发现 Skills

Common patterns for the podverse-management-api Express application

Use when the user invokes $fix-pr or asks Codex to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports.

Guidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating functions or arguments, (3) Renaming functions or arguments, (4) Superseding functions, (5) Marking functions as experimental, (6) Understanding lifecycle stages (stable, experimental, deprecated, superseded), or (7) Writing deprecation helpers for complex scenarios.

Coding patterns extracted from OpenAI Codex Rust codebase - a production CLI/agent system with strict error handling, async patterns, and workspace organization

This skill should be used when the user wants to "create a skill", "add a skill", "write a new skill", "build a skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code.

API gateway testing skill covering rate limiting validation, request routing, authentication proxy testing, load balancing verification, circuit breaker testing, and gateway configuration validation for Kong, Envoy, and AWS API Gateway.

Freeze a module so future edits trigger advisory warnings until explicitly unfrozen. Use to mark a module post-incident as do-not-touch without review.

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

AI-assisted pair programming with multiple modes (Driver/Navigator/Switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.

AQE skill

Guide collection and analysis of performance traces. Use when a mid-level developer needs to diagnose slowness.

The correct way to handle dragging, scaling, and boundary detection of 3D models in Three.js. Addresses issues such as mouse movement not syncing with model movement and only part of the model being visible after scaling.

Data modeling with Entity-Relationship Diagrams (ERDs), data dictionaries, and conceptual/logical/physical models. Documents data structures, relationships, and attributes.

Prioritization techniques including MoSCoW, Kano model, weighted scoring, and value-effort matrices. Ranks requirements, features, backlog items, and investment decisions.

Use when encountering TypeScript any types, type errors, or lax type checking - eliminates type holes and enforces strict type safety through proper interfaces, type guards, and module augmentation

Provide repeatable CRUD workflows for Spring Boot 3 services with Spring Data JPA and feature-focused architecture; apply when modeling aggregates, repositories, controllers, and DTOs for REST APIs.

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.

Implement or extend a user-facing workflow in a web application, integrating with existing backend APIs. Use when the feature is primarily a UI/UX change backed by existing APIs, affects only the web frontend, and requires following design system, routing, and testing conventions.

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

View the repository's strategy backtest summaries. Called when a user asks about historical win rate / “backtest with X strategy” / which strategy has performed well recently / whether a previous analysis for this stock was accurate / system-wide backtest metrics / what strategies are available. The CLI has three modes: overall / by-strategy / by-stock, plus --list-strategies to list 11 built-in strategies. **Read-only: only reads existing evaluations and will not trigger new backtests**; if the project has no backtests yet, return an informational prompt and honestly tell the user. **No LLM_API_KEY required**.

Run code reviews with the Codex CLI /review command. Use cases: (1) PR reviews, (2) review of uncommitted changes, (3) branch-diff reviews, (4) security and quality checks. Triggers: codex-review, /codex-review, cr

This skill should be used when creating, applying, listing, or managing database migrations in Supabase projects, or when making DDL schema changes that need to be tracked. Trigger when: "create migration", "apply migration", "list migrations", "migration history", "schema change", "DDL change", "supabase migration new", "supabase db push", "migration best practices", "migration drift", "repair migration", "squash migrations", "migration workflow", "database versioning", or any tracked schema modification.

Configure how resource fields are rendered in forms, show pages, and tables