发现 Skills

Windows 11 system management

Revise scientific papers, manuscripts, and research proposals using principles from Writing Science (Schimel), scientific writing best practices, and structured editorial frameworks. Use this skill whenever a user asks you to review, revise, edit, critique, or improve a scientific paper, research manuscript, journal article, grant proposal, thesis chapter, or academic writing of any kind. Also trigger when users say things like 'make my paper better', 'help me polish this manuscript', 'review my draft', 'edit my Introduction/Discussion/Methods', 'tighten my writing', or 'prepare this for submission'. This skill applies even if the user only shares a single section (e.g., just an Abstract or Introduction). If the user mentions scientific or academic writing quality in any way, use this skill.

Evidence-driven, section-by-section CS/AI/ML paper drafting orchestrator with Draft→Quality Gate→Verification loop. Coordinates evidence audit, citation, experiments, polishing, review, and figure generation.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Z.ai API integration for building applications with GLM models. Use when working with Z.ai/ZhipuAI APIs for: (1) Chat completions with GLM-4.7/4.6/4.5 models, (2) Vision/multimodal tasks with GLM-4.6V, (3) Image generation with GLM-Image or CogView-4, (4) Video generation with CogVideoX-3 or Vidu models, (5) Audio transcription with GLM-ASR-2512, (6) Function calling and tool use, (7) Web search integration, (8) Translation, slide/poster generation agents. Triggers: Z.ai, ZhipuAI, GLM, BigModel, Zhipu, CogVideoX, CogView, Vidu.

Client group welcome-script generator — combines a senior accountant identity anchor + industry pain-point insights + minimalist conventions

Turn any markdown file into a publication-quality PDF. Proper 1in margins, intelligent page breaks, page numbers, cover pages, running headers, curly quotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft artifact — a finished artifact. Use when asked to "make a PDF", "export to PDF", "turn this markdown into a PDF", or "generate a document". (gstack) Voice triggers (speech-to-text aliases): "make this a pdf", "make it a pdf", "export to pdf", "turn this into a pdf", "turn this markdown into a pdf", "generate a pdf", "make a pdf from", "pdf this markdown".

Modern shell prompt configuration with Powerlevel10k and Zsh Vi Mode. Use when configuring shell prompts, setting up vi/vim keybindings in zsh, customizing cursor styles per mode, adding mode indicators, optimizing prompt performance, or troubleshooting slow prompts. Covers P10k instant prompt, vi mode plugins, and cursor customization.

Modern HTML5 and CSS3 patterns for semantic markup, layout systems, responsive design, accessibility, and production-ready styling conventions

Ultra-fast validation library for TypeScript/JavaScript (77x faster than Zod). Use when building validated schemas for APIs, forms, or data processing. Provides Zod 4-compatible API with WASM-powered SIMD validation.

Create and manipulate PowerPoint PPTX files programmatically. Use when the user needs to generate presentations, modify PPTX templates, extract slide content, create thumbnail previews, or automate PowerPoint workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: PowerPoint, PPTX, presentation, slides, template, deck, slideshow, corporate, branding.

Help neurodivergent users break down overwhelming tasks into manageable steps. Use when tasks feel paralyzing, when executive function is struggling, when someone can't start, or when the Wall of Awful has built up. Applies ADHD/autism-aware decomposition strategies.

Generate stories about institutional outcasts given impossible mandates with minimal resources. Use when you want team dynamics in hostile institutions, David vs. Goliath within organizations, or narrative tension from constraint-driven creativity.

Create repository classes implementing the repository pattern with Protocol interfaces, ORM separation, and mapper integration for clean data access.

Generates unit and integration tests for a function, class, or module — covering happy path, edge cases, error cases, and boundary conditions. Supports common frameworks (Jest, Vitest, Pytest, Go testing, JUnit, RSpec). Use this skill when the user asks to "write tests for this", "add test coverage", "what tests should I add", or pastes code that lacks tests.

BMAD Method: Validate an existing PRD against BMAD standards for completeness, clarity, and quality. Use when user says "validate PRD", "VP", "review PRD", "check PRD", or wants to verify their PRD meets quality standards. Phase 2 Planning workflow.

Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series models (ARIMA, SARIMAX, VAR) use statsmodels; for time series classification/clustering use aeon.

Applies the reasoning, principles, and mental models of Sebastian Thrun (robotics and self-driving car pioneer; founder of Google X, Waymo, Udacity; Stanford professor). Use this skill when Claude is asked to advise on hardware/software systems engineering, autonomous vehicles, moonshot ideation, probabilistic robotics (SLAM), or leading high‑stakes engineering teams. Trigger it for discussions about democratizing education, regulating AI, moving from academic research to product development, or managing technical teams with empathy. Use it to shift attention from incremental component debates to end‑to‑end execution and audacious goals.

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.