测试与安全技能

Deep behavioral security audit for AI agent skills and MCP tools. Performs deterministic static analysis (AST + Semgrep + 15 specialized scanners), cryptographic lockfile generation, and optional LLM-powered intent analysis. Use when installing, reviewing, or approving any skill, tool, plugin, or MCP server — especially before first use. Replaces basic safety summaries with full CWE-mapped, OWASP-tagged, line-referenced security reports.

中文简介正在准备中。当前显示原文说明。

Blockchain security API for AI agents. Scan tokens, simulate transactions, check addresses for threats.

中文简介正在准备中。当前显示原文说明。

Design and implement adaptive testing systems using Item Response Theory (IRT). Use when working with computerized adaptive tests (CAT), psychometric assessment, ability estimation, question calibration, test design, or IRT models (1PL/2PL/3PL). Covers test algorithms, stopping rules, item selection strategies, and practical implementation patterns for K-12, certification, placement, and diagnostic assessments.

中文简介正在准备中。当前显示原文说明。

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

中文简介正在准备中。当前显示原文说明。

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.

中文简介正在准备中。当前显示原文说明。

Compare models with A/B testing for selection

中文简介正在准备中。当前显示原文说明。

Plan, prioritize, and design rigorous A/B tests using the Test Velocity Method. Use when a user wants to test a landing page, CTA, email, signup flow, pricing page, or any digital experience — this skill produces a complete, dev-ready test plan with hypothesis, sample size, duration, segmentation strategy, and guardrail metrics.

中文简介正在准备中。当前显示原文说明。

Scan HTML and JSX for accessibility issues and get fix suggestions. Use when you need to catch WCAG violations before they hit production.

中文简介正在准备中。当前显示原文说明。

This skill provides a high-quality, manually crafted prompt template for AI google veo generation.

中文简介正在准备中。当前显示原文说明。

Install, configure, and manage 1-SEC — an open-source, all-in-one cybersecurity platform (16 modules, single binary) on Linux servers and VPS instances. Use when the user asks to secure a server, install security monitoring, set up intrusion detection, harden a VPS, protect an AI agent host, or deploy endpoint defense. Covers installation, setup, enforcement presets, module configuration, alert management, and ongoing security operations.

中文简介正在准备中。当前显示原文说明。

Score a repository's agentic legibility from repo-visible evidence only. Use when Codex needs to audit how easy a codebase is for coding agents to discover, bootstrap, validate, and navigate, especially for harness-engineering reviews, developer-experience audits, repo cleanup, or before/after comparisons after improving docs, tooling, or architectural constraints.

中文简介正在准备中。当前显示原文说明。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

中文简介正在准备中。当前显示原文说明。

Use for Hono (web framework) development when Codex needs to consult Hono documentation or test Hono apps via the `hono` CLI. Trigger on requests about Hono CLI usage, searching/browsing Hono docs, or testing Hono routes without running a server.

中文简介正在准备中。当前显示原文说明。

Test authoring guidance

中文简介正在准备中。当前显示原文说明。

Production-ready CSS transition snippets for web apps. Use when adding or reviewing UI motion for badges, dropdowns, modals, panel/page reveals, card resizes, number pop-ins, text/icon swaps, success checks, avatar-group hovers, and validation shakes. Supports namespaced commands: transitions reveal (list catalog), transitions review (audit project fit), and transitions apply (install the best-fit snippet with hooks and reduced-motion handling).

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks to "implement a DiD regression", "run a staggered difference-in-differences", "set up an event study", "implement IV / 2SLS", "run a regression discontinuity design", "build synthetic control", "do propensity score matching", "test parallel trends", "run Honest DiD", "wild cluster bootstrap", "Callaway-Sant'Anna", "Sun-Abraham", "Bacon decomposition", "double machine learning", "debiased machine learning", "DML / DoubleML", "cross-fitting", "causal forest", "heterogeneous treatment effects", "ATE with ML controls", "which causal design fits my data", or needs causal-inference code, diagnostics, or identification writing in Python (StatsPAI), R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape, with runnable validated templates, ML-based causal inference patterns, and Journal of Finance applications.

中文简介正在准备中。当前显示原文说明。

Implement a change end-to-end from a freeform prompt - settle the requirements, design the engineering approach and get it approved, implement with TDD, run the format/compile/credo/coveralls gates without shortcuts, self-review the diff like a senior engineer, QA the finished change in the running app, record a demo video when it is visible there, then commit and open the PR. Use when the user wants to "complete an issue", "work the ticket", or hands over a description of something to build.

中文简介正在准备中。当前显示原文说明。

QA a change by driving the running dev app like a real QA engineer - start the server and a real browser session, write a checklist from the agreed requirements and the diff, execute every item with evidence, then go looking for anything that looks off even where the diff did not touch. Reports findings by severity and separates regressions from pre-existing problems. Use after a change is implemented and the gates pass, when the user asks to "QA this", "test it in the app", or "check it actually works".

中文简介正在准备中。当前显示原文说明。

Test-driven development with a red-green-clean loop, running mix credo on the whole project at the end of every vertical slice so standards violations are fixed in the slice that introduced them instead of piling into a refactor at the end. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

中文简介正在准备中。当前显示原文说明。

v09-audit-evidence-map

中文简介正在准备中。当前显示原文说明。

yardlet-binary-crate-focused-tests

中文简介正在准备中。当前显示原文说明。

Use when implementing any feature or bugfix, before writing implementation code

中文简介正在准备中。当前显示原文说明。

i18n-leak-audit

中文简介正在准备中。当前显示原文说明。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

中文简介正在准备中。当前显示原文说明。