Write and run Playwright E2E tests for Redpanda Console using testcontainers. Analyzes test failures, adds missing testids, and improves test stability. Use when user requests E2E tests, Playwright tests, integration tests, test failures, missing testids, or mentions 'test workflow', 'browser testing', 'end-to-end', or 'testcontainers'.

Generate Playwright integration tests for Vaadin 25 views using the DramaFinder library, including element interaction, form validation, grid assertions, and navigation checks. Use whenever you are about to write, edit, or run an integration/IT test for a Vaadin view — including when the requirement comes from a GitHub issue, PR, spec, or ticket rather than the user's direct words (e.g. "implement

Protect a portfolio slice by applying one Universal (canonical) policy across API instances on any gateway (Kong, Apigee, Azure, AWS, MuleSoft). Use when the user says all / many / my APIs / a portfolio slice — JWT validation, rate limiting, spike arrest, IP filtering, or apply one config across providers. DO NOT TRIGGER for "what protection do I have" / listing or editing already- applied native policies — use skill apply-native-policy-to-instance. DO NOT TRIGGER for a single already-chosen instance that needs a provider-native plugin — same skill. Do not use to remove, detach, enable, or disable a policy (those tools do not exist).

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Apply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates Lift_To_Graph mappings and composes Graph_Render_View, Graph_Fold_By_Property, Extract_Node_*, Enrich_Node_*, and Enrich_Graph_* calls. Accepts a supplied query or limited basic natural-language source request; it is not a general natural-language-to-KQL/IRQL skill. WHEN: Lift_To_Graph, Graph_Render_View, Graph_Fold_By_Property, IRQL graph enrichment, graph mapping for existing query results, icon-decorated graph, fold graph nodes. Use azure-kusto-graph for native make-graph analysis, graph-match, shortest paths, components, or persistent graphs.

Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming", "EventHubProducerClient", "EventProcessorClient", "send events", "receive events", "checkpointing", "partition".

Use for writing, reviewing, editing, or generating Meteor release changelog entries. Defines canonical file locations, naming rules, required section structure, formatting conventions, release-diff and milestone reconciliation, contributor and reporter attribution, PR-based generation workflow, incremental updates, and common entry patterns. Applies to files under v3-docs/docs/generators/changelog/versions/.

Generate images, videos, and SVGs using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Vectorizing images to SVG - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "vectorize", "convert to svg" - "stablestudio", "nano-banana", "sora", "veo", "grok", "flux", "seedance", "gpt-image" ALWAYS use agentcash.fetch for stablestudio.dev endpoints.

Use the `cursorctl` CLI (Cursor SDK Bridge) to spawn, send, detach, follow up, inspect, and collect Cursor cloud or local agents. Trigger when delegating work to Cursor cloud agents (`bc-…` IDs), running a local Cursor agent, fire-and-forget with `--detach`, polling `run get`/`wait`/`watch`, collecting artifacts or conversations, managing `cursorctl auth` profiles, or troubleshooting the SDK Bridge. Run cursorctl via Bash. Do not call the SDK Bridge HTTP API directly.

Produces an LPM working view on a single matter — a focused zoom-in for the LPM's own operational use, not for distribution. Structured around deliverables (what is due, when, to whom), issues (current problems requiring action), and risks (plausible future problems requiring monitoring). Use when the user asks "drill into [matter]", "brief me on [matter]", "focus on [matter]", "zoom into [matter]", "prep me for [partner] call on [matter]", "I'm handing [matter] to [name]", "leave cover on [matter]", "taking over [matter]", or pastes single-matter correspondence asking for a working view. Four modes: standard drill-down, decision-first, partner prep, handoff briefing. Not for status reports for distribution (use status-report-drafter) or portfolio views across multiple matters (use daily-briefing). Produces a .docx working view saved to the matter folder.

Produces a portfolio-level morning briefing for an LPM running two or more active matters. Reads email, call notes and matter state across the portfolio and produces a triage surface structured around meetings (today and this week), deliverables (what is due, when, to whom), issues (current problems requiring action), and risks (plausible future problems requiring monitoring). Also reads Outlook Calendar to surface upcoming matter-relevant meetings and to flag past meetings where no follow-up correspondence has been identified. Use when the user asks "run my daily briefing", "portfolio briefing", "what do I need to know today", "what's landed overnight", "Monday sweep", "pre-09:00 briefing", "weekend catchup", or pastes correspondence spanning two or more matters. Not for single-matter briefings (use matter-drill-down) or for audience-facing status reports (use status-report-drafter). Produces a .docx working surface for the LPM's own consumption, not distribution.

When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'battle card,' or 'competitor teardown.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For sales-specific competitor docs, see sales-enablement.

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,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' or 'should I run ads.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see cro.

When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see emails. For in-app upgrade paywalls, see paywalls.

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.

Create, search, and manage Bear notes via grizzly CLI.

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Run backend tests and code quality checks for OPRE OPS. Covers ops_api pytest, data_tools pytest, and nox linting/formatting sessions. Use this skill when the user wants to run backend tests, check code quality, lint Python code, run pytest, or verify their backend changes pass CI checks — even if they just say "run the tests" or "does this pass".

Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps. Supports CI stages (run, run-test, background), CD stages (service/environment with action steps for K8s, Helm, ECS), approval (stage-level and inline), parallel execution, matrix/for/while strategies, caching, volumes, and templates. Use when asked for a v1 pipeline, simplified pipeline, new pipeline format, or when user specifically requests v1 syntax. Do NOT use for v0/standard pipelines (use create-pipeline). Trigger phrases: v1 pipeline, simplified pipeline, new pipeline format, create v1, modern pipeline syntax.

Generate Harness Service YAML for deployable workloads and create via MCP. Supports Kubernetes, Helm, ECS, Serverless, SSH, and WinRm deployment types with artifact sources from Docker Hub, ECR, GCR, ACR, Nexus, and S3. Use when asked to create a service, define a Kubernetes service, set up a Helm chart deployment, configure an ECS service, or define what gets deployed. Trigger phrases: create service, service definition, Kubernetes service, Helm service, ECS service, deployment service, artifact source.