发现 Skills

Unit testing with mocks, integration testing, LangSmith evaluation, benchmarking

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

Provides patterns for unit testing caching behavior using Spring Cache annotations (@Cacheable, @CachePut, @CacheEvict). Use when validating cache configuration and cache hit/miss scenarios.

Interview a user in-depth about an epic, task, or spec file to extract complete implementation details. Use when a user wants to flesh out a spec, refine requirements, or clarify a feature before building. Triggers on /flow-next:interview with Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2) or file paths.

Scans the agent's skills folder for malicious patterns, prompt injections, and unauthorized data exfiltration risks.

Comprehensive guide for Algorand Python (PuyaPy) smart contract development — contract building with decorators, storage, transactions, types, AlgoKit Utils, ARC standards, and troubleshooting. This is the parent skill for all Python-specific Algorand content. Use when writing Python contract code, working with algopy decorators, understanding Algorand Python storage patterns, using AlgoKit Utils in Python, or troubleshooting Python-specific errors. Strong triggers include "Algorand Python", "PuyaPy", "algopy", "ARC4Contract", "@arc4.abimethod", "GlobalState Python", "BoxMap Python", "algokit_utils Python", "pip install algokit-utils", "Python contract", "Python smart contract".

Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.

Gene Ontology over-representation analysis using clusterProfiler::enrichGO. Use when identifying biological functions enriched in a gene list from differential expression or other analyses. Supports all three ontologies (BP, MF, CC), multiple ID types, and customizable statistical thresholds.

End-to-end GWAS workflow from VCF to association results. Covers PLINK QC, population structure correction, and association testing for case-control or quantitative traits. Use when running genome-wide association studies.

Protein quantification from mass spectrometry data including label-free (LFQ, intensity-based), isobaric labeling (TMT, iTRAQ), and metabolic labeling (SILAC) approaches. Use when extracting protein abundances from MS data for differential analysis.

Performs a structured code and documentation review using a severity-tiered findings format. Use when the user says "CR", "code review", or "perform a review". Produces a numbered findings report, waits for terse directives (fix/stet/GH), then implements and commits approved changes.

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

Expert code refactoring for Java, JavaScript, and React projects. Focuses on SOLID principles, design patterns, and idiomatic improvements while ensuring test stability.

Use Osterwalder's Value Proposition Canvas to systematically achieve product-market fit by matching your products and services to customer jobs, pains, and gains Use when: **Launching a new product or service** and need to validate the value proposition; **Struggling with product-market fit** and need to diagnose why customers aren't buying; **Repositioning an existing offering** to better meet customer needs; **Entering a new market segment** with different customer requirements; **Developin...

Perform a codebase readiness and technical debt analysis covering scale metrics, type safety, dead code, test coverage, complexity hotspots, and dependency vulnerabilities. Use this skill whenever the user asks for a code health check, codebase readiness assessment, technical debt review, pre-launch audit, or wants to understand the overall quality and risk profile of a codebase. Also trigger when the user asks about dead code, test coverage gaps, complexity hotspots, or dependency vulnerabilities as part of a broader audit. Produces 6 structured section files plus a consolidated report ready to include in a client deliverable.

This Skill is an **example template** for smart home control plugins. Smart home manufacturers can refer to this structure to provide their own Skills.

Use when designing or rewriting a high-converting SaaS pricing page (structure, plan design, copywriting, SEO/AEO, FAQs, layout patterns, experiments). Includes checklists, templates, and common pitfalls.

Use when reviewing Android code (own or others'). Five-axis review framework: Correctness, Readability, Architecture, Security, Performance. Categorized findings with Kotlin/Compose-specific checks.

Use before creative or design work — features, components, new behaviors, or pipeline briefs that need refinement before a spec exists. Loaded by creating-a-pipeline Phase 0 when the user's request is exploratory or under-specified.

从模糊的用户需求中提取领域概念——实体、流程和"暗物质"（用户没说的）。基于 DDD（领域驱动设计）方法论。

Take photos using the device camera on connected edge devices

Safe sandboxed self-evolution engine with 5-layer safety, automatic rollback, and evolution dashboard

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

Build production-ready Web3 applications, smart contracts, and decentralized systems. Implements DeFi protocols, NFT platforms, DAOs, and enterprise blockchain integrations. Use PROACTIVELY for smart contracts, Web3 apps, DeFi protocols, or blockchain infrastructure.