发现 Skills

Show enriched status of your open PRs — CI checks, approvals, and unresolved review threads in one table.

Guide to transform prototypes into robust, distributable Python packages using the src/ layout, a hybrid paradigm, and strict configuration management.

基于预览文档和 Best Practice，实际拆分组件代码，生成符合规范的子组件。优先从 store 获取数据，避免 props 透传。

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include "browse", "check the page", "take a screenshot", "test the UI", "fill the form", "click the button", "QA", "visual check", "healthcheck", and any task requiring a real browser.

Manage Apple Notes via the memo CLI on macOS.

Manage Apple Reminders via remindctl CLI on macOS

Use Codex CLI with your OpenAI subscription

name: business-model-analyzer description: Use this agent when you need to analyze business models, evaluate monetization strategies, or optimize business operations. Call this agent when planning ...

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".

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits".

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".

Analyze raw prompts, identify user intent and missing context, map the request to ECC components (skills/commands/agents/hooks), and produce a ready-to-paste, optimized prompt. Advisory role only — never execute the task itself. TRIGGER when the user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or otherwise explicitly asks to enhance prompt quality. Also trigger on equivalent Chinese phrases (i.e., Chinese-language requests that ask to optimize or improve a prompt). DO NOT TRIGGER when the user wants the task executed directly or says phrases like "just do it" (or the equivalent in another language). DO NOT TRIGGER when the user asks to "optimize code", "optimize performance", or "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

AI辅助开发的回归测试策略。沙盒模式API测试，无需依赖数据库，自动化的缺陷检查工作流程，以及捕捉AI盲点的模式，其中同一模型编写和审查代码。

NestJS architecture patterns for modules, controllers, providers, DTO validation, guards, interceptors, config, and production-grade TypeScript backends.

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"

B2: Check existence of table_name.column_name patterns in the reference specification

Redesign a learning space using biophilic design principles to improve focus, calm, and wellbeing. Use when classroom environment contributes to restlessness, poor attention, or stress.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

チーム全体で統一された開発プロセスとコーディング規約を確立するための包括的なガイドとテンプレート。開発ガイドライン作成時、コード実装時に使用する。

Creates Jira epics for large features following Prowler's standard format. Trigger: When user asks to create an epic, large feature, or multi-task initiative.

Comprehensive guide for creating and developing Doover device applications, including state machines, workers, and hardware I/O patterns

Query Stream data and run CLI operations against Chat, Video, Feeds, and Moderation: list channels, list calls, show flagged messages, find users, query any Stream resource. Run stream api / stream config / stream auth commands. Install the Stream CLI binary. Use when the user gives operational verbs ('list', 'show', 'find', 'check', 'query') with Stream nouns, or invokes the CLI literally.

Reviews project text — documentation, READMEs, marketing copy, UI strings, code comments, error messages — for compliance with the U.S. federal government Plain Language Guidelines. Produces structured edit recommendations with concrete rewrites. Activates on plain language review, readability check, copy audit, "make this clearer," or "improve the writing."