productivity▌

Activate when the user wants to obtain data from a website:

Multi-market stock analysis with fundamental and technical evaluation across US, China A-shares, and Hong Kong equities. \n \n Covers fundamental metrics (P/E, P/B, ROE, margins, growth rates) and technical patterns (moving averages, support/resistance, momentum indicators) \n Generates structured analysis reports including valuation assessment, peer comparison, risk factors, and investment thesis \n Supports quick overview or deep-dive analysis modes with customizable focus areas \n Works with

Transforms raw user prompts into optimized prompts using 11 established frameworks. \n \n Analyzes task type, complexity, and clarity to intelligently select the best framework(s) for the job \n Supports 11 frameworks including RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, and GROW \n Operates in \"magic mode,\" silently selecting frameworks without exposing technical jargon to users \n Blends multiple frameworks for complex tasks spanning different dimens

Guide founders through early-stage sales, from first outreach to repeatable processes. \n \n Diagnose where deals stall (lead generation, qualification, discovery, closing, or implementation) and apply stage-specific strategies based on insights from 16 product leaders \n Emphasize founder-led sales as a learning phase, not a revenue phase; stay hands-on until you've closed ~$1M ARR with a documented, repeatable process \n Cover core tactics: manual personalized outreach over AI tools, diagnosti

Personalized 1-on-1 mastery tutor using Bloom's 2-Sigma method with adaptive pacing and Socratic questioning. \n \n Diagnoses learner level through targeted probing, then builds a structured concept roadmap with dependency tracking and mastery gates (80% threshold before advancing) \n Asks 1-2 questions per round, never giving direct answers; uses hint escalation and counter-examples to dismantle misconceptions rather than just correct wrong answers \n Generates interactive visual outputs: HTML

FlowIO is a lightweight Python library for reading and writing Flow Cytometry Standard (FCS) files. Parse FCS metadata, extract event data, and create new FCS files with minimal dependencies. The library supports FCS versions 2.0, 3.0, and 3.1, making it ideal for backend services, data pipelines, and basic cytometry file operations.

Context-driven code reviews prioritizing quality, security, testability, and maintainability. \n \n Organizes feedback into four priority levels: blockers (must fix), major issues (should fix), minor improvements, and suggestions, with clear templates and rationale for each \n Covers five core review areas: logic correctness, security risks, test coverage, performance issues, and error handling; explicitly excludes style nitpicking and formatting \n Recommends reviewing code in chunks under 400

Miscellaneous CTF techniques covering encoding, signal processing, sandbox escape, and system exploitation. \n \n Covers 20+ technique categories including Python/Bash jail escape, RF/SDR signal processing, DNS exploitation, Unicode steganography, QR codes, Z3 constraint solving, and WASM patching \n Includes quick-reference commands for common encodings (Base64, Base32, Hex, ROT13), IEEE-754 float data hiding, and cipher identification workflows \n Provides Linux privilege escalation techniques

Fetch and summarize arxiv papers from their LaTeX source code. \n \n Normalizes arxiv URLs to source format (/src/), downloads .tar.gz archives, and unpacks them locally with caching to avoid re-downloads \n Locates the LaTeX entrypoint (main.tex or equivalent) and recursively reads all relevant source files to reconstruct the full paper \n Generates markdown summaries in the local knowledge directory with contextual tags, designed for integration with the nanochat project \n Includes guidance f

A skill for creating new skills and iteratively improving them.