Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.

Use when writing or reviewing Java code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for text analysis. Covers `client.read().v1().text().analyze(...)` with `ReadV1Request` or `TextAnalyzeRequest`. Use `deepgram-java-audio-intelligence` when the source is audio instead of text. Triggers include "read api", "text intelligence", "analyze text", "sentiment", "topics", "intents", and "summarize text".

Start voice calls via the OpenClaw voice-call plugin.

Google Workspace CLI for agents. Use gog to access Gmail, Calendar, Drive, Contacts, Tasks, Sheets, Docs, Slides, Forms, Chat, and more. Triggers on: 'check my email', 'what's on my calendar', 'search gmail', 'list calendar events', 'send email', 'check tasks', 'search drive', 'list contacts', 'create event', 'upload to drive', 'read spreadsheet', or any Google Workspace task.

Static-first Next.js 16 architecture patterns: cached shells with dynamic slots, provider islands, 'use cache' boundaries, and link preloading strategy. Use when building or refactoring Next.js routes to maximize static rendering, implementing 'use cache' with dynamic personalization, splitting entry vs static renderers, scoping client providers, or tuning prefetch behavior. Triggers on 'static shell', 'use cache pattern', 'dynamic slots', 'provider island', 'prefetch strategy', 'static first', 'cache boundary', 'route goes dynamic unexpectedly', or any Next.js architecture work involving mixed static/dynamic rendering.

Deploys agent skill collections from any GitHub repository with a /skills folder to one or more distribution surfaces: GitHub releases, Claude Code marketplace, VS Code plugin marketplace, and Copilot CLI plugin marketplace. Handles pre-flight validation, conventional commit analysis, version bumping across surface configs, and surface-specific publishing with dry-run support. Use when releasing, publishing, or deploying a skills collection to any supported marketplace or creating a GitHub release for a skills repository. Don't use for deploying non-skill packages, npm modules, Docker images, or Azure resources.

Run the evm-wallet Docker e2e tests (build, start stack, wait for healthy, test, diagnose failures).

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

Implement Angular SSR with hydration, TransferState caching, and per-route render modes. Use when configuring Angular Universal SSR, client hydration, static prerendering, or preventing double-fetching.

Implement ViewBinding, RecyclerView, and XML layouts correctly on Android. Use when changing XML view binding or RecyclerView behavior, including its item animations and layout managers; defer standalone animation or layout-manager questions unrelated to RecyclerView.

Implement WorkManager and background processing correctly on Android. Use when creating Worker classes, scheduling tasks, choosing between WorkManager and Foreground Services, or setting up Hilt in workers; defer FCM and notification delivery to android-notifications.

Replay a list of git-revert commits against the current base branch and resolve the conflicts, when the chat-service's automatic rollback hit a merge conflict it couldn't resolve. Load this when your developer dispatch asks you to resolve a rollback conflict (it carries BASE_BRANCH, FAILED_COMMIT, COMMITS_TO_REVERT). This is NOT a feature ticket — the workflow below replaces the normal ticket rules.

Architecture Decision Record format and rules for the developer agent. Load when the implementation introduces a structural decision worth remembering 6 months later — new pattern, new dependency, deliberate departure from convention, non-obvious schema choice. Skip for naming and file-layout micro-choices. No ADR is the default.

Use when checking whether a Proofpack release candidate has complete local evidence before packaging.

Start voice calls via the OpenClaw voice-call plugin.

Start voice calls via the OpenClaw voice-call plugin.

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.