Results for “t-test”

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experimentation and synthesis, producing papers and presentations.

Scaffold and develop AI agents using OpenAI Agents SDK patterns, covering agent definition, tools, guardrails, handoffs, context, RAG pipelines, streaming, API routes, testing, and debugging.

Implements comprehensive backtesting capabilities for Pine Script indicators and strategies. Use when adding performance metrics, trade analysis, equity curves, win rates, drawdown tracking, or statistical validation. Triggers on "backtest", "performance", "metrics", "win rate", "drawdown", or testing requests.

Build, review, debug, or test declarative statistical visualizations in Python with Altair and Vega-Lite, including chart marks, typed encodings, transforms, parameters, layers, facets, and specification export.

Comprehensive guide to prevent unmaintainable code, especially from AI generation. Covers code duplication, documentation, error handling, naming conventions, architecture, performance, dependencies, modularity, testing, and technical debt prevention. Essential for code reviews and ensuring long-term code health.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Enforce writing specifications before any code, with structured formats, acceptance criteria, and validation to reduce rework and clarify requirements.

Modify, build, test, debug, and contribute to the NVIDIA cuOpt codebase (C++/CUDA, Python, server, CI). Includes guidance for solver internals, pull requests, DCO signoff, and code conventions.

Orchestrates parallel AI agent sessions using dmux, a tmux pane manager, with patterns for research, implementation, testing, and code review across multiple harnesses.

Implements code features phase by phase from a JSON or Markdown plan, with configurable unit-test and quality-gate choices, token-budgeted execution, and resumable state.

Bun all-in-one JavaScript runtime and toolkit reference. Covers runtime APIs (file I/O, HTTP server, SQLite, shell), ultra-fast package manager, built-in bundler with plugins, test runner with mocking, TypeScript support, and Node.js compatibility.

Use this skill when writing, rewriting, or improving marketing copy for any page (homepage, landing page, pricing, feature, product, or about page). This skill produces clear, compelling, and testable copy while enforcing alignment, honesty, and conversion best practices.

Audit and optimize application runtime performance (Core Web Vitals, slow code, load time). Use when "slow page", "LCP/INP/CLS", or "optimize performance". JS payload → audit-bundle-size. Concurrent breaking point → test-load. Timeouts/retries → audit-resilience.

Use this when a Python service, package, or repository needs a maintainable internal structure for modules, domain logic, adapters, config, entrypoints, and tests. Trigger on requests about project layout and internal organization for Python systems.

Generates Angular code and provides architectural guidance for projects, components, services, and more, covering reactivity, forms, dependency injection, routing, accessibility, animations, styling, testing, and CLI tooling.

Build, scaffold, and deploy Power Automate cloud flows programmatically via the FlowStudio MCP server, including constructing flow definitions, wiring connections, deploying, and testing.

Simulates BGP hijacking attacks in isolated lab environments to test RPKI deployment, route origin validation, and BGP monitoring defenses against prefix hijacking and route leak attacks.

Test for Server-Side Request Forgery vulnerabilities by probing cloud metadata endpoints, internal network services, and protocol handlers through user-controllable URL parameters.

Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps, and generates API facade designs for aging codebases.

Automate continuous integration, deployment, and post-deployment verification of developed solutions. Use when setting up CI/CD pipelines, deploying to staging/production environments, running automated tests in CI, or verifying deployments. Ensures reproducible builds and reliable deployments.

Agent profile for plan PPC account structure, creative testing, budget hypotheses, measurement, and landing-page alignment. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Dart static analysis, linting, formatting, and code-generation standards. Use only for analysis_options.yaml, build_runner, dart format, DCM, lefthook, or analyze/format CI failures; defer Dart language, null-safety, Flutter tests, and generic CI questions.

Identify, test, deploy, and verify software updates across an organization's IT infrastructure using a structured patch management workflow with phased rollouts and automated assessment.

Write defensive, portable Bash scripts for automation, CI/CD, and system utilities, with strict error handling, safe argument parsing, and testing via Bats and ShellCheck.

Get best practices for developing applications with Helidon 4 (SE and MP). Use when working with Helidon SE or Helidon MP, HttpService routing, Helidon DB Client, MicroProfile Config, Helidon Security, or Helidon testing in Java 21+ projects.

Analytics tracking, interpretation, funnel analysis, product metrics, and ROI measurement. Use when setting up GA4/GTM tracking, interpreting analytics data, analyzing conversion funnels, calculating ROI, or measuring product engagement. Triggers on "analytics," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "funnel analysis," "conversion rates," "user flow," "cohort analysis," "retention," "product metrics," "North Star metric," "ROI," "break-even," "payback period," "investment analysis," "validate my funnel," "why isn't my funnel converting," or "executive financial report." For A/B test setup, see ab-test-setup.

Detect and exploit Server-Side Template Injection (SSTI) vulnerabilities across Jinja2, Twig, Freemarker, and other template engines to achieve remote code execution during authorized penetration tests.

Use this skill for turning issues into implementation plans, branches, code changes, tests, and PR descriptions. Trigger when the task involves programming work related to Issue To PR Agent, implementation, audits, debugging, strategy, or validation.

Coordinates purple team exercises by running MITRE ATT&CK-mapped attack scenarios with real-time detection testing and collaborative gap remediation.

Collects publicly available information about a target organization to identify attack surfaces, social engineering targets, technology stacks, and credential exposures for authorized security testing.

Select the right Proof of Life (PoL) probe type based on hypothesis, risk, and resources to match validation method to the real learning goal.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Claude Code built-in /verify (which runs the app to observe a single change working) — this one walks the CLAUDE.md "Features (Behavior Anchors)" list.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".