Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Performance patterns and gotchas for querying a Rerun catalog from Python. Reach for this when a CatalogClient/dataset query is unexpectedly slow, or when shaping a per-segment / per-episode pipeline that hits the catalog from many places.

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO: baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".

Use only when a focused Sales workflow has selected a connected HubSpot CRM, or the user explicitly asks for HubSpot guidance, reads, drafts, notes, or reviewed record changes. Do not use when another CRM is authoritative.

Review commercial proposals and build customer-led business cases, ROI or value models, pricing or investment rationales, executive summaries, and customer-ready value stories tied to a customer, workflow, initiative, or decision.

Load or manage Product Design's saved user context. Use when the user asks to set up Product Design, get started, onboard, save product or design sources, see what Product Design remembers, update saved context, or remember Product Design preferences. Examples include product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, and general product/design notes.

Use this skill set when contributing to the InsForge monorepo itself. This is for InsForge maintainers and contributors editing the platform, the shared dashboard package, the self-hosting shell, the UI library, shared schemas, tests, or docs.

Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.

Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.

Assists in designing and implementing secure n-tier serverless web applications and microservices on Google Cloud. Use when users need architecture designs, security checklists, Terraform code, or deployment guidance for multi-tier serverless apps, regional data residency / European sovereignty compliance, zero-trust private VPC networking, or Private Service Connect. Don't use for VM, GKE, or non-Google Cloud architectures.

Guides agents through a 6-step discovery process to design and deploy Google Cloud global external Application Load Balancers with Cloud CDN, Cloud Armor, and Service Extensions, mapping workload requirements to best-practice configurations. Use when: - Designing, configuring, or deploying a Google Cloud global external Application Load Balancer, Cloud CDN, Cloud Armor WAF, or Service Extensions. - Discovering existing Google Cloud resources (Cloud Storage, MIGs, GKE, Cloud Run) to use as backends. - Generating production-grade Terraform HCL or gcloud CLI scripts for global external Application Load Balancers. - Actuating deployments via Infrastructure Manager or bash scripts, including IAM pre-checks. - Detecting, analyzing, or reconciling configuration drift on deployed global external Application Load Balancers. Don't use for: - Non-Google Cloud load balancing or security configurations. - Purely regional or internal load balancing setups (unless part of a hybrid/failover global design).

Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructing, proposing, describing, or executing any gcloud CLI commands - including when answering questions about gcloud syntax, or formatting flags. Don't use when writing Google Cloud client library code or raw REST/gRPC API requests.

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google Workspace RAG, or other RAG products like gRAG.

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

Build new Plate plugins with Slate-first architecture, sane typing, and explicit React/Plate wrapper boundaries. Use when authoring or refactoring Plate plugin packages, deciding between createSlatePlugin vs createPlatePlugin, defining plugin APIs/transforms/options, or lifting semantic base plugins into React/Plate wrappers.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".