Generate JSON-LD for ONE blog post (BlogPosting with Person, Organization, BreadcrumbList, ImageObject, VideoObject; FAQPage only as optional entity markup) in a single @graph, and check it against Google's current structured data support. Use when the user says "generate schema", "json-ld for this post", "blog schema". Not for auditing schema across a whole site or other schema types (claude-seo seo-schema), not for product pages, and not a promise of rich results: FAQ rich results ended 2026-05-07.

HashQL testing strategies including compiletest (UI tests), unit tests, and snapshot tests. Use when writing tests for HashQL code, using //~ annotations, running --bless, debugging test failures, or choosing the right testing approach.

HASH tracing and instrumentation practices for Rust. Use when adding spans, events, or #[tracing::instrument] to Rust code.

Generate Rust documentation to understand crate APIs, structure, and usage. Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace.

Points at the testing guide, the reference that defines the vocabulary for talking about tests, classifies them on six dimensions, and says how to choose which kind to write, with sections mapping it to Ruby, RSpec, and Rails. Load only when asked why a testing rule exists, what a test term means, how to classify or name a test, or when writing or reviewing a testing skill or standard. Do not load it for ordinary test writing; the standards skills are self-sufficient for that.

Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.

Maintains PRD implementation-phase status and artifact links. Always use when a PRP workflow records a planned, implemented, or merged phase in its source PRD, when the user asks to update PRD progress, or when the user invokes /prp-prd-update.

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.

Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when training, evaluating, exporting, or running inference for a TAO monocular depth model. Trigger phrases include "train monocular depth", "DepthAnything v2", "metric depth from single image", "monocular depth estimation".

Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.

Triage gates for the GitHub Copilot Code Review bot on github.com only: provenance (fork or in-repo), intake checks for fork PRs, a one-logical-change scope check with split proposals and issue drafts, and re-review churn detection when fix commits introduce new defects. Use when acting as GitHub Copilot Code Review on a NIC pull request, before nic-code-review. Never load for local reviews (/pr-review prompt, IDE chat, Copilot CLI, Claude Code).

Guides performance optimization for MSBuild engine code. Consult when working on hot paths in evaluation or execution, reducing allocations, choosing collection types, handling strings efficiently, modifying Expander.cs or Evaluator.cs, using Span-based APIs and stackalloc, caching values, or profiling build performance. Also applies when reviewing PRs for performance regression.

Guides CsWin32 P/Invoke interop in MSBuild. Consult when working with the PInvoke class, Windows.Win32 namespaces, FEATURE_WINDOWSINTEROP, HANDLE/HMODULE/HRESULT types, the generic BufferScope type, replacing [DllImport] with CsWin32, or conditioning Windows-only code for source builds.

Rigorous PRD-writing methodology — challenge the idea, verify every claim against actual code, trace every downstream consumer of a mechanism, evaluate performance impact against the schema/indexes that actually exist, record rejected alternatives and open-issue decisions explicitly, and do a dedicated final-check pass before calling it done. Use this when asked to write, draft, or review a PRD, design doc, or feature proposal for this codebase.

Author or scope a first-party Nx migration. Use whenever code removes, renames, or deprecates an option/flag/executor/generator-schema field, changes a default, or bumps a dependency, and someone asks whether existing workspaces need a migration so they don't break on `nx migrate`/upgrade. Covers writing the colocated update-VER/NAME.{ts,spec.ts,md} set, the migrations.json entry (version, requires, implementation, prompt, documentation) or packageJsonUpdates group, and the AI-agent prompt/runbook .md for prompt-only or hybrid (generator + prompt) migrations. Also covers porting an upstream framework's own migrations into Nx. Invoke BEFORE writing, fixing, or editing any migration, migration prompt/runbook, or packageJsonUpdates group, and before concluding a breaking change needs no migration at all.

Rewrite a prompt into a deeper version of the same task, the way a top professional would approach it. Use only when explicitly invoked with /better-prompt.

Find named code entities, inspect callers, and review changed functions with the locally installed Ataraxy Sem CLI. Use for code discovery or Git change review when Sem is available.

Pre-PR validation — working tree status, format, lint, TypeScript check, and protected file check. Workspace-aware: detects which of backend/, frontend/, services/apps/*, services/libs/* were changed and runs only the relevant scripts. Use before submitting any PR, to check if code is ready, or to validate a branch before review.

Open, edit, republish, and Figma-sync the template prototypes in prototypes/ (Claude artifacts of Design, Chat, Slides, Clips, Analytics). Use when asked to open or change a prototype, push one to its app's Figma page, or pull Figma edits back into it.