Find the perfect capability for your agent.
How FabLL (faebryk.core.node) maps Python node/trait declarations into the TypeGraph + instance graph, including field/trait invariants and instantiation patterns. Use when defining new components or traits, working with the Node API, or understanding type registration.
How the Zig↔Python binding layer works (pyzig), including build-on-import, wrapper generation patterns, ownership rules, and where to add new exported APIs. Use when adding Zig-Python bindings, modifying native extensions, or debugging C-API interactions.
Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.
Create new Harbor Boost modules — the Python plugins that run inside Harbor's LLM proxy. Use this skill whenever the user wants to build a Boost module, write a custom module for Harbor Boost, add a new feature to the Boost proxy pipeline, or create any kind of middleware that transforms, augments, or intercepts LLM chat completions in Harbor. Also triggers when the user mentions "boost module", "boost plugin", "custom module for boost", or wants to add prompt engineering, reasoning chains, or output transforms to Harbor's proxy layer.
Model cap table dilution, SAFE conversion, and exit waterfall across scenarios. Triggered by: "/venture-capital-intelligence:cap-table-waterfall", "model my cap table", "simulate dilution", "SAFE conversion math", "exit waterfall", "how much do I own after Series A", "liquidation waterfall", "cap table scenario", "what happens to equity at exit", "model the waterfall", "how much equity do I have left", "what is my ownership after funding", "run dilution scenarios", "model a new round", "what happens at acquisition", "cap table after SAFE conversion", "pari passu waterfall", "preference stack analysis". Claude Code only. Requires Python 3.x.
Run deterministic financial models for startup valuation and SaaS health analysis. Triggered by: "/venture-capital-intelligence:financial-model", "run a financial model on X", "DCF this company", "model the financials", "calculate runway", "what is the valuation", "SaaS metrics model", "LTV CAC analysis", "unit economics", "burn rate analysis", "comparable valuation", "how long is my runway", "what's my burn multiple", "revenue projection for X", "model the ARR growth", "what is the pre-money valuation", "comps analysis", "NRR and churn model", "how healthy are these SaaS metrics". Claude Code only. Requires Python 3.x. Accepts user-supplied numbers or searches for publicly available data.
Compute fund KPIs (TVPI, DPI, IRR, MOIC), model carried interest and management fees, and generate LP quarterly update narratives. Triggered by: "/venture-capital-intelligence:fund-operations", "calculate fund KPIs", "what is my fund TVPI", "IRR calculation", "compute MOIC", "LP report", "quarterly update draft", "carried interest calculation", "management fee calculation", "fund performance report", "write my LP update", "how is my fund performing", "what is my DPI", "fund returns analysis", "model my carry", "how much carry do I earn", "portfolio performance summary", "generate investor update". Claude Code only. Requires Python 3.x.
Run TAM/SAM/SOM market sizing with top-down and bottom-up methods, competitive landscape, and tech stack analysis. Triggered by: "/venture-capital-intelligence:market-size", "size this market", "what is the TAM for X", "market sizing analysis", "competitive landscape for X", "who are the competitors", "TAM SAM SOM for X", "market opportunity analysis", "how big is this market", "is this market big enough", "what's the addressable market", "total addressable market for X", "how large is the opportunity", "market research for X", "how saturated is this market", "market size estimate", "go-to-market sizing", "what is the serviceable market". Claude Code only. Requires Python 3.x. Uses web search for market data.
Deterministic Python-scored startup screening with full audit trail. Use when you need a reproducible, weighted-score verdict on a startup — not just a qualitative opinion. Triggered by: "/venture-capital-intelligence:hard-screening-startup", "hard screen this startup", "run a hard screen on X", "score this startup with Python", "give me an auditable screen", "run a scored evaluation on X", "give me a weighted score for this startup", "screen with numbers", "objective startup score", "reproducible screen", "investment scorecard for X", "score this company out of 100", "run the full screen on X". Claude Code only. Requires Python 3.x. For conversational soft-mode screening, use /venture-capital-intelligence:soft-screening-startup.
Search, reserve, inspect, and cancel KTX or Korail tickets in Korea with the korail2 + pycryptodome Python packages. Use when the user asks for KTX seats, Korail bookings, train changes, or reservation status.
Drop-in pandas replacement with ClickHouse performance. Use `import chdb.datastore as pd` (or `from datastore import DataStore`) and write standard pandas code — same API, 10-100x faster on large datasets. Supports 16+ data sources (MySQL, PostgreSQL, S3, MongoDB, ClickHouse, Iceberg, Delta Lake, etc.) and 10+ file formats (Parquet, CSV, JSON, Arrow, ORC, etc.) with cross-source joins. Use this skill when the user wants to analyze data with pandas-style syntax, speed up slow pandas code, query remote databases or cloud storage as DataFrames, or join data across different sources — even if they don't explicitly mention chdb or DataStore. Do NOT use for raw SQL queries, ClickHouse server administration, or non-Python languages.
In-process ClickHouse SQL engine for Python — run ClickHouse SQL queries directly on local files, remote databases, and cloud storage without a server. Use when the user wants to write SQL queries against Parquet/CSV/ JSON files, use ClickHouse table functions (mysql(), s3(), postgresql(), iceberg(), deltaLake() etc.), build stateful analytical pipelines with Session, use parametrized queries, window functions, or other advanced ClickHouse SQL features. Also use when the user explicitly mentions chdb.query(), ClickHouse SQL syntax, or wants cross-source SQL joins. Do NOT use for pandas-style DataFrame operations — use chdb-datastore instead.
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields, Instructions for searching arXiv papers using Python script and shell tool. Read SKILL.md to learn the workflow.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
流水线插件开发完整指南，涵盖插件创建、task.json 配置规范、多语言开发示例（Python/Java/NodeJS/Golang）、输入输出规范、错误码规范、发布流程、调试方法。当用户需要开发蓝盾流水线插件、配置 task.json、处理插件输入输出或排查插件错误时使用。
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Team code quality checklist - use for checking Python code quality, bugs, security issues, and best practices
Generate comprehensive pytest tests - use when generating tests, creating test suites, or testing Python code
