发现 Skills

Manages feature flags with Laravel Pennant. Activates when creating, checking, or toggling feature flags; showing or hiding features conditionally; implementing A/B testing; working with the @feature directive; or when the user mentions feature flags, feature toggles, Pennant, conditional features, rollouts, or gradually enabling features.

Create and manage pi-coding-agent skills. Use when creating new skills, understanding skill structure, writing SKILL.md files, or debugging skill loading. Covers skill format, frontmatter, directory structure, and best practices.

Clarify vague requirements into an executable ClarifiedRequirement, producing scope, assumptions, constraints, and open/blocked points for consumption by modeling-first or spec-driven development. Trigger terms: requirement clarification, clarify requirement, supplement requirements, organize requirements, define scope.

Warren Buffett's quality value investing approach, emphasizing buying high-quality businesses at reasonable prices

Automated CI/CD pipeline setup with GitHub Actions, deployment strategies, and automation workflows. Use for build automation, testing, and deployment.

GraphQL schema design, resolvers, and client integration. Use for building GraphQL APIs and front-end queries.

Analyze Python code quality using MCP tools - complexity, clones, dead code, coupling. Use when user asks about code quality, refactoring, maintainability, duplicates, or technical debt.

Prisma Postgres setup and operations guidance across the Prisma Console, create-db CLI, Management API, and Management API SDK. Use this when creating Prisma Postgres databases, working in the Prisma Console UI, provisioning with create-db/create-pg/create-postgres CLIs, or integrating programmatic provisioning via service tokens or OAuth.

Restart a Claude Code session to reload new skills, manage context, or start fresh. Use this skill when skills have been added or modified, when you need to compact or clear accumulated context, or to apply configuration changes.

Browser automation, visual testing, and screenshot validation using Playwright MCP server for accelerated web development. Master visual regression testing, automated UI testing, and cross-browser validation.

Detects and flags AI writing patterns in text. Use it when reviewing content for authenticity, editing AI-generated text, or checking your own writing for mechanical patterns. Identifies 24 documented patterns across categories including content structure, language choices, style markers, communication patterns, and filler language. Returns specific pattern violations with examples and suggestions.

Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for a JARVIS AI assistant.

Systematic quality validation, test verification, and a safe merging workflow for deployment and release operations. ALWAYS asks for confirmation when the user wants to ship, deploy, merge, release, or complete features to production, merge to the main branch, or finalize features. This is a DESTRUCTIVE operation (merges and deletes branches).

Automate Serpdog tasks via Rube MCP (Composio). Always search tools first for current schemas.

Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting, estimated spend, and identifies competitive gaps and opportunities. Use when user says "competitor ads", "ad spy", "competitive analysis", "competitor PPC", or "ad intelligence".

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and conversion rate potential. Use when user says "landing page", "post-click experience", "landing page audit", "conversion rate", or "landing page optimization".

Statechart and state machine modeling for lifecycle and behavior specification

Reviews finished and in-progress digital products to assess adherence to design specifications and discover potential issues. Use when user says "design review", "design QA", "QA review", "check implementation", "visual bugs", "compare to design", "match the specs", "review the build", "before launch", "pre-launch review", "implementation review", "verify design", "design validation", "spacing issues", "visual discrepancies", "accessibility review", "WCAG compliance", or "responsive testing". Validates implementation against design intent, identifies visual and interaction discrepancies, and provides actionable feedback. Do NOT use when still designing concepts (use design-concepts), need to understand users (use design-research), or nothing has been built yet.

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.

Azure Tables SDK for Python (Storage and Cosmos DB). Use for NoSQL key-value storage, entity CRUD, and batch operations. Triggers: "table storage", "TableServiceClient", "TableClient", "entities", "PartitionKey", "RowKey".

Azure Identity SDK for .NET. Authentication library for Azure SDK clients using Microsoft Entra ID. Use for DefaultAzureCredential, managed identity, service principals, and developer credentials. Triggers: "Azure Identity", "DefaultAzureCredential", "ManagedIdentityCredential", "ClientSecretCredential", "authentication .NET", "Azure auth", "credential chain".

Azure Monitor Query SDK for Java. Execute Kusto queries against Log Analytics workspaces and query metrics from Azure resources. Triggers: "LogsQueryClient java", "MetricsQueryClient java", "kusto query java", "log analytics java", "azure monitor query java". Note: This package is deprecated. Migrate to azure-monitor-query-logs and azure-monitor-query-metrics.

Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics. Triggers: "azure-monitor-query", "LogsQueryClient", "MetricsQueryClient", "Log Analytics", "Kusto queries", "Azure metrics".

Use when authoring instruction sets for agents, skills, prompts, or custom instruction files. Produces enforceable, unambiguous instructions through 8-section template, conflict resolution clause, personas, and comprehensive examples.