发现 Skills

Tasmota firmware management for ESP8266/ESP32 devices. Flash firmware, configure WiFi, MQTT, device templates, rules, and automation. Use when working with Tasmota, ESP devices, smart plugs, switches, sensors, Sonoff devices, or custom IoT hardware flashing and configuration.

Use when implementing authentication or authorization — JWT/OAuth/session management, RBAC guards, secure cookie handling, OWASP best practices.

Use when deploying a React app or setting up a server — provisions VPS, configures Nginx reverse proxy, SSL certificates, domain DNS, and firewall rules.

Tell jokes and make the user laugh. Use when: the user asks for a joke, wants humor, says "make me laugh", or the mood is light. Don't use when: the user is asking a serious question or wants comedy recommendations (use the movie-tv skill).

Create distinctive, non-generic UI designs with aesthetic direction and wireframes. Use when asked to "design the UI", "create a layout", "wireframe this", or when building UI that should be memorable rather than generic. Avoids AI slop patterns.

Exploratory QA of web apps: find bugs, evidence, reports.

Debug Python: pdb REPL + debugpy remote (DAP).

Toolkit for testing web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing screenshots, or viewing browser logs.

Real-time sedimentation of reusable writing insights generated in the conversation into the project guideline document, maintaining consistent terminology, stable structure, verifiability, and reproducibility. The guideline document path must be specified when invoked. Used for user requests such as "update project guideline/synchronize guideline/sediment insights into guideline" and other scenarios.

AstrBot QQ bot plugin development guide. Covers plugin structure, decorators, message handling, LLM integration, config system, data persistence. Use when developing AstrBot plugins or QQ bot plugins with OneBot protocol.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Use this skill when users ask about benchmarking Clojure code, measuring performance, profiling execution time, or using the criterium library. Covers the 0.5.x API including bench macro, bench plans, viewers, domain analysis, and argument generation.

Comprehensive literature search with automatic summarization, trend analysis, and key paper identification from PubMed and preprints. Use this skill for literature review, trend identification, key paper discovery, and staying current with research developments. Keywords: literature, PubMed, papers, search

Human Made CSS and SCSS standards. Apply when writing styles, reviewing CSS/SCSS, or working on theme styling. Covers BEM naming, CSS custom properties, theme.json integration, and Stylelint configuration.

Complete HUMMBL Base120 mental models framework with all 120 models across six transformation families (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, an application methodology, and a validation checklist. Version 1.0-beta definitive reference.

This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Draft GitHub issues for i-am-bee/agentstack. Use when the user wants to report a bug, request a feature, or draft a general GitHub issue.

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Collaborate with Codex CLI to iteratively analyze, plan, and solve complex coding problems through multiple rounds of expert feedback. Use when analyzing complex codebases with multiple approaches, validating implementation plans, or solving problems that benefit from expert validation.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, provide confidence scores, and support virtual screening for structure-based drug design. Not for affinity prediction.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

Send commands to Hubitat devices or interact with app instances