全部能力

Write high-quality bug reports that get fixed quickly. Use when reporting bugs, training teams on bug reporting, or establishing bug report standards.

Use when optimizing conversion rates, designing A/B tests, or improving landing pages. Covers A/B testing methodology, landing page optimization, form design,…

Use when encountering unfamiliar import statements, exploring dependency APIs, or when user asks "what's import X" or "what does X do". Generates on-demand API…

Scaffold a production-ready full-stack monorepo with working MVP features, tests, and CI/CD. Generates complete CRUD functionality, Clerk authentication, and…

Validates all code changes before committing by running format, lint, type, and unit test checks. Use after making backend (Python) or frontend (TypeScript)…

backtesting.py configuration for SQL oracle validation and range bar pattern backtesting. Use when running backtesting.py against ClickHouse SQL results,…

Set up a full AI ensemble/mob programming team for any software project. Creates agent definition files (.claude/agents/), coordinator instructions (.team/coordinator-instructions.md), project owner constraints (PROJECT.md), team conventions (AGENTS.md), architectural decisions (docs/ARCHITECTURE.md), domain glossary, and supporting docs. Use when: (1) starting a new project and wanting a full expert agent team, (2) the user asks to "set up a team", "create a mob team", "set up ensemble programming", or "create agent profiles", (3) converting an existing project to the driver-reviewer mob model, (4) the user wants AI agents to work as a coordinated product team with retrospectives and consensus-based decisions.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework with built-in backward tracing for…

feature 流程的可选阶段 0——想法还模糊时通过对话理清楚到能进 design 的程度。AI 的角色是思考伙伴：挖用户真正想解决的问题（而不是停在 TA 最先脱口而出的方案上），在用户带着方案来时主动评估它、必要时提出更好的替代。聊完产出 {slug}-brainstorm.md…

把一个新仓库或有零散文档的仓库接入 easysdd 体系。两条路径自动判断：空仓库路径（仓库内无任何 spec 类文档也没有 easysdd/ 目录）从零搭骨架；迁移路径（仓库内已有零散文档或部分 easysdd/ 结构）先做审计报告 +…

Rust testing best practices covering test architecture, assertions, mocking, snapshots, event testing, determinism, and integration patterns for the codex-rs…

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Search for places, businesses, and locations using Google Maps APIs via x402. USE FOR: - Finding businesses by name or type - Searching nearby places - Getting detailed place information (address, hours, reviews) - Finding restaurants, stores, services in an area - Getting business ratings and reviews TRIGGERS: - "find", "search for", "locate", "nearby" - "restaurants near", "hotels in", "stores around" - "business details", "opening hours", "reviews for" - "places in", "what's near", "directions to" Use `npx agentcash@latest fetch` for Google Maps endpoints. Choose partial ($0.02) vs full ($0.05-0.08) based on data needs.

Follow a complete coding workflow for one scoped implementation task: understand, plan, implement, test, verify, and report.

Validez la qualité de vos vidéos IA avant publication avec une checklist complète couvrant technique, créatif, et positionnement marque. Use when: **Avant…

Use when running paid advertising campaigns on Xiaohongshu, setting up promoted posts, managing ad budgets, optimizing ad performance, or scaling growth…

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a…

Test Node.js applications with Jest including unit tests, integration tests, mocking, code coverage, and CI/CD integration

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".

Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback…