Run a focused N-question study session on a subject — MBE, essay, or flashcards. Tracks performance and updates the study plan. Use when the user says "run me 10 questions on [subject]", "do a session on [subject]", "let's do 5 cards on [subject]", or wants to drill a fixed number of questions and have the plan adapt.

Add data to an open investigation — documents, interview notes, or observations. Processes batches against the documented pull criteria, surfaces significant items, and logs everything reviewed for coverage verification. Use when new evidence, interview notes, or document productions come in for an open investigation.

Tabular review — one row per document, one column per data point, every cell cited to source. Built for M&A diligence ("review these 200 target contracts for change-of-control, assignment, and MAC clauses") but works for any batch review that needs a spreadsheet out the other end. Use when user says "tabular review", "review grid", "build a grid", "extract these fields from these contracts", "review these documents for X, Y, Z", "give me a spreadsheet of", "batch review", or points at a folder of documents and asks to compare them.

Detects when Luminance, Kira, or a similar bulk-review tool is in use, hands off the high-volume clause extraction to it, and QAs its output per the trust level in `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`. Use when user says "send to Luminance", "bulk review", "AI extraction", or when diligence-issue-extraction hits a high-volume category.

Wire Ginkgo into a Go package — install the ginkgo CLI and Ginkgo+Gomega, ginkgo bootstrap to generate the suite_test.go (TestXxx/RegisterFailHandler(Fail)/RunSpecs), the package xxx_test convention, dot-import alternatives (aliased import, dsl/* subpackages, --nodot), ginkgo generate, and *testing.T interop via GinkgoT()/GinkgoTB() for testify/gomock. Use when first adding Ginkgo to a repo, bootstrapping a suite, or integrating a *testing.T-based library.

Generate, consume, and enrich Ginkgo reports — console verbosity (-v/-vv/--trace/--no-color/--succinct), machine-readable reports (--json-report/--junit-report with --output-dir/--keep-separate-reports), programmatic reporting nodes (ReportAfterEach, ReportAfterSuite, CurrentSpecReport), AddReportEntry with ReportEntryVisibility, and profiling (--cover/--race/--cpuprofile/--memprofile). Use when you need a report file, custom suite-level reporting, attaching data to a spec, controlling console output, or profiling a suite.

Run Ginkgo suites in parallel — ginkgo -p / --procs, the separate-process (not goroutine) model, SynchronizedBeforeSuite/SynchronizedAfterSuite vs BeforeSuite, GinkgoParallelProcess() for sharding ports/tmpdirs/databases, building a binary once via gexec, and piping child-process output to GinkgoWriter. Use when parallelizing a suite, speeding up integration tests, fixing parallel-only flakes/races, sharding external resources, or choosing between BeforeSuite and SynchronizedBeforeSuite.

ET test execution and failure debugging workflow for WOW. Use when building before tests, cleaning Logs, running server or Hotfix tests through ET.App Test commands, running Unity Editor tests through UnityBridge UnityTestRunRequest, reading Logs/All.log, judging results, and diagnosing failed or unmatched tests.

First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the reviewer has accumulated finding outcomes.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.

Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.

Modern Python project setup with uv, ruff, and pyright. Use when initializing a new Python project, configuring the Python environment, setting up linting/formatting, or when a project needs uv (the fast Python package manager). Trigger on: 'set up Python', 'new Python project', 'configure uv', 'install uv', 'ruff', 'pyright', 'Python linting', 'Python formatting', or when a task requires Python and no pyproject.toml exists yet.

Schedule a prompt to fire on a fixed cadence (recurring loop). Use when the user asks to "run X every N minutes/hours/days", "loop X", "babysit Y", "be proactive about Y every N", or invokes `/loop` directly. Parses `[interval] <prompt>`, picks a clean cron expression, registers the job via the `cron` tool, and executes the prompt once immediately so the user sees activity without waiting for the first cron tick.

Estimate market, segment, or opportunity size with transparent assumptions and uncertainty. Use for TAM/SAM/SOM, sizing scenarios, or comparing the scale of possible opportunities.

Create, edit, or validate reproducible SQL or Python notebooks. Use for notebooks, SQL/Python scratchpads, reproducible exploration, audit trails, or runnable companions where the analysis should be reviewable or rerunnable.

Gather business context from connected or provided sources so downstream analysis starts with the right framing. Use when an analytical question depends on missing context, such as what a metric means, what changed recently, or which sources should be checked. If the same prompt asks for diagnosis, recommendation, or a deliverable, gather context first and continue to the focused skill.

Design KPI frameworks, metric definitions, targets, guardrails, and measurement plans for product or business decisions. Use when success metrics, drivers, guardrails, targets, or the measurement approach need to be defined or improved.

Operate Claude Code CLI (v2.1+) via the terminal only when the user explicitly requests Claude Code or names this skill. Covers print mode (-p), interactive tmux sessions, and background (--bg) orchestration.