Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

Find which scaling-framework concession has hardened into a constraint in your organization, then design one descaling experiment against it. Diagnoses across five named concessions, then produces a hypothesis, the smallest move, a leading indicator, the resistance to expect, and a retrospective question. Use when a scaling framework was adopted with compromises that were meant to be temporary and never revisited. Scoped to a scaling framework's own compromises — for the broader project-to-product operating-model question use portfolio-to-product-shift-coach, and for one initiative's readiness use sniff-test. If the question is broad — AI pilots with no clear return, or "where do we start" — run ai-activity-to-impact first; it finds the constraint and routes here.

Work out where you actually sit between using AI and architecting workflows with it, and what the next rung is. Places you on behavioural ladders across the three modes of engagement (automation, augmentation, agency), how the AI gets your context, verification rigour and leadership scope, then names one habit change worth making. Use when AI is clearly helping but the leverage has plateaued, when every session starts by re-explaining the same background, or before rolling AI practices out to a team. If the question is broad — AI pilots with no clear return, or "where do we start" — run ai-activity-to-impact first; it triages and routes here.

Migrate Databricks workloads from classic compute to serverless compute. Use when migrating notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`) from classic clusters to serverless, checking if existing code is serverless-compatible, or writing new serverless-compatible code. Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration. Not for classic DBR version upgrades or cluster configuration changes within classic compute.

Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node/TypeScript/React) — reach for it first.** Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only. Covers OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model / Vector Search / model-serving APIs (via `databricks-python-sdk`), and deployment via CLI or DABs.

Use when you add, change, or run the Playwright tests that make the docs.camunda.io images for the orchestration cluster webapp (webapp/client/apps/orchestration-cluster-webapp/test/docs-screenshots/). Use also for the callout helpers, getScreenshotPath, and the test:docs-screenshots script.

Autonomously investigate a GitHub issue in camunda/camunda — read it, find the relevant code, reproduce it, root-cause it, and validate a fix, posting progress as a single updating issue comment. At Medium/High confidence, implements the fix and opens it as a draft PR. Use when asked to investigate, triage-deep-dive, or look into a specific bug issue (given a URL or issue number).

Run a structured threat-modeling session for a new feature, system, or architecture — STRIDE, attack trees, data flow diagrams, abuse cases. Use when the user mentions 'threat model,' 'threat modeling,' 'STRIDE,' 'attack tree,' 'abuse case,' 'data flow diagram,' 'DFD,' 'security architecture review,' 'design review,' 'pre-implementation security,' 'shift left,' 'what could go wrong,' or needs strategic security thinking before code is written.

Repository conventions for this Bun starter — Bun-only tooling, workspace layout, quality gates, Lefthook hooks, Conventional Commits, Tailwind CSS, Storybook, type checking with `bun check`, and reference repositories in repos/. Use when starting work in this repository, choosing tools, running checks, committing, or when AGENTS.md / CLAUDE.md point here.

Create or update a custom WordPress plugin for site functionality that should not live in a theme or a block. Use when the user needs reusable behavior, admin/settings UI, hooks, REST endpoints, scheduled tasks, integrations, or server-side logic for a Studio-backed site.

Guide for using Apollo Rover CLI to manage GraphQL schemas and federation. Use this skill when: (1) publishing or fetching subgraph/graph schemas, (2) composing supergraph schemas locally or via GraphOS, (3) running local supergraph development with rover dev, (4) validating schemas with check and lint commands, (5) configuring Rover authentication and environment, (6) exploring or searching a graph's schema for agent-driven discovery (rover schema describe / rover schema search), (7) initializing a new graph project or MCP server with rover init, (8) working with Apollo Connectors, contracts, persisted queries, or client operations, (9) managing API keys, plugins, templates, or graph artifacts.

Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.

Manages stacked PRs with gh-stack — creation, viewing, editing, push, submit, sync, rebase, merge, and checkout. Use when splitting work into reviewable branches, managing dependent PRs, whenever the user mentions a stack, branch layers, or gh stack, or whenever a stack is already checked out.

Diagnostic and repair workflow that analyzes error logs, traces root causes, implements fixes, and verifies with regression tests. Use when fixing bugs, debugging runtime errors or exceptions, investigating test failures or crashes, or submitting bug-fix pull requests. Activated by commands: /unattended, /assess, /diagnose, /reproduce, /fix, /test, /review, /document, /pr, /feedback, /start.

Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.

This skill should be used when the user says "scan for CVEs", "CVE scan", "check for vulnerabilities", "dependabot triage", "audit dependencies", "security scan", "arness CVE scan", "arn-code-batch-cve-scan", "run a scheduled CVE scan", "finalize a CVE proposal", or wants Arness to discover, triage, and ticket security advisories across project dependencies (GitHub Dependabot plus locally-detected scanners). Three modes: interactive, proposal (unattended, safe for Routines or claude -p), and finalize (review a proposal and file tickets on GitHub or Jira).

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'ad templates,' 'iMessage ad,' 'ChatGPT ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'creative review page,' 'motion video ad,' 'faceless video ad,' 'UGC ad,' 'greenscreen ad,' 'TikTok/Reels ad format,' 'Meta ad format tier list,' or 'creative format taxonomy.' Use it to produce or iterate ad copy at scale. Copy avoids AI tells like 'it's not X, it's Y' reveals. For campaign strategy and targeting, see ads. For landing page copy, see copywriting. Test hypotheses must be falsifiable, naming the metric, the comparison, and the expected direction.

Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.