Load test a Databricks App to find its maximum QPS. Use when: (1) User says 'load test', 'benchmark', 'QPS', 'throughput', or 'performance test', (2) User wants to find how many queries per second their app can handle, (3) User wants to set up load testing scripts for their agent, (4) User wants to view load test results/dashboard, (5) User wants to validate results or observe latency/error rate with MLflow tracing.

Load test a Databricks App to find its maximum QPS. Use when: (1) User says 'load test', 'benchmark', 'QPS', 'throughput', or 'performance test', (2) User wants to find how many queries per second their app can handle, (3) User wants to set up load testing scripts for their agent, (4) User wants to view load test results/dashboard, (5) User wants to validate results or observe latency/error rate with MLflow tracing.

Enable Supervisor API background mode for long-running agent tasks. Use when: (1) Agent needs to run tasks longer than HTTP timeout limits, (2) User says 'background mode', 'long-running', 'supervisor api', (3) Converting from streaming to background polling pattern, (4) Agent needs resilience to connection drops during execution.

Terminal and TUI automation CLI for AI agents. Use when the user needs to create a terminal session, run a command in a terminal, automate an interactive CLI or TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, or test a CLI workflow with reviewable artifacts.

Empirically measure what each of model-right-sizer's four research-grounded citation layers (Token Economics, IBPO, BudgetThinker, Speculative Decoding) actually does to its blueprints — instead of trusting the citations alone. Renders layer-ablated variants (any of the 16 layer subsets), runs a fixed six-task benchmark through each variant's Pass A blueprint, and for a scoped subset actually executes the recommended build and scores whether real effort stayed within the predicted budget (wrapping `classify_budget_adherence`). Reports each layer's effect in ISOLATION vs. a zero-layer baseline, and every COMBINATION across the full 16-subset grid, so synergy or redundancy is visible, not assumed away. Read-mostly: writes only a scratch directory and a final report, never `agents/model-right-sizer.md`. Use when someone says "does the Token Economics layer actually change anything", "ablate the research layers", "run the layer-ablation study", or "audit model-right-sizer's citations empirically".

Use scipy.optimize.curve_fit for nonlinear least squares parameter estimation from experimental data.

Design effective excitation signals (step tests) for system identification and parameter estimation in control systems.

How to decide whether and how much to reorder a SKU. Load this whenever a task involves reorder recommendations, purchase orders, or "should we restock" questions.

Interactively debug source code — set breakpoints, step through execution line by line, inspect live variable state, evaluate expressions against the running program, and navigate the call stack to trace root causes. Use when a program crashes, raises unexpected exceptions, produces wrong output, when you need to understand how execution reached a certain state, or when print-statement debugging isn't revealing enough.

Execution checklist for net-new Algolia search, browse, autocomplete, ecommerce search, recommendations, personalization, Dynamic Re-Ranking, or search UI builds. Use during a greenfield build to keep data contract, event taxonomy, index configuration, UI, and release QA visible as explicit checkpoints with completion signposts and suggested artifacts, so agents proceed deliberately and document tradeoffs and deferrals. Do NOT use as the entry point for Algolia work; start with algolia-discovery-planning, which maps the request to the lifecycle and loads this skill for net-new builds.

Use this skill whenever a user wants to execute operations against Algolia indices or accounts — deleting records, copying/migrating indices, backing up data, importing/exporting records, managing API keys, editing synonyms, configuring rules, changing settings like facets, clearing indices, or automating Algolia in CI/CD pipelines. The key signal is that the user wants to *act on* their Algolia data or configuration (server-side / backend / admin operations), regardless of whether they mention "CLI" or "command line." If someone names a specific Algolia index and wants to change, move, query, or manage it, use this skill. Do NOT use for frontend search UI work (InstantSearch, React components, autocomplete widgets), Algolia dashboard GUI questions, or evaluating Algolia vs. other providers.

Identify what could go wrong before launch by imagining failure and working backward. Use after a spec is approved but before you ship — surfaces risks the team isn't talking about.

Write a hypothesis, define success metrics, and plan a holdout strategy. Use when designing A/B tests or experiment plans.

Write a weekly stakeholder update on a core pillar or initiative — metrics, bets in progress, customer quotes, and highlights. Use when you need to keep leadership and cross-functional partners informed on what's shipping and what's moving.

Read completed tickets from Linear, Jira, or GitHub Issues, filter to user-visible changes, group by product area, and write polished user-facing release notes saved as a .docx to Google Drive. Use before each release or on a weekly cadence.

Generate tailored SaaS and product marketing ideas across organic, paid, community, partnerships, product-led growth, retention, and launch channels. Use when the user asks for `/marketing-ideas`, marketing brainstorms, launch ideas, channel ideas, growth tactics, or a prioritized marketing plan.

Collect a testimonial (name, rating, text, email) and publish it to testimonials.html

Profiling methodology and optimization strategy for performance work. Use when the user asks to "make this faster", "optimize", "profile", "reduce latency", "fix slow", "improve throughput", or when investigating performance regressions.

Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.

Retrospective meta-skill for the `repo-visuals` skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes concrete edits to `repo-visuals/SKILL.md` as a reviewable diff. Runs on-demand, not per run.