Loading...
Loading...
Found 3,718 Skills
Senior AI Product Manager. Expert in Probabilistic Strategy, Rapid Agentic Prototyping, and Hypothesis Generation for 2026.
Smoke test for alicloud-media-live. Validate minimal authentication, API reachability, and one read-only query path.
Minimal visual reasoning smoke test for Model Studio QVQ.
Generate statistical analysis code with 4-round review. Select appropriate statistical tests, interpret results, and produce analysis reports with p-values, effect sizes, and confidence intervals. Use when analyzing experimental data for a paper.
Write usability test scenarios with tasks, success criteria, and observation guides.
Build and deploy agentic finance applications on the Alva platform. Access 250+ financial data sources (crypto, equities, macro, on-chain, social), run cloud-side analytics, backtest trading strategies, and release interactive playbooks -- all from your AI agents.
Run 7 UI integrity checks on any URL. Catches blank renders, contrast failures, undersized tap targets, horizontal overflow, broken images, text overflow, and element overlap. Returns structured findings your agent can read and fix. Use when asked to validate UI, browser check, check before shipping, UI integrity check, accessibility check.
Design click/first-click tests to evaluate navigation and information findability.
当用户需要模拟API、新增接口mock、启动mock服务器或管理模拟数据时，使用此技能。支持REST和SSE端点
A complete guide to developing plugins for the MusicFree music player. Triggered when users request to write, create, or develop MusicFree plugins, or to adapt a music website or API into a MusicFree plugin. Covers the full process including plugin protocols, media type definitions, method signatures, sandbox environment, site analysis, local debugging, release and updates, etc. This Skill is designed for AI execution, guiding AI to collaborate with beginners to complete plugin development.
Generate and run comprehensive test suites — unit tests, integration tests with real services (testcontainers/docker-compose), and Playwright E2E tests. Analyzes coverage gaps, spawns parallel test-generator agents per tier, runs tests, and heals failures (max 3 iterations). Use when generating tests for existing code, improving coverage after implementation, or creating a full test suite from scratch. Chains naturally after /ork:implement. Do NOT use for verifying/grading existing tests (use /ork:verify) or running tests without generation (use npm test directly).
Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.