Поиск skills
Найдите подходящую возможность для вашего агента.
time-helper
This skill should be used when users request current time information, timezone conversions, or any time-related queries. It provides a simple interface to Claude's built-in time-tools functionality for accurate time information and timezone conversions.
sc-repomix-nuget
Generate AI-optimized context for NuGet packages using Repomix. Use when preparing AI docs, API references, or dependency analysis ("nuget context", "repomix nuget").
native-app-performance
Native macOS/iOS app performance profiling via xctrace/Time Profiler and CLI-only analysis of Instruments traces. Use when asked to profile, attach, record, or analyze Instruments .trace files, find hotspots, or optimize native app performance without opening Instruments UI.
integrating-stripe-payments
Complete guide for integrating Stripe payments (subscriptions or one-time) with Convex + Next.js. Includes user interviews, API setup, webhook configuration, testing phases, and production deployment. Use this skill when Adding payment functionality to a Convex + Next.js app
stripe-payment
Stripe 支付集成统一接口。支持 Checkout Session、订阅管理、Webhook 处理、 Customer Portal、退款等功能。让 Agent 能快速实现支付功能上线。
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
instruction-adherence
Use when instruction drift is likely: multi-step tasks, mid-task detours (tooling upgrades), or when agents must consult MCP memory / Skills / sessions and re-anchor repeatedly. Triggers: 'stay on track', 'follow instructions', 'resume main task', 'detour', 'intermediate task done'.
engineering-collaborator
The Technical Bridge of the PM Brain. Manages PM-Engineering collaboration, architecture decisions, tech debt, and translates technical constraints to business impact. Use for
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
work-command-center
Primary orchestration hub that FIRST enforces skill discipline (checking for applicable skills before any action), then manages deliverables, deadlines, team coordination, priority coaching, and work-life balance. Provides structured task management, daily standups, and orchestrates specialized skills when technical deep-dives are needed.
event-storming
Event Storming 引導專家，透過 Plan Mode 問答帶領使用者完成 Event Storming 工作坊，識別 Domain Events、Commands、Actors、Policies 等元素，最終生成 Markdown 文件。
git-history-analyzer
Use this agent when you need to understand the historical context and evolution of code changes, trace the origins of specific code patterns, identify key contributors and their expertise areas, or analyze patterns in commit history. This agent excels at archaeological analysis of git repositories to provide insights about code evolution and development patterns. <example>Context: The user wants to understand the history and evolution of recently modified files.\nuser: "I've just refactored the authentication module. Can you analyze the historical context?"\nassistant: "I'll use the git-history-analyzer agent to examine the evolution of the authentication module files."\n<commentary>Since the user wants historical context about code changes, use the git-history-analyzer agent to trace file evolution, identify contributors, and extract patterns from the git history.</commentary></example> <example>Context: The user needs to understand why certain code patterns exist.\nuser: "Why does this payment processing co
contrarian-thought-partner
Brutal, honest critique of strategies, plans, and analyses. Use when someone explicitly wants their thinking torn apart, stress-tested to destruction, or called out on weak logic. Triggers include requests like "tear this apart", "be brutal", "what's wrong with this", "play devil's advocate", "tell me why this won't work", or "poke holes in this". This is adversarial by design, not for collaborative exploration, but for ruthless pressure-testing.
tool-selection-framework
Design systematic decision frameworks for selecting appropriate AI tools (Claude Code vs Gemini CLI) based on context requirements, codebase size, reasoning depth needs, and task complexity. Use this skill when starting projects with unclear tool requirements, optimizing context-constrained workflows, or designing multi-phase strategies that leverage multiple tools' strengths. This skill helps match tool capabilities to task characteristics, preventing wasted context and ensuring optimal resource allocation.
interview-records
Archive of past customer interviews. Contains full transcripts, summaries, pain points, outcomes, and skills used. Use for referencing previous conversations with the same company or finding similar case patterns.
phase-02-requirements-scope
Define detailed functional, non-functional, security, compliance, and data requirements. Create requirements traceability matrix and get stakeholder sign-off.
