheses using "spot anomalies—trace processes—decompose explanations—transfer with conditions", verify the phenomenon online, test key causal links and competing explanations, and deliver the mechanism best supported by evidence along with its boundaries. USE WHEN the user invokes ljg-mechanism, says "find the mechanism", "mechanism research", "run through the four-step framework", "verify this explanation online", or wants to study how a phenomenon occurs. NOT FOR pure concept definitions, ordinary summaries, operational questions with a unique answer, or merely drawing a map.
Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist and delivers a formatted report with pass/warn/fail findings and actionable fixes. Use this skill whenever a user provides a domain or URL and wants to know if llms.txt or llms-full.txt is available, discoverable, or properly structured. Trigger on phrases like "check llms.txt for", "does this site have llms.txt", "find llms.txt", "check llms for this url", "audit llms.txt", "is llms-full.txt available", or any time a user shares a domain/docs URL and wants AI-readiness checked. Also trigger when the user wants to verify GEO/AEO readiness of a documentation site.
Use when resuming work after a pause, reboot, or context switch and the workspace uses `wiki/checkpoints/` resumable notes. Read the latest relevant checkpoint chain, orient to the most likely in-flight scope, verify current files and tools before acting, and report the safest next step. Treats a goal path as concrete context; checks live goal status over stale checkpoints.
Guide for implementing Grafana Loki, a horizontally scalable, highly available log aggregation system. Use when configuring Loki deployments, setting up storage backends (S3, Azure Blob, GCS), writing LogQL queries, configuring retention and compaction, deploying via Helm, integrating with OpenTelemetry, or troubleshooting Loki issues on Kubernetes.
Looker Studio (formerly Google Data Studio) expertise. Build dashboards, design data visualizations, connect data sources, and create marketing reports. Use when the user asks about Looker Studio, Data Studio, marketing dashboards, data visualization, report building, or connecting analytics data sources.
Use when a project has a components.json from marko-ui, or when installing, using, editing, or debugging marko-ui components (shadcn-style components for Marko 6 backed by Zag.js) — finding a component, reading its API, adding it with the marko-ui CLI, fixing a component that renders but misbehaves, or setting marko-ui up in a new project. Not for general Marko 6 syntax (see marko6) or routing (see marko-run).
Provides comprehensive guidance for Midjourney AI image generation including prompt engineering, image generation, parameters, and best practices. Use when the user asks about Midjourney, needs to generate AI images, create prompts, or work with Midjourney features.
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.
Use the One CLI (`one`) to interact with third-party platforms—Gmail, Slack, Stripe, Notion, etc.—through their APIs. One handles auth, request building, and execution. TRIGGER when: - Interacting with any third-party platform or external service (e.g., “send an email”, “create a Shopify order”, “find a HubSpot contact”, “post to Slack”) - Listing connected platforms or checking available ones - Finding the actions a task needs (e.g., “how do I send a Slack message”, “what can I do with Gmail”) - Executing API calls with a connected platform - Setting up webhook-driven automations between platforms (e.g., “when a Stripe payment comes in, notify Slack”) - Building multi-step workflows that chain actions across platforms (e.g., “fetch Stripe customers and email each one”) - Anything involving third-party APIs, integrations, or connected apps—even if they don't mention “One” by name DO NOT TRIGGER for: - Setting up One or installing MCP (use `one init`) - Adding new connections (use `one add <platform>`) - Configuring access control (use `one config`)
Defines the O11y Change Context manifest — the structured PR block that carries a change's observability intent (type, touched services, telemetry added/changed, guarding alerts, watch items, gaps) from authoring through review into production triage. Referenced by oodle-o11y-review and oodle-triage.
Reviews a code change's telemetry during authoring or code review — checks business-context attributes and cardinality placement, telemetry duplication, RED/USE/queue/fan-out coverage, and alert-driven scrutiny of code guarded by existing alerts and SLOs. Writes findings into the O11y Change Context manifest and hands fixes off to oodle-monitors, oodle-drop-rules, and oodle-log-metrics. Use when reviewing or authoring instrumentation changes.
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.