AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate).
Help users apply behavioral science to product design.
Scientific data analysis including data cleaning, exploratory data analysis (EDA), statistical testing, regression, and reporting.
Automate Bench tasks via Rube MCP (Composio).
Run mxx repository programs, tests, or benchmarks on Runpod instances with GPU machine selection, network volume setup, SSH/scp…
Prepare a benchflow release for launch. Use when the user says "prepare for launch", "release prep", "cut a release", "bump version", or…
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token…
Automate Benchmark Email tasks via Rube MCP (Composio).
Benchmarks the wall-clock runtime of shell commands using hyperfine, runs a command many times, accounts for shell startup overhead, and…
Track and visualize benefit realization against targets
Use when saving progress before a context clear or compaction, or when picking work back up after one.
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views.
Configure Turborepo for efficient monorepo builds with local and remote caching.
Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices.
Interact with a local Chrome browser session via Chrome DevTools Protocol (only on explicit user approval after being asked to inspect…
Have OpenAI Codex review the current branch with documentation research.
This skill should be used when the user asks to "im Benno-Stil antworten", "professionelle Nachricht schreiben", "LinkedIn Antwort…
Every Bento feature, plus the ones their own CLI does not have.
Automate Benzinga tasks via Rube MCP (Composio).
Automates legal precedent and legislation searches on the Korean Supreme Court Library website to retrieve structured case data.
Develops BepInEx plugins with hooks, patches, and mod initialization for Unity games.