skills

Use when building, redesigning, or polishing frontend screens, UI components, web apps, dashboards, landing pages, games, or interactive tools where visual quality, interaction feel, responsive layout, or product fit matters.

Use when writing, reviewing, pruning, or refactoring tests and there is risk of low-value tests, implementation-detail assertions, over-mocking, redundant coverage, brittle setup, or tests that do not protect a real public contract.

Use when the user explicitly asks for deep research / 深度研究 / 深入调研, or when they need evidence-driven, multi-source research for a decision, report, due diligence, current-state analysis, technical comparison, recommendation, or contested/high-stakes question.

Use when the user asks for a non-fiction book summary, 高保真读书笔记, 拆书, 导读, argument map, chapter study guide, application manual, reading route, critical evaluation, multi-book synthesis, or interactive book-learning dialogue.

Use when rewriting, editing, or drafting prose so it sounds specific, situated, and human rather than generic, over-polished, or AI-like. Works for Chinese and English prose, messages, essays, fiction, dialogue, memoir-like writing, public copy, and explanatory text. Focuses on voice, reader effort, scene logic, uneven human rhythm, and concrete context. Avoids template tone, consultant phrasing, fake warmth, excessive symmetry, moral summaries, and detector-gaming.

Find evidence-backed architecture deepening opportunities in a codebase. Use when the user wants to improve architecture, find refactoring opportunities, consolidate shallow or tightly-coupled modules, improve testability, or make a repository easier for AI agents to navigate.

Use when producing an equity, company, sector, industry, ETF, basket, or theme investment research report for internal discussion, especially when the user needs a testable thesis, valuation view, risk framework, investment plan, or review framework.

Use when working with GitHub from the command line, especially repositories, issues, pull requests, reviews, Actions, projects, releases, API calls, or GitHub-specific automation.

Use when the user provides raw interviews, meeting notes, or scattered product requirements and needs a developer-friendly requirement and architecture report, optionally with issue-shaped implementation briefs. Prioritizes entities, state machines, vertical slices, edge cases, and plain language.

Use when creating text-only diagrams in markdown, code comments, chat, or terminal output and you need stable rendering across fonts, platforms, and narrow viewports.

Use when the user asks complex medical, pharmacological, or biomedical research questions. Provides evidence-based, high-signal-to-noise ratio consulting for clinical or research scenarios, strictly adhering to medical rigor, quantitative data, and specific formatting constraints.

Use when the user asks complex financial, wealth management, macro-economic, or quantitative investment questions. Provides high-signal-to-noise, objective, and probabilistically rigorous consulting, strictly avoiding financial fluff and formatting with dense paragraphs instead of lists.

Use when the user asks deep philosophical, cognitive, ethical, or interdisciplinary questions. Bridges science and humanities using analytic philosophy, evolutionary biology, and physics. Strictly enforces logical rigor, denoises cultural metaphors, and outputs dense, paragraph-based academic prose.

Use when the user wants a local Codex token usage daily, weekly, or monthly report, trend table, spike analysis, or terminal summary from ~/.codex data.

Use when the user provides raw meeting transcripts, audio-to-text logs, or messy conversation records and requests a structured, professional, and concise executive summary. This skill prioritizes noise reduction, action items, and adapting to the transcript's source language.

Use when the user wants to turn structured data into a chart image or map by selecting a chart type, shaping arguments from the chart references, and issuing an HTTP request to the chart rendering service.

Use when the user wants a daily work summary generated from Codex threads, inserted into an Obsidian daily note, or written as a timeline-style engineering report grounded in thread evidence.

Use when the user wants a git commit created or needs a commit message that should match the repository's existing language and Conventional Commit style.

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to install/search/generate skills, or needs to set up Context7 for their AI coding agent.

Use when the user wants a fast but comprehensive understanding of an unfamiliar repository, including its purpose, architecture, stack, key workflows, and recent engineering direction.

Use when the user wants to add a todo to today's Obsidian daily note, create today's daily note if it does not exist, or locate an Obsidian vault automatically before writing a task.