Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

Research technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when exploring implementation options or evaluating technologies.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Build forms that change as they are filled in — cascading or dependent dropdowns, conditional fields and sections, option lists that depend on another field, STI type switches — with the turbo_form gem. Use when a form must update without a full page reload, when adding or changing a dynamic form, or when touching existing `turbo_fetch` routes, actions, or `turbo-form`/`turbo-fetch` Stimulus wiring.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook that injects a compact project brief. Use when context must survive across sessions, saving session state with next steps and decisions, resuming where a previous session left off, or picking up a project without re-explaining it.

Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.

Fetch CI build results and diagnose failures. Auto-detects provider from project files or URLs. Supports GitHub Actions, Buildkite, and CircleCI.

Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.

Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~/.claude/writing-lint/proposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts/writing-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts/writing-rule-approve.sh), listing pending proposals (use scripts/writing-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine / PostToolUse hook does that).

Build an ultra-realistic open ocean in Three.js with a deep-water Gerstner spectrum shaded per pixel from analytic derivatives, each wave faded at its own pixel footprint, plus Fresnel sky-cube and planar reflections, subsurface light through the crests, HDR sun glitter, Jacobian lace foam, a Kelvin wake, hull foam, buoyancy queries and aerial perspective into the sky's horizon haze. Use for seas, oceans, sunset or daylight water, sun glitter paths, ship or boat scenes, wakes, coastal flyovers and any 3D scene with a moving camera and a water horizon. Includes the approved water from Pirate Ship Sunset as a reusable module and demo.

Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content. Generates a polished single-file HTML deck in the Editorial Monocle visual direction (warm cream background, serif type, brick-red accent) — designed to be opened in a browser, full-screened, and shared. Does NOT apply to generating skills (that's `openkb skill new`), long-form research reports, or interactive prototypes.

Use for natural-science or engineering tasks, scientific software routing, simulation, dataset analysis, model fitting, package checks, HPC-through-shell work, validation, and evidence-backed scientific claims using DeepScientist's `artifact.science(...)` Science Evidence Graph. Includes a progressive-disclosure catalog of FermiLink skilled-scipkg package cards.

Use this skill when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions. Write a self-contained task description so the receiving agent needs no prior context.

Running Positron IDE commands: changing the window layout, focusing panes (Console, Variables, Plots, Help, Packages), clearing the console, opening a file or data file in the right editor, discovering interpreters, listing, switching, starting, restarting or interrupting sessions, setting up Python, reading, installing or updating a session's packages, running or debugging a web app (Shiny, Flask, Dash, Streamlit, FastAPI, Gradio, marimo), and reading the Data Connections pane -- connections code cannot see -- including a live connection's tables and columns. Use when the user wants Positron itself to act, or to know what is installed, rather than to run R or Python code. Triggers: "show the variables pane", "open data.csv", "what interpreters are available", "switch to my R session", "my session is stuck", "is pandas installed?", "set up a Python environment", "run my shiny app", "what databases am I connected to", "what tables are in my warehouse", "deploy my app to Connect".

Extract product list from any e-commerce category page, search results page, or keyword search with filters. Returns paginated product arrays with URL, name, price, currency, image, rating, review count per item. Supports URL input, keyword search, and site-scoped search with filters: price range, brand, category, minimum rating, in-stock only, and sort order. Works on Amazon, eBay, Walmart, Shopify collections, WooCommerce shops, Google Shopping, and any public product listing page. Use when: category listing, product search results, ecommerce search, search for products, filter products by price, list products from a site, price range filter, brand filter, keyword search with filters, scrape product list, product catalog extraction, get all products from category, bulk product URLs, product list scraping, category page scraper, search results scraper, multi-page product extraction.

Extracts Airbnb accommodation search results from a destination query via SSR-embedded data, returning listing ID, URL, name, coordinates, rating, price, photos, and badge info for each result, plus pagination cursors for multi-page retrieval. Use when user mentions Airbnb search results, Airbnb listings, vacation rental search, short-term rental listings, scrape Airbnb, get Airbnb data, find rentals on Airbnb, Airbnb destination search, Airbnb property list, Airbnb stays search, Airbnb accommodation results, pull Airbnb listings, collect Airbnb search data, Airbnb scraper, Airbnb search page extraction, Airbnb search by destination.

Diagnoses and fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test).