发现 Skills

Excel data-analysis multi-step orchestrator. Covers: (1) reading multi-sheet Excel files and counting rows, (2) large-file detection (≥10k rows → automatic Parquet optimization), (3) data cleaning (missing-value handling, text normalization, removal of invalid characters), (4) conditional filtering and category extraction, (5) cross-sheet statistical aggregation, (6) export to Excel/CSV and provide download links. Implements the full flow from data reading to report generation, orchestrating capability sub-skills step by step. **Proactively use this skill in any of the following situations; do not respond with just a few lines of pandas code**: ① The user uses trigger terms: Excel analysis / spreadsheet analysis / data analysis / data cleaning / data statistics / data filtering / data visualization / data export / summary statistics / pivot table / grouped statistics / cross analysis / trend analysis / comparative analysis / outlier detection / deduplication / missing value handling / Excel report / generate report / analyze Excel / data analysis / data cleaning / pivot table; ② The user uploads or specifies a .xlsx / .xls / .csv file and requests analysis, cleaning, statistics, or visualization; ③ The task involves any of: reading multiple sheets, conditional filtering, category aggregation, or chart generation; ④ The user requests exporting a formatted Excel report or a download link. Not for: pure text processing unrelated to tabular data, image analysis (use sn-da-image-caption), or simple single-formula Q&A.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) a command or operation fails unexpectedly, (2) a user corrects Claude (e.g., “No, that’s wrong…”, “Actually…”), (3) a user requests a capability that doesn't exist, (4) an external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) a better approach is discovered for a recurring task. Also review learnings before major tasks.

UI component conventions for 8-bit styled components. Use when working with shadcn/ui components or implementing retro-styled UI elements.

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.

This skill should be used when the user requests to create professional business documents (proposals, business plans, or budgets) from templates. It provides PDF templates and a Python script for generating filled documents from user data.

Fetches information from official GraalVM, Truffle, and Graal compiler documentation for API guidance, performance optimization, compiler flags, profiling, specializations, Bytecode DSL, Truffle DSL, partial evaluation, and compilation analysis. Use when you need authoritative documentation about the Truffle framework, GraalVM compiler options, or optimization techniques. Use when asking about the Truffle API, compiler flags, specialization patterns, or Graal options.

Google Apps Script development best practices learned from production. Use when building Apps Script automation, payment API integrations, Google Sheets menu functions, modal dialogs, or Poka Yoke quality gates. Covers UI dialog philosophy, API field discovery, submission architecture (source_amount vs transfer_amount), clasp CLI logging, and gate flow design.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Create minimal subtests to isolate and fix complex bugs. Use when a test fails and the issue is buried in complexity.

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

dontbesilent concept deconstruction. Using a Wittgenstein + Austrian economics approach to break fuzzy business concepts down to the atomic level. Triggers: /dbs-deconstruct, /拆概念, "deconstruct this concept", "what does this really mean"

dontbesilent business model diagnosis. Two modes: consultation (address your specific question) and checkup (break down and analyze your business model). Trigger: /dbs-diagnosis, "diagnose my business model", "I have a business question"

Creates unique web designs with brand identity, color palettes, typography, and modern UI/UX patterns. Use for brand identity development, visual design systems, layout composition, and responsive web design. Activate on "web design", "brand identity", "color palette", "UI design", "visual design", "layout". NOT for typography details (use typography-expert), color theory deep-dives (use color-theory-expert), design system tokens (use design-system-creator), or code implementation without design direction.

Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language prompts or code. Use when the user needs to interact with a webpage beyond simple scraping: logging into a site, submitting forms, clicking through pagination, handling infinite scroll, navigating multi-step checkout or wizard flows, or when a regular scrape failed because content is behind JavaScript interaction. Also useful for authenticated scraping via profiles. Triggers on "interact", "click", "fill out the form", "log in to", "sign in", "submit", "paginated", "next page", "infinite scroll", "interact with the page", "navigate to", "open a session", or "scrape failed".

USE WHEN the user wants to manage calendars and events via the `gws` CLI.

Transform extracted engineer expertise into an actionable skill with progressive disclosure, allowing agents to find and apply relevant patterns for specific tasks.

This skill enables Claude to generate CI/CD pipeline configurations for various platforms, including GitHub Actions, GitLab CI, and Jenkins. It is used when a user requests the creation of a CI/CD pipeline, specifies a platform (e.g., "GitHub Actions"), or mentions specific pipeline stages like "test," "build," "security," or "deploy." This skill is also useful when the user needs to automate software delivery, integrate security scanning, or set up multi-environment deployments. The skill is triggered by terms such as "CI/CD pipeline," "GitHub Actions pipeline," "GitLab CI configuration," or "Jenkins pipeline."

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving. Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces. This skill helps discover and use resources via `datasets`, `transformers`, the HF Inference API, `gradio_client`, and methodology citations.

Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information. Note: query text is transmitted to api.parallel.ai (PARALLEL_API_KEY) and, for academic searches, to openrouter.ai (OPENROUTER_API_KEY).

Define how system components connect, establishing boundaries, patterns, and integration approaches during PRD v0.6 Architecture. Triggers on requests to design architecture, create system design, define component relationships, or when a user asks "design architecture", "system design", "how do components connect?", "architecture decisions", "technical architecture", "system overview". Consumes TECH- (stack selections), RISK- (constraints/high-priority risks), FEA- (feature requirements). Outputs ARC- entries documenting architecture decisions with rationale. Feeds the v0.6 Technical Specification.