Use for paid campaign strategy on Google, Meta, LinkedIn or X: structure, targeting, bids, retargeting and budgets. Scores account health with ad_health_scorer.py and models ROAS with roas_calculator.py. Ad copy only: ad-creative.

Design a RAG pipeline: chunk size, embedding model, vector database and retrieval quality metrics. Use whenever the user builds search over their docs, picks a vector store or finds answers miss the right context.

Use before high-stakes or multi-file coding (auth, databases, migrations), or when asked to plan carefully and avoid invented APIs. Runs discuss, map, decompose, execute and verify, checking every import and API exists. Not for trivial edits.

Use for any local business's Google Business Profile, Maps ranking, service-area pages, citations or review replies, before writing. Checks NAP consistency with nap_checker.py and generates LocalBusiness schema and area pages with its scripts.

Write the least code: no over-engineering, fewer dependencies. Use whenever the user wants it simpler; applies a ladder first: YAGNI, reuse, stdlib, native platform, existing deps.

Check a diff for overbuilt code: hidden assumptions, needless abstraction, non-surgical changes, unverified goals (Karpathy's four principles). Load whenever the user thinks they overcomplicated something or wants a pre-commit check.

Start a fullstack project or audit a codebase: pick a stack (Next.js, FastAPI, MERN, Django), scaffold it and score code quality. Use whenever the user asks which stack to use, wants a new web app set up, or asks how good or messy their codebase is.

Use for any code review: a pull request, a diff, a commit, or a pasted function, handler or file in TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#/.NET, Java, C, C++, Rust, Ruby, PHP or Dart/Flutter. Applies per-language rule packs (security such as SQL injection and missing auth, async and resource handling, error handling, performance) and scripts that score a PR's risk and complexity, then gives a merge verdict with blocking and non-blocking findings. Use whenever the user asks to review, check or look over code, says 'code review', 'review this PR', 'review this diff' or 'is this safe to merge', or asks what is wrong with a snippet, even a single function.

Use when architecting a multi-step LLM or agent pipeline, choosing single vs multi-agent, or fixing context bloat and broken handoffs. Scaffolds the pattern, handoff contracts and failure handling with workflow_scaffolder.py.

Authorized penetration testing of an app or API: vulnerability scans, OWASP Top 10 checks, dependency audits and a pentest report. Use whenever the user asks if their app is secure or hackable, wants a security scan or a pentest report.

Use for putting ML models or LLM features into production: deployment, MLOps, drift monitoring, RAG pipelines, LLM API cost and retries. Deploys with model_deployment_pipeline.py, monitors with ml_monitoring_suite.py and builds RAG with rag_system_builder.py.

End-to-end testing for Falcon Foundry apps using Playwright and @crowdstrike/foundry-playwright. TRIGGER when user asks to "add e2e tests", "add playwright tests", "write end-to-end tests", "test my app", or mentions "e2e", "playwright", or "end-to-end" in the context of testing a Foundry app. DO NOT TRIGGER during normal app creation, UI development, or function development. This skill is opt-in; not all apps need e2e tests.

Use when a generated resource upgrades old state by refresh and the first plan shows labels or lists changing from [] or {} to null. Covers readEmptyAs and a flatten hook.

Use when tfgen fails for a released resource whose Create returns only an id or whose Update returns {}. Names the overrides keys.

Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files, and whenever a test or spec file is written, reshaped, reviewed, or deleted: the four-question test authoring gate and the junk-test classes live here.

Certification coach for Flows apps. Captures the app name, value case, persona, problem, and design intent through a structured conversation and writes App-Brief.md at the repo root. Write the brief after the SME conversation — do not dump an empty template as the opening move. If they came from Fusion Custom apps Start building, follow start-flows-app so https://localhost is up first. Use when the user asks to start an app brief, run the certification coach, fill out the app brief, or run flows-app-brief.

Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.

Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.

Use when implementing, fixing, or reviewing Zeebe engine code in zeebe/engine/ — BPMN process execution, DMN decision evaluation, job lifecycle, user/identity management, batch operations, variables, deployments, signals, messages, timers, multi-tenancy, or authorization. Also when modifying or reviewing processors, event appliers, state classes, record value types, intents, or engine tests.

Create or update a custom WordPress plugin for site functionality that should not live in a theme or a block. Use when the user needs reusable behavior, admin/settings UI, hooks, REST endpoints, scheduled tasks, integrations, or server-side logic for a Studio-backed site.