Loading...
Loading...
Found 3,721 Skills
Smoke test for alicloud-ai-contactcenter-ai. Validate minimal authentication, API reachability, and one read-only query path.
Smoke test for alicloud-security-content-moderation-green. Validate minimal authentication, API reachability, and one read-only query path.
Test skill for security scanning
Add support for a new CLI command. Use when implementing a handler or adding to SIMPLE_SAFE.
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Generate manual test plans for PR changes with verified commands and pass/fail criteria
Comprehensive web accessibility audit using WCAG 2.1/2.2 guidelines. Evaluate compliance across 4 POUR principles (Perceivable, Operable, Understandable, Robust) with A, AA, AAA conformance levels.
Proof-driven exploitation with 4-level evidence system, bypass exhaustion protocol, mandatory evidence checklists, and strict EXPLOITED/POTENTIAL/FALSE_POSITIVE classification.
Эксперт по интеграционным спецификациям. Используй для документирования интеграций, webhooks, event schemas и data flows.
Comprehensive conversion rate optimization framework combining customer-centric methodology (CRE), form optimization, page optimization, signup flows, onboarding, paywalls, popups, and UI/UX auditing. Use when optimizing conversion rates, improving landing pages, reducing signup abandonment, increasing activation, optimizing paywalls, designing popup strategies, or conducting conversion-focused UX audits. Covers the full conversion funnel from first impression through activation and upgrade.
Benchmark any agent skill to measure whether it actually improves performance. Use when the user wants to evaluate, test, or compare a skill against baseline, or when they mention "benchmark", "eval", "skill performance", or "does this skill help". Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
Comprehensive Test Driven Development guide for engineering subagents with multi-framework support, coverage analysis, and intelligent test generation