Define a Loop — a durable scaffold that works a queue of recurring tasks autonomously (Sentry issues, Front tickets, small perf PRs) with its outputs held for human review. Use when someone wants an agent to keep doing a kind of work on a schedule, rather than one-off. Walks the interview, runs one real item live before arming anything, then writes the playbook and creates the loop.

**UTILITY SKILL** — Must be consulted before making any changes to packages under sdk/. Discovers and loads package-specific domain knowledge that prevents common mistakes. WHEN: add feature to package; fix bug in package; modify package code; regenerate from typespec; change client library.

Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the review outbox", or invokes /review-pending-pr-reviews.

Resume Mem0 memory capture after it was paused with /mem0:pause.

Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.

Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.

Stand up OpenMed's FastAPI REST service for clinical NER, PII extraction, and de-identification, with health checks, model keep-alive/unload, optional dynamic batching, and no-PHI logging. Use when the user wants to serve OpenMed over HTTP, deploy a de-id/NER REST API, run an inference endpoint for clinical text, add a /analyze or /pii/deidentify route, or containerize OpenMed as a service. Covers the service extra, launching create_app with uvicorn, the real endpoints (/health, /analyze, /pii/extract, /pii/deidentify, /models/loaded, /models/unload), request/response shapes, ServiceRuntime env-var configuration, and self-hosted auth/CORS/TLS notes.

Add authentication and authorization to a Blazor Web App, accounting for the app's render mode. USE WHEN the user needs [Authorize] on pages, AuthorizeView, role or policy-based access, login/logout Identity pages, or AuthenticationStateProvider. Also USE WHEN auth state is null after WebAssembly loads, SignInManager throws in an interactive component, NotAuthorized content never renders in static SSR, or HttpContext.User is null in an interactive component. DO NOT USE for general component authoring (see author-component), for prerendering concerns unrelated to auth (see support-prerendering), or for managing non-auth cascading state (see coordinate-components).

Audit how a brand shows up in AI answers about its market and deliver a short report on the few changes most likely to get it mentioned or cited, such as a third-party page to get onto, an owned page to improve, or an access problem to fix. Use when the user asks for an AI visibility audit, a GEO or AEO audit, why AI recommends competitors instead of them, or how to show up in ChatGPT, Gemini or Google AI answers.

Remove AI writing patterns from prose so it reads like a person wrote it. Use when writing, editing, or reviewing user-facing text (blog posts, docs, marketing copy, PR descriptions), or when asked to "deslop", "de-AI", or "make it sound human".

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

Write or review OpenVINO ov::Model graph transformations (passes: MatcherPass, ModelPass, GraphRewrite, BackwardGraphRewrite). Use when the user asks to write, add, or refactor a transformation/fusion/decomposition pass, choose between MatcherPass and ModelPass, write pattern-matching predicates, or bring an existing pass in line with OpenVINO transformation conventions.

Use when the user gives a source (URL, file, or text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts cross-linked entity pages, audits backlinks, updates the index. Not for casual reads.

Use when you need to visually interact with a GUI: test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Needs the `cua` CLI (curl -fsSL https://cua.ai/install.sh | sh).

Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

Create comprehensive industry and sector landscape reports covering market dynamics, competitive positioning, key players, and thematic trends. Use for client requests, sector initiations, thematic research pieces, or internal knowledge building. Triggers on "sector overview", "industry report", "market landscape", "sector analysis", "industry deep dive", or "thematic research".

Look up the applied tariff on one HS6 product imported by one country from another (MFN, partner-specific preferential, and the best available applied rate), from UNCTAD TRAINS via World Bank WITS. Use when the user asks what duty a specific product pays between two specific countries.

Health-check crypto futures positions the user describes or pastes in chat ("I'm long ETH from 2,400 at 10x") with TraderSpy market data. TraderSpy cannot see anyone's account, so the position always comes from the user. Produces a structured risk report per position — distance to liquidation and to the stop, where price sits versus entry, the multi-timeframe technical read, funding cost or benefit and the open-interest regime, whether top traders are on the same or the opposite side, and what would invalidate the position's thesis. Use this whenever the user asks "how's my position", "am I in trouble", "how far am I from liquidation", "should I hold or close", "what do you think of my long / short", or pastes a position. It reports and explains; it never tells the user to close, add, hedge or move a stop, and it cannot trade.

Close out an entire epic in one session — every open child issue of a parent issue, worked by dispatched agents, reviewed and committed one at a time. Use when Josh points at a parent issue and wants the whole thing finished: 'close out the epic', 'let's do epic 40', 'knock out the children of #40', 'work through all of #40's sub-issues', 'finish the whole epic'. Also use when a ref he named — even plain 'let's work on #40' — turns out to have open sub-issues. Routing: if the ref has no open sub-issues it is a single issue, so hand off to the `issue` skill with that ref.

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.