MUST be used whenever integrating CogniteFileViewer into a Flows app to preview CDF files (PDFs, images, text). Do NOT manually wire up react-pdf or file resolution — this skill handles installation, Vite config, worker setup, and component usage. Triggers: file viewer, file preview, CogniteFileViewer, PDF viewer, view CDF files, document viewer, preview file.

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this; /publish ships directly. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this; /publish ships directly. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.

Test whether a candidate real-work signal in `eval/token_ceiling_formula.py` (e.g. `context_ingestion_volume`, `investigative_uncertainty`, or new) deserves a nonzero default weight, via the blind multi-draw rating + correlation methodology this repo's research converged on. Ratings must come from genuinely independent sub-agent dispatches seeing ONLY a forward-looking task spec and the signal definitions — never a context holding the real actuals or this repo's retired write-ups, which would turn "blind rating" into transcribing the answer key. Dispatches 3+ independent draws per held-out task, computes per-signal CV and Pearson correlation (alone, and added to the signal sum — dilution, not weak correlation, is the dominant failure found twice), requiring replication on a SECOND held-out task before proposing a nonzero weight. Use when someone says "test this new signal", "does [signal] deserve a nonzero weight", "re-run the signal validation experiment", or "validate real-work signals against real data".

Updates Python test code to work with new versions of the code being tested. Use when Claude needs to: (1) Update tests after code changes, (2) Fix broken tests due to signature changes, (3) Update assertions to match new behavior, (4) Add test cases for new functionality, (5) Analyze code differences and their test impact, (6) Run tests and fix failures based on error messages. Takes old code, new code, and old tests as input, outputs updated tests that pass.

Guide for building GraphQL servers with Apollo Server 5.x. Use this skill when: (1) setting up a new Apollo Server project, (2) writing resolvers or defining GraphQL schemas, (3) implementing authentication or authorization, (4) creating plugins or custom data sources, (5) troubleshooting Apollo Server errors or performance issues.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Autonomously submit brief, constructive internal feedback when an agent encounters material, generalizable friction and can suggest an improvement that would make agents more effective. Use this skill proactively during any task without waiting for the user to invoke it, and submit without asking permission, previewing the message, or mentioning the submission.

Reference documentation for the Agent2Agent (A2A) protocol. Use when building A2A servers or clients, configuring Ark A2AServer resources, debugging A2A communication, or answering questions about the A2A specification, Agent Cards, task lifecycle, streaming, extensions, or protocol bindings.

Build event-driven architectures with Groq streaming, batch processing, and async patterns. Use when setting up real-time SSE endpoints, batch processing pipelines, or event-driven LLM processing with Groq. Trigger with phrases like "groq streaming", "groq events", "groq SSE", "groq batch", "groq async", "groq event-driven".

Apply production-ready Groq SDK patterns for TypeScript and Python. Use when implementing Groq integrations, refactoring SDK usage, or establishing team coding standards for Groq. Trigger with phrases like "groq SDK patterns", "groq best practices", "groq code patterns", "idiomatic groq".

Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks. Use when designing new Groq integrations, reviewing project structure, or establishing architecture standards for Groq applications. Trigger with phrases like "groq architecture", "groq best practices", "groq project structure", "how to organize groq", "groq design".

Implement Groq rate limit handling with backoff, queuing, and header parsing. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Groq. Trigger with phrases like "groq rate limit", "groq throttling", "groq 429", "groq retry", "groq backoff".

Use when you need Groq to behave differently across dev, staging, and production — cheap fast models and verbose logs in dev, the production model and hardened retries everywhere else, with per-environment API keys. Configure environment-specific model selection, rate limits, and secrets. Trigger with phrases like "groq environments", "groq staging", "groq dev prod", "groq environment setup", "groq multi-env", "groq config by env".

Use when you run Groq inference for multiple teams and need per-team model allow-lists, spending caps, rate limits, and key rotation — because Groq API keys have no built-in scopes, so access control must live in your gateway. Configure Groq organization management, API key scoping, spending controls, and team access patterns. Trigger with phrases like "groq organization", "groq RBAC", "groq enterprise", "groq team access", "groq spending limits", "groq multi-team".

Deploy Groq integrations to Vercel, Cloud Run, and containerized platforms. Use when deploying Groq-powered applications to production, configuring platform-specific secrets, or setting up deployment pipelines. Trigger with phrases like "deploy groq", "groq Vercel", "groq production deploy", "groq Cloud Run", "groq Docker".

Execute Groq's primary workflow: chat completions with tool use and JSON mode. Use when implementing chat interfaces, function calling, structured output, or building AI features with Groq's fast inference. Trigger with phrases like "groq chat completion", "groq tool use", "groq function calling", "groq JSON mode".

Configure Groq CI/CD integration with GitHub Actions, testing, and model validation. Use when setting up automated testing, configuring CI pipelines, or integrating Groq tests into your build process. Trigger with phrases like "groq CI", "groq GitHub Actions", "groq automated tests", "CI groq".

Build programmable calling with the Sinch Voice API v2 (public preview). Use for creating outbound calls, handling Voice v2 webhooks, writing SVAML v2 call flows, IVR menus, bridging call legs, call recording, batch calling, connecting Voice Relay or raw audio streams to AI voice agents, and migrating Voice v1 call control to v2. Not for Voice API v1 callouts and ICE/ACE/PIE callbacks (use sinch-voice-api), the In-App Calling SDKs, or Elastic SIP Trunking.

Build a walkthrough the user works through until they can pass a quiz on it. Use when the user needs to understand something deeply and be quizzed on it.