发现 Skills

Evaluate representation and flag potential harm concerns. Use when writing characters from marginalized groups, depicting sensitive subject matter, or wanting to check for stereotypes and harmful tropes.

Maintain a wiki-style world bible for collaborative fiction. Use for long-running story worlds, shared universes, membership sites, or any fiction requiring persistent canonical reference.

Systematically evaluate completed short stories or novel chapters to identify strengths, weaknesses, and improvement opportunities. Use after drafting to assess whether the piece achieves its narrative goals.

Diagnose what any story needs regardless of its current state. This skill should be used when a writer is stuck, evaluating story problems, when narrative feels broken, or when someone asks 'what's wrong with my story?'. Keywords: story, diagnosis, stuck, narrative, plot, character, worldbuilding, revision.

Build worlds through cascading consequences from speculative changes. Use when introducing new technologies, species, or alternate histories and need to trace realistic societal transformations across multiple domains.

A skill that makes a kebab for the user.

Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file I/O, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Use this skill when reasoning about deep tech commercialization, biomedical engineering, drug delivery, material design, or overcoming institutional skepticism. Robert Langer, MIT professor and pioneer of drug delivery systems, approaches problems through first-principles engineering, interdisciplinary convergence, and relentless perseverance against consensus. Trigger this skill whenever the user is evaluating high-risk/high-reward research, deciding between incremental vs. paradigm-shifting impact, spinning out academic discoveries into startups, or designing physical/biological systems from scratch. Apply his frameworks to navigate patenting, funding, and translating lab science into real-world impact.

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1–100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Style, review, and refactoring standards for C#/.NET codebases. Trigger when `.cs`, `.csproj`, `.sln`, `.props`, `.targets`, or `.razor` artifacts are created, modified, or reviewed and C#-specific quality rules (naming, nullability, async patterns, API design consistency) must be enforced. Do not use for Java/Kotlin or JavaScript/TypeScript style concerns unless C# artifacts are also changed. In multi-language pull requests, run together with other applicable `*-style-guide` skills.

Extract text from PDFs/scans (pymupdf, marker-pdf).

使用 TimeProvider 測試時間相依邏輯的專門技能。當需要測試 DateTime、控制時間流逝、處理時區轉換、測試過期邏輯時使用。涵蓋 TimeProvider 抽象化、FakeTimeProvider 時間控制、時間凍結與快轉等。 Make sure to use this skill whenever the user mentions DateTime testing, TimeProvider, FakeTimeProvider, time-dependent logic, cache expiration, or token expiration testing, even if they don't explicitly ask for time testing guidance. Keywords: datetime, time testing, 時間測試, TimeProvider, FakeTimeProvider, DateTime.Now, 時間相依, 快取過期, token 過期, Microsoft.Bcl.TimeProvider, GetUtcNow, SetUtcNow, Advance, time freeze, 時間凍結, 時間快轉

Use when working with ESP32 firmware or IoT hardware projects — covers PlatformIO build system, I2S audio, WiFi/BLE patterns, memory management, and state machine design

Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

RSA (Rivest–Shamir–Adleman) is the most widely used asymmetric cryptographic algorithm for digital signatures, key exchange, and encryption. This skill covers generating, storing, rotating, and managing RSA key pairs in accordance with the NIST SP 800-57 key management guidelines, including key serialization formats (PEM, DER, PKCS#8), password protection, and key strength validation.

Use when the user shares a fleeting thought, discovery, or reflection to categorize and log it in the current day's daily note.

Use when the user wants to initialize or audit GitHub repository best practices — branch protection, CODEOWNERS, PR templates, Dependabot, and CI/CD foundations.

When the user wants to build digital twins, simulate supply chain operations, or create virtual replicas for testing. Also use when the user mentions "digital twin," "simulation modeling," "discrete event simulation," "system simulation," "virtual supply chain," "what-if analysis," "scenario simulation," or "operational testing." For network optimization, see network-design. For forecasting, see demand-forecasting.

Comprehensive naming convention guide for TypeScript and Angular applications. Covers casing rules (camelCase, PascalCase, UPPER_CASE), prefix conventions (I for interfaces, _ for private, T for generics), boolean naming, the S-I-D principle (Short, Intuitive, Descriptive), context duplication, and structured naming patterns (P/HC/LC for variables, A/HC/LC for functions). Use when writing, reviewing, or refactoring TypeScript code. Triggers on tasks involving naming, variables, functions, interfaces, or code style.