发现 Skills

Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.

Developer reference for GoHighLevel API v2 — OAuth 2.0, private tokens, endpoint reference, rate limits, webhooks, and building marketplace apps.

Narrative RPG game master for collaborative storytelling. Use for tabletop RPG sessions, solo narrative games, or any real-time collaborative fiction requiring scene management, NPC portrayal, and story coherence.

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.

Pythonic wrapper around RDKit with a simplified interface and sensible defaults. Preferred for standard drug discovery tasks including SMILES parsing, standardization, descriptor calculation, fingerprints, clustering, 3D conformer generation, and parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use RDKit directly.

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

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".

Private 與 Internal 成員測試策略指南。當需要測試私有或內部成員、設定 InternalsVisibleTo 或評估可測試性設計時使用。涵蓋設計優先思維、反射測試、策略模式重構、AbstractLogger 模式與決策框架。 Make sure to use this skill whenever the user mentions private method testing, internal testing, InternalsVisibleTo, reflection testing, or testability design, even if they don't explicitly ask for testing strategy guidance. Keywords: private method testing, internal testing, InternalsVisibleTo, 私有方法測試, 內部成員測試, 反射測試, reflection testing, GetMethod BindingFlags, Meziantou.MSBuild.InternalsVisibleTo, 可測試性設計, 策略模式重構, testability

Use when creating new skills, updating existing skills, or packaging skills for distribution.

Used after design completion to generate detailed implementation tasks for engineers who are largely unfamiliar with the codebase. The output is an implementation plan that includes exact file paths, complete code examples, and verification steps, assuming the engineer has minimal domain knowledge.

Skript-reflect addon for Skript - powerful reflection and element manipulation capabilities

Manages ServiceNow update sets. Use for creating, retrieving, previewing, committing. Triggers - customizations, deployments.

When the user wants to create or update their product marketing context document. Also use when the user mentions "product context," "marketing context," "positioning," or wants to avoid repeating foundational information across marketing tasks. Creates a context file that other marketing skills reference.

Implement reactive state management with Effect Atom for React applications

Decide between Context Tag witness and capability patterns for dependency injection, understanding coupling trade-offs

A skill to create auth service for new applications.

Write formal laws and covenants for codebases using proper legal-style structure. Use when establishing inviolable standards, architectural constraints, or domain-specific rules that must be followed without exception.

Guidance for writing `@kubb/react-fabric` components and generators (React-based and function-based).

Durable workflow orchestration with Temporal for distributed systems across Java 21, Python 3.14, and NestJS 11.x. Covers Workflow vs Activity separation, Saga pattern, Entity workflows, Fan-out/Fan-in, determinism constraints, retry policies, and idempotency. Use when building long-running, failure-resilient distributed business processes.

Add UI automation tests to Trail-Sense Android app using AutomationLibrary. Use when asked to create, add, write, or implement automated tests, UI tests, integration tests, or androidTests for Trail Sense tools. Covers test class structure, AutomationLibrary functions, and testing patterns.

Captures screenshots of selected Axure prototype pages and converts each page into a Markdown spec document via vision analysis. Triggers when a user provides an Axure Share URL and requests spec extraction, e.g. "/parsing-axure https://xxxx.axshare.com/".

Use the phab CLI for Phabricator task management, code review workflows, revision creation and updates, with Git integration and auto-detection features.

Evaluate multimodal AI agents that process images, audio, PDFs, or other files. Sets up evaluations using LangWatch's LLM-as-judge with image inputs, Scenario's multimodal testing, and document parsing evaluation patterns. Use when your agent handles non-text inputs.